XMemo

yonro/memory-os-cli

Gives Claude and other AI agents a persistent, user-owned memory layer over remote MCP. The CLI handles OAuth login via xmemo.dev, writes config for Codex, Cursor, Copilot, Gemini, and Antigravity without embedding tokens, and optionally installs behavior profiles that nudge agents to search memory before starting work and save context after decisions. Uses streamable HTTP transport with stable agent instance IDs and zero telemetry. Reach for this when you want conversation history and project context to survive across sessions and tools without scattering state into each editor's isolated storage. The token flow supports both device login and manual credential injection.

tools: 49
auth: Secret needed
transport: STDIO, HTTP
env vars: 2
last updated: Sep 25, 2026

View on GitHub

Tools

49 tools

Public tool metadata for what this MCP can expose to an agent.

get_mcp_identityCheck XMemo connection status and the connected account/agent. Call this when the user asks whether XMemo is connected.

Check XMemo connection status and the connected account/agent. Call this when the user asks whether XMemo is connected.

No parameter schema in public metadata yet.

store_memoryLow-level memory write with full field control. Use only when a caller needs explicit field-level control; for normal conversational capture use remember.17 params

Low-level memory write with full field control. Use only when a caller needs explicit field-level control; for normal conversational capture use remember.

Parameters* required

agent_idstring

Optional client-supplied agent label for memory attribution.default:

agent_instance_idstring

Optional stable, non-secret agent instance ID for per-client attribution.default:

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: public

confidencenumber

Confidence score for the saved or updated memory, from 0.0 to 1.0.default: 1

contentstring

Text body to save, such as a memory, TODO/action item, event note, or state summary.

device_idstring

Optional client-supplied device identifier for attribution.default:

device_labelstring

Optional human-readable device label for attribution.default:

embedding_jsonstring

Optional JSON array or object containing a precomputed embedding; leave blank for normal use.default:

expires_atstring

Optional ISO 8601 expiration timestamp for the memory.default:

importancenumber

Importance score for the saved or updated memory, from 0.0 to 1.0.default: 0.5

memory_typestring

Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %.default: semantic

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

pathstring

A simple user-facing category or path for this memory, such as preferences, projects/xmemo, or personal/travel.

provenance_jsonstring

Optional JSON object string describing memory source, evidence, or attribution.default: {}

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

semantic_keystring

Optional stable semantic key used to identify or upsert a memory concept.default:

team_idstring

Optional team/workspace identifier for team-scoped memory access.default:

rememberSave a memory so it can be recalled in future conversations. Call this whenever the user states a durable fact, preference, instruction, identity or profile detail, project detail, or recurring workflow likely useful later — you do not need an explicit 'remember this'. Skip tr...19 params

Save a memory so it can be recalled in future conversations. Call this whenever the user states a durable fact, preference, instruction, identity or profile detail, project detail, or recurring workflow likely useful later — you do not need an explicit 'remember this'. Skip tr...

Parameters* required

agent_idstring

Optional client-supplied agent label for memory attribution.default:

agent_instance_idstring

Optional stable, non-secret agent instance ID for per-client attribution.default:

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: public

confidencevalue

Confidence score for the saved or updated memory, from 0.0 to 1.0.

contentstring

Text body to save, such as a memory, TODO/action item, event note, or state summary.

dedupeboolean

Whether to check for and merge likely duplicate memories before saving.default: true

device_idstring

Optional client-supplied device identifier for attribution.default:

device_labelstring

Optional human-readable device label for attribution.default:

embedding_jsonstring

Optional JSON array or object containing a precomputed embedding; leave blank for normal use.default:

expires_atstring

Optional ISO 8601 expiration timestamp for the memory.default:

importancevalue

Importance score for the saved or updated memory, from 0.0 to 1.0.

memory_idstring

Exact XMemo memory reference shown by search or recall.default:

memory_typestring

Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %.default: auto

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

pathstring

A simple user-facing category or path for this memory, such as preferences, projects/xmemo, or personal/travel.

provenance_jsonstring

Optional JSON object string describing memory source, evidence, or attribution.default: {}

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

semantic_keystring

Optional stable semantic key used to identify or upsert a memory concept.default:

team_idstring

Optional team/workspace identifier for team-scoped memory access.default:

add_expenseRecord one expense in the XMemo Ledger. Call this whenever the user states a concrete expense, purchase, income, or refund — for example, 'I spent 25 on lunch' or 'log this expense' — not only on an explicit 'record this'. Capture date, amount, currency, item, and merchant/cat...16 params

Record one expense in the XMemo Ledger. Call this whenever the user states a concrete expense, purchase, income, or refund — for example, 'I spent 25 on lunch' or 'log this expense' — not only on an explicit 'record this'. Capture date, amount, currency, item, and merchant/cat...

Parameters* required

agent_idstring

Optional client-supplied agent label for memory attribution.default:

agent_instance_idstring

Optional stable, non-secret agent instance ID for per-client attribution.default:

amountnumber

Positive transaction amount as a number.

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: private

categorystring

Optional spending category, such as food, transport, or electronics.default:

currencystring

Currency code or label, such as CNY, RMB, JPY, yen, or USD. For ledger search/list tools, leave blank unless the user explicitly requested one currency; labels are normalized to codes.default: CNY

device_idstring

Optional client-supplied device identifier for attribution.default:

device_labelstring

Optional human-readable device label for attribution.default:

itemstring

The purchased item or service, for example 2 watermelons or Nintendo Switch 2.

merchantstring

Optional merchant or store name.default:

notestring

Optional completion note.default:

pathstring

A simple user-facing category or path for this memory, such as preferences, projects/xmemo, or personal/travel.default: finance/ledger/expenses

payment_methodstring

Optional payment method, such as card, cash, Alipay, or WeChat Pay.default:

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

team_idstring

Optional team/workspace identifier for team-scoped memory access.default:

transaction_datestring

Transaction date in YYYY-MM-DD. Leave blank to use today's UTC date.default:

update_stateSave the current working state during long-running work — active task, next action, or blocker — so future turns/sessions can resume. For durable user facts use remember.9 params

Save the current working state during long-running work — active task, next action, or blocker — so future turns/sessions can resume. For durable user facts use remember.

Parameters* required

blocked_reasonstring

Short explanation of why the current work is blocked.default:

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: work

contentstring

Text body to save, such as a memory, TODO/action item, event note, or state summary.default:

current_taskstring

Current task or work item to persist for later resume.default:

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

next_actionstring

Next action to persist so future turns can resume the work.default:

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

state_keystring

Working-state key to save, snapshot, or restore, such as active_task.default: active_task

ttl_secondsinteger

Time-to-live in seconds for working state or restart snapshot records.default: 86400

search_memorySearch XMemo memories by natural-language query. Call this when the user asks about saved or past information, AND proactively before answering any question where prior preferences, facts, projects, decisions, or history could change the answer. To delete a memory, use forget.10 params

Search XMemo memories by natural-language query. Call this when the user asks about saved or past information, AND proactively before answering any question where prior preferences, facts, projects, decisions, or history could change the answer. To delete a memory, use forget.

Parameters* required

agent_idstring

Optional client-supplied agent label for memory attribution.default:

agent_instance_idstring

Optional stable, non-secret agent instance ID for per-client attribution.default:

explainboolean

Whether to include retrieval explanation details with search or recall results.default: false

limitinteger

Maximum number of results to return.default: 5

memory_typestring

Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %.default: %

path_filterstring

Memory path filter; % matches all paths.default: %

prefer_workingboolean

Whether to prioritize working/session-state memories in retrieval.default: false

querystring

Natural-language question or search text.

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

team_idstring

Optional team/workspace identifier for team-scoped memory access.default:

recall_planPlan which memory searches to run before retrieval. Use only for complex tasks; for ordinary answers call recall_context or recall directly.8 params

Plan which memory searches to run before retrieval. Use only for complex tasks; for ordinary answers call recall_context or recall directly.

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: %

memory_typestring

Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %.default: %

output_jsonboolean

Return a machine-readable JSON response instead of a human-readable summary.default: false

path_filterstring

Memory path filter; % matches all paths.default: %

prefer_workingboolean

Whether to prioritize working/session-state memories in retrieval.default: false

querystring

Natural-language question or search text.

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

team_idstring

Optional team/workspace identifier for team-scoped memory access.default:

recall_contextBuild a context pack from XMemo memories. Call this before answering or planning when the task could benefit from multiple saved memories — preferences, prior conversations, projects, decisions, TODOs, or long-running work.13 params

Build a context pack from XMemo memories. Call this before answering or planning when the task could benefit from multiple saved memories — preferences, prior conversations, projects, decisions, TODOs, or long-running work.

Parameters* required

agent_idstring

Optional client-supplied agent label for memory attribution.default:

agent_instance_idstring

Optional stable, non-secret agent instance ID for per-client attribution.default:

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: %

limitinteger

Maximum number of results to return.default: 0

max_itemsinteger

Maximum number of memory items to include.default: 8

max_tokensinteger

Approximate maximum response size.default: 1500

memory_typestring

Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %.default: auto

output_jsonboolean

Return a machine-readable JSON response instead of a human-readable summary.default: false

path_filterstring

Memory path filter; % matches all paths.default: %

prefer_workingboolean

Whether to prioritize working/session-state memories in retrieval.default: true

querystring

Natural-language question or search text.

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

team_idstring

Optional team/workspace identifier for team-scoped memory access.default:

list_ledger_transactionsShow XMemo Ledger records. Call this when the user asks about past expenses, purchases, or spending history, or before answering a finance question that depends on recorded transactions. For item searches use query and leave currency blank unless a currency was requested.13 params

Show XMemo Ledger records. Call this when the user asks about past expenses, purchases, or spending history, or before answering a finance question that depends on recorded transactions. For item searches use query and leave currency blank unless a currency was requested.

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: %

categorystring

Optional spending category, such as food, transport, or electronics.default:

currencystring

Currency code or label, such as CNY, RMB, JPY, yen, or USD. For ledger search/list tools, leave blank unless the user explicitly requested one currency; labels are normalized to codes.default:

date_fromstring

Only include ledger transactions on or after this YYYY-MM-DD date.default:

date_tostring

Only include ledger transactions on or before this YYYY-MM-DD date.default:

limitinteger

Maximum number of results to return.default: 20

max_amountvalue

Only include ledger transactions with amount less than or equal to this value.

min_amountvalue

Only include ledger transactions with amount greater than or equal to this value.

offsetinteger

Number of matching records to skip for pagination.default: 0

output_jsonboolean

Return a machine-readable JSON response instead of a human-readable summary.default: false

querystring

Natural-language question or search text.default:

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

transaction_typestring

Optional ledger type filter: expense, income, refund, or transfer.default:

get_monthly_ledger_summarySummarize Ledger totals by month and currency. Call this when the user asks for monthly spending, income, refunds, net balance, budget review, or spending trends.6 params

Summarize Ledger totals by month and currency. Call this when the user asks for monthly spending, income, refunds, net balance, budget review, or spending trends.

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: %

currencystring

Currency code or label, such as CNY, RMB, JPY, yen, or USD. For ledger search/list tools, leave blank unless the user explicitly requested one currency; labels are normalized to codes.default:

monthsinteger

Number of recent ledger months to summarize.default: 6

output_jsonboolean

Return a machine-readable JSON response instead of a human-readable summary.default: false

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

transaction_typestring

Optional ledger type filter: expense, income, refund, or transfer.default:

mark_memory_usedRecord that a recalled memory was used in the answer. Call this after a retrieved memory actually influenced your response (not for ignored results).5 params

Record that a recalled memory was used in the answer. Call this after a retrieved memory actually influenced your response (not for ignored results).

Parameters* required

actionstring

Usage action or audit-event action filter, depending on the tool.default: used

contextstring

Short context explaining a memory usage event or pending decision.default:

memory_idstring

Exact XMemo memory reference shown by search or recall.

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

usage_tracking_idstring

Optional tracking ID that links a recalled memory to later usage feedback.default:

record_recall_eval_judgmentEvaluation only — record whether a returned memory was relevant for a query. Do not use in normal conversation.7 params

Evaluation only — record whether a returned memory was relevant for a query. Do not use in normal conversation.

Parameters* required

expected_relevant_totalinteger

Expected number of relevant memories for this recall-evaluation query.default: 0

memory_idstring

Exact XMemo memory reference shown by search or recall.

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

positioninteger

One-based rank position of the memory in the recall results, or 0 if not returned.default: 0

querystring

Natural-language question or search text.

reasonstring

Optional user-facing reason for the deletion.default:

relevantboolean

Whether the memory was relevant to the recall-evaluation query.

run_recall_evalAdmin/evaluation only — aggregate stored recall judgments and optionally tune retrieval. Not for normal conversation.3 params

Admin/evaluation only — aggregate stored recall judgments and optionally tune retrieval. Not for normal conversation.

Parameters* required

auto_tuneboolean

Whether recall evaluation may tune retrieval settings from recorded judgments.default: true

sincestring

Only include memories or activity on or after this ISO 8601 timestamp.default:

untilstring

Only include memories or activity on or before this ISO 8601 timestamp.default:

record_recall_feedbackRecord recall corrections. Call this when the user says relevant context was missing or wrong, or supplies memories that should have been found.7 params

Record recall corrections. Call this when the user says relevant context was missing or wrong, or supplies memories that should have been found.

Parameters* required

corrected_ids_jsonstring

JSON array of memory IDs that should have been returned for the recall query.default: []

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

missing_ids_jsonstring

JSON array of relevant memory IDs that were missing from recall results.default: []

missing_memories_jsonstring

JSON array of memory snippets or objects that should exist but were missing.default: []

notesstring

Freeform notes explaining recall feedback or corrections.default:

querystring

Natural-language question or search text.

returned_ids_jsonstring

JSON array of memory IDs returned by the recall query.default: []

get_recall_policyInspect XMemo retrieval policy (debug/admin). For actual recall use recall_context/recall/search_memory.

Inspect XMemo retrieval policy (debug/admin). For actual recall use recall_context/recall/search_memory.

No parameter schema in public metadata yet.

get_safety_policyShow the account safety policy. Useful before custom memory-writing that may include sensitive content; normal writes are already sanitized server-side.

Show the account safety policy. Useful before custom memory-writing that may include sensitive content; normal writes are already sanitized server-side.

No parameter schema in public metadata yet.

query_audit_eventsAdvanced audit query by action/time/target. For normal users prefer memory_activity.8 params

Advanced audit query by action/time/target. For normal users prefer memory_activity.

Parameters* required

actionstring

Usage action or audit-event action filter, depending on the tool.default:

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default:

limitinteger

Maximum number of results to return.default: 100

offsetinteger

Number of matching records to skip for pagination.default: 0

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

sincestring

Only include memories or activity on or after this ISO 8601 timestamp.default:

target_idstring

Optional audit target ID to filter audit events.default:

untilstring

Only include memories or activity on or before this ISO 8601 timestamp.default:

query_consolidation_auditInspect consolidation/lifecycle/reflection audit records (admin). Not for normal recall/save.7 params

Inspect consolidation/lifecycle/reflection audit records (admin). Not for normal recall/save.

Parameters* required

action_typestring

Consolidation, lifecycle, or reflection audit action type to filter by.default:

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default:

limitinteger

Maximum number of results to return.default: 100

offsetinteger

Number of matching records to skip for pagination.default: 0

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

sincestring

Only include memories or activity on or after this ISO 8601 timestamp.default:

untilstring

Only include memories or activity on or before this ISO 8601 timestamp.default:

record_eventRecord a significant session event, milestone, decision, or handoff note useful for reconstructing recent work. Not for durable facts/preferences (use remember).6 params

Record a significant session event, milestone, decision, or handoff note useful for reconstructing recent work. Not for durable facts/preferences (use remember).

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: work

contentstring

Text body to save, such as a memory, TODO/action item, event note, or state summary.

event_typestring

Timeline event type, such as event, milestone, decision, or handoff.default: event

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

session_idstring

Optional session identifier associated with the event, timeline query, or snapshot.default:

get_timelineShow recent events. Call this when the user asks what happened recently or when resuming work that may depend on recent events.5 params

Show recent events. Call this when the user asks what happened recently or when resuming work that may depend on recent events.

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: %

event_typestring

Timeline event type, such as event, milestone, decision, or handoff.default:

limitinteger

Maximum number of results to return.default: 20

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

session_idstring

Optional session identifier associated with the event, timeline query, or snapshot.default:

create_reminderCreate a TODO item. Alias for create_memory_todo.5 params

Create a TODO item. Alias for create_memory_todo.

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: work

contentstring

Text body to save, such as a memory, TODO/action item, event note, or state summary.

due_atstring

Optional due time for a memory TODO/action item, preferably ISO 8601.default:

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

list_remindersList TODO items. Alias for list_memory_todos.5 params

List TODO items. Alias for list_memory_todos.

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: %

due_beforestring

Only show memory TODO/action items due before this time.default:

item_statusstring

Optional memory TODO/action-item status filter.default: open

limitinteger

Maximum number of results to return.default: 20

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

complete_reminderComplete a TODO item. Alias for complete_memory_todo.2 params

Complete a TODO item. Alias for complete_memory_todo.

Parameters* required

notestring

Optional completion note.default:

reminder_idstring

The memory TODO/action-item ID to complete.

create_memory_todoCreate a TODO/action item in XMemo with an optional due time. Call this when the user asks to save a task, follow-up, action item, or reminder-style item to revisit later.5 params

Create a TODO/action item in XMemo with an optional due time. Call this when the user asks to save a task, follow-up, action item, or reminder-style item to revisit later.

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: work

contentstring

Text body to save, such as a memory, TODO/action item, event note, or state summary.

due_atstring

Optional due time for a memory TODO/action item, preferably ISO 8601.default:

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

list_memory_todosList open or completed TODO/action items. Call this when the user asks what tasks, follow-ups, or saved action items are pending or done.5 params

List open or completed TODO/action items. Call this when the user asks what tasks, follow-ups, or saved action items are pending or done.

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: %

due_beforestring

Only show memory TODO/action items due before this time.default:

item_statusstring

Optional memory TODO/action-item status filter.default: open

limitinteger

Maximum number of results to return.default: 20

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

complete_memory_todoMark a TODO/action item completed. Call this when the user says a saved task is done, resolved, or no longer needed; use the exact reference from list_memory_todos.2 params

Mark a TODO/action item completed. Call this when the user says a saved task is done, resolved, or no longer needed; use the exact reference from list_memory_todos.

Parameters* required

notestring

Optional completion note.default:

todo_idstring

The memory TODO/action-item ID to complete.

create_pending_decisionRecord an unresolved decision with its options to revisit later. Use for open choices, not ordinary TODOs.6 params

Record an unresolved decision with its options to revisit later. Use for open choices, not ordinary TODOs.

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: work

contextstring

Short context explaining a memory usage event or pending decision.

due_atstring

Optional due time for a memory TODO/action item, preferably ISO 8601.default:

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

options_jsonstring

JSON array of candidate options for a pending decision.default: []

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

list_pending_decisionsList open/unresolved decisions. Call this when the user asks what decisions are pending, or before planning work that depends on unresolved choices.5 params

List open/unresolved decisions. Call this when the user asks what decisions are pending, or before planning work that depends on unresolved choices.

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: %

due_beforestring

Only show memory TODO/action items due before this time.default:

item_statusstring

Optional memory TODO/action-item status filter.default: open

limitinteger

Maximum number of results to return.default: 20

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

resolve_decisionRecord the chosen option for a previously saved pending decision. Call this when the user states their decision.2 params

Record the chosen option for a previously saved pending decision. Call this when the user states their decision.

Parameters* required

decision_idstring

Exact pending-decision ID returned by list_pending_decisions.

resolutionstring

Chosen resolution text for a pending decision.

create_restart_snapshotSave active state, recent events, TODOs, and pending decisions for restart. Call this before handoff or when context may be lost.9 params

Save active state, recent events, TODOs, and pending decisions for restart. Call this before handoff or when context may be lost.

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: work

decision_limitinteger

Maximum number of pending decisions to include in a restart snapshot.default: 20

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

reminder_limitinteger

Maximum number of TODO/reminder items to include in a restart snapshot.default: 20

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

session_idstring

Optional session identifier associated with the event, timeline query, or snapshot.default:

state_keystring

Working-state key to save, snapshot, or restore, such as active_task.default: active_task

timeline_limitinteger

Maximum number of recent timeline events to include in a restart snapshot.default: 20

ttl_secondsinteger

Time-to-live in seconds for working state or restart snapshot records.default: 604800

restore_restart_snapshotResume previous work from a saved snapshot. Call this when the user asks to resume/restart or after context loss.9 params

Resume previous work from a saved snapshot. Call this when the user asks to resume/restart or after context loss.

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: work

record_restore_eventboolean

Whether to write a timeline event after restoring a restart snapshot.default: true

restore_stateboolean

Whether restore_restart_snapshot should restore the saved working-state record.default: true

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

snapshot_idstring

Exact restart snapshot memory ID to restore.default:

source_session_idstring

Session ID whose saved restart snapshot should be restored.default:

state_keystring

Working-state key to save, snapshot, or restore, such as active_task.default:

target_session_idstring

Session ID to associate with restored state and restore events.default:

ttl_secondsinteger

Time-to-live in seconds for working state or restart snapshot records.default: -1

recallRecall the few most relevant saved memories before answering, when prior preferences, known facts, past decisions, or project context may directly affect the response. Use recall_context when many memories are needed.8 params

Recall the few most relevant saved memories before answering, when prior preferences, known facts, past decisions, or project context may directly affect the response. Use recall_context when many memories are needed.

Parameters* required

agent_idstring

Optional client-supplied agent label for memory attribution.default:

agent_instance_idstring

Optional stable, non-secret agent instance ID for per-client attribution.default:

explainboolean

Whether to include retrieval explanation details with search or recall results.default: false

limitinteger

Maximum number of results to return.default: 5

memory_typestring

Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %.default: %

path_filterstring

Memory path filter; % matches all paths.default: %

prefer_workingboolean

Whether to prioritize working/session-state memories in retrieval.default: false

querystring

Natural-language question or search text.

update_memoryUpdate the content, location, or type of an existing memory. Call this only when the user explicitly asks to correct, revise, move, or reclassify a specific saved memory.18 params

Update the content, location, or type of an existing memory. Call this only when the user explicitly asks to correct, revise, move, or reclassify a specific saved memory.

Parameters* required

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default:

confidencevalue

Confidence score for the saved or updated memory, from 0.0 to 1.0.

contentstring

Text body to save, such as a memory, TODO/action item, event note, or state summary.default:

detect_conflictsboolean

Whether to detect possible conflicts with existing memories during an update.default: true

expires_atstring

Optional ISO 8601 expiration timestamp for the memory.default:

importancevalue

Importance score for the saved or updated memory, from 0.0 to 1.0.

memory_idstring

Exact XMemo memory reference shown by search or recall.

memory_typestring

Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %.default:

merge_metadataboolean

Whether to merge new metadata with existing metadata instead of replacing it.default: true

merge_provenanceboolean

Whether to merge new provenance with existing provenance instead of replacing it.default: true

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

pathstring

A simple user-facing category or path for this memory, such as preferences, projects/xmemo, or personal/travel.default:

provenance_jsonstring

Optional JSON object string describing memory source, evidence, or attribution.default: {}

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

semantic_keystring

Optional stable semantic key used to identify or upsert a memory concept.default:

statusstring

Memory status filter or update value, such as active, archived, deleted, or %.default:

supersession_reasonstring

Reason the updated memory supersedes older content.default:

team_idstring

Optional team/workspace identifier for team-scoped memory access.default:

forget_memoryDelete a memory (recoverable) by exact reference, when the user explicitly asks to remove or hide it. Use forget or delete_current_memory for permanent deletion.5 params

Delete a memory (recoverable) by exact reference, when the user explicitly asks to remove or hide it. Use forget or delete_current_memory for permanent deletion.

Parameters* required

memory_idstring

Exact XMemo memory reference shown by search or recall.

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

modestring

Deletion mode for forget_memory, such as soft_delete, hard_delete, or redact when supported.default: soft_delete

reasonstring

Optional user-facing reason for the deletion.default:

replacement_contentstring

Replacement text to store when redacting or replacing deleted memory content.default:

forgetPermanently delete one memory by natural target ('latest', 'current', or an exact ID). Call this only when the user explicitly asks to forget/delete a specific memory; search or check activity first if the target is ambiguous.2 params

Permanently delete one memory by natural target ('latest', 'current', or an exact ID). Call this only when the user explicitly asks to forget/delete a specific memory; search or check activity first if the target is ambiguous.

Parameters* required

reasonstring

Optional user-facing reason for the deletion.default:

targetstring

The memory to forget: current or an exact memory ID shown by search.default: current

delete_current_memoryPermanently delete the single active memory (no ID needed). Call this only when exactly one memory exists and the user explicitly asks to delete it; refused if zero or multiple match.1 params

Permanently delete the single active memory (no ID needed). Call this only when exactly one memory exists and the user explicitly asks to delete it; refused if zero or multiple match.

Parameters* required

reasonstring

Optional user-facing reason for the deletion.default:

memory_overviewShow a summary of XMemo memories and recent activity. Call this when the user asks what XMemo remembers without a specific query.

Show a summary of XMemo memories and recent activity. Call this when the user asks what XMemo remembers without a specific query.

No parameter schema in public metadata yet.

memory_statsShow aggregate statistics for XMemo memories — counts by type, source, location, and optional time range. Call this when the user asks for counts, breakdowns, or distributions.8 params

Show aggregate statistics for XMemo memories — counts by type, source, location, and optional time range. Call this when the user asks for counts, breakdowns, or distributions.

Parameters* required

group_bystring

Optional grouping: none, month, agent, location, memory_type, type, source, path, bucket, day, or comma-separated advanced fields.default:

memory_typestring

Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %.default: %

output_jsonboolean

Return a machine-readable JSON response instead of a human-readable summary.default: false

path_filterstring

Memory path filter; % matches all paths.default: %

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

sincestring

Only include memories or activity on or after this ISO 8601 timestamp.default:

top_ninteger

Maximum number of aggregate groups to return.default: 10

untilstring

Only include memories or activity on or before this ISO 8601 timestamp.default:

memory_activityShow recent memory activity — writes, deletions, TODO changes, ledger changes, and timeline events. Call this when the user asks what changed recently, or before deleting 'latest/recent' memory so the user can confirm the preview.6 params

Show recent memory activity — writes, deletions, TODO changes, ledger changes, and timeline events. Call this when the user asks what changed recently, or before deleting 'latest/recent' memory so the user can confirm the preview.

Parameters* required

activity_typestring

Activity filter: all, writes, deletions, reads, reminders, ledger, or timeline.default: all

include_timelineboolean

Whether to include timeline events in recent memory activity.default: true

limitinteger

Maximum number of results to return.default: 10

output_jsonboolean

Return a machine-readable JSON response instead of a human-readable summary.default: false

sincestring

Only include memories or activity on or after this ISO 8601 timestamp.default:

untilstring

Only include memories or activity on or before this ISO 8601 timestamp.default:

analyze_memory_textCount a word or phrase across XMemo memories, optionally grouped by month, agent, location, or type. Call this when the user asks how often a word/topic appears.12 params

Count a word or phrase across XMemo memories, optionally grouped by month, agent, location, or type. Call this when the user asks how often a word/topic appears.

Parameters* required

group_bystring

Optional grouping: none, month, agent, location, memory_type, type, source, path, bucket, day, or comma-separated advanced fields.default: none

include_examplesboolean

Whether to include a few short matching memory snippets.default: false

match_modestring

How to match phrase: exact, case_insensitive, or regex_lite.default: exact

max_examplesinteger

Maximum number of short snippets to include.default: 3

max_memoriesinteger

Maximum number of memories to inspect while analyzing text.default: 1000

memory_typestring

Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %.default: %

output_jsonboolean

Return a machine-readable JSON response instead of a human-readable summary.default: false

path_filterstring

Memory path filter; % matches all paths.default: %

phrasestring

Exact word or phrase to count across visible XMemo memories.

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

sincestring

Only include memories or activity on or after this ISO 8601 timestamp.default:

untilstring

Only include memories or activity on or before this ISO 8601 timestamp.default:

restore_memoryRestore a previously deleted memory. Call this only when the user explicitly asks to restore or undo a deletion.3 params

Restore a previously deleted memory. Call this only when the user explicitly asks to restore or undo a deletion.

Parameters* required

memory_idstring

Exact XMemo memory reference shown by search or recall.

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

reasonstring

Optional user-facing reason for the deletion.default:

redact_memoryRedact sensitive content from a memory while keeping an audit trail. Call this only when the user explicitly asks to redact.4 params

Redact sensitive content from a memory while keeping an audit trail. Call this only when the user explicitly asks to redact.

Parameters* required

memory_idstring

Exact XMemo memory reference shown by search or recall.

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

reasonstring

Optional user-facing reason for the deletion.default:

replacement_contentstring

Replacement text to store when redacting or replacing deleted memory content.default: [REDACTED]

explain_memoryExplain why a memory exists or matched a query. Call this when the user asks why something was saved or why it was retrieved.4 params

Explain why a memory exists or matched a query. Call this when the user asks why something was saved or why it was retrieved.

Parameters* required

include_embeddingboolean

Whether to include embedding/vector metadata in the returned explanation.default: false

memory_idstring

Exact XMemo memory reference shown by search or recall.

output_jsonboolean

Return a machine-readable JSON response instead of a human-readable summary.default: false

querystring

Natural-language question or search text.default:

list_memory_versionsShow version history for a memory. Call this when the user asks for previous content or changes over time.2 params

Show version history for a memory. Call this when the user asks for previous content or changes over time.

Parameters* required

memory_idstring

Exact XMemo memory reference shown by search or recall.

output_jsonboolean

Return a machine-readable JSON response instead of a human-readable summary.default: false

list_memory_conflictsList conflicting/inconsistent memories. Call this when the user/admin asks to review unresolved conflicts.3 params

List conflicting/inconsistent memories. Call this when the user/admin asks to review unresolved conflicts.

Parameters* required

limitinteger

Maximum number of results to return.default: 50

output_jsonboolean

Return a machine-readable JSON response instead of a human-readable summary.default: false

unresolved_onlyboolean

Whether to show only unresolved memory conflicts.default: true

resolve_memory_conflictResolve a listed memory conflict. Call this only when the user/admin explicitly chooses a resolution strategy.5 params

Resolve a listed memory conflict. Call this only when the user/admin explicitly chooses a resolution strategy.

Parameters* required

conflict_idstring

Exact memory-conflict ID returned by list_memory_conflicts.

merge_contentstring

Merged memory content to apply when resolving a conflict with a merge strategy.default:

metadata_jsonstring

Optional JSON object string with extra metadata for the operation.default: {}

resolution_strategystring

Conflict resolution strategy, such as mark_conflict, keep_existing, replace, or merge.default: mark_conflict

winning_memory_idstring

Memory ID that should win when resolving a conflict.default:

run_lifecycleMaintenance tool. Use only when the user/admin explicitly asks to expire, archive, decay, or dry-run lifecycle processing.8 params

Maintenance tool. Use only when the user/admin explicitly asks to expire, archive, decay, or dry-run lifecycle processing.

Parameters* required

archiveboolean

Whether lifecycle maintenance should archive stale memories.default: true

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: %

decayboolean

Whether lifecycle maintenance should decay low-value memories.default: true

dry_runboolean

Preview the maintenance action without applying changes.default: false

expireboolean

Whether lifecycle maintenance should expire memories that reached their expiration policy.default: true

limitinteger

Maximum number of results to return.default: 500

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

team_idstring

Optional team/workspace identifier for team-scoped memory access.default:

reflectMaintenance tool. Use only when the user/admin asks to summarize, promote, expire, decay, or archive via reflection. Prefer dry_run unless changes are explicitly requested.11 params

Maintenance tool. Use only when the user/admin asks to summarize, promote, expire, decay, or archive via reflection. Prefer dry_run unless changes are explicitly requested.

Parameters* required

actions_csvstring

Comma-separated maintenance actions to run, such as summarize, promote, expire, decay, or archive.default: summarize,promote,expire,decay,archive

bucketstring

Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.default: %

dry_runboolean

Preview the maintenance action without applying changes.default: false

limitinteger

Maximum number of results to return.default: 500

owner_filtervalue

Optional owner/user filter for administrative maintenance tools.

path_filterstring

Memory path filter; % matches all paths.default: %

scopevalue

Optional scope that narrows memory access; leave blank for the token default.

sincevalue

Only include memories or activity on or after this ISO 8601 timestamp.

team_idstring

Optional team/workspace identifier for team-scoped memory access.default:

time_window_hoursnumber

Number of recent hours to inspect during reflection maintenance.default: 24

untilvalue

Only include memories or activity on or before this ISO 8601 timestamp.

get_system_statsDetailed memory stats with filters and grouping. For a quick summary use memory_overview or memory_stats.11 params

Detailed memory stats with filters and grouping. For a quick summary use memory_overview or memory_stats.

Parameters* required

group_bystring

Optional grouping: none, month, agent, location, memory_type, type, source, path, bucket, day, or comma-separated advanced fields.default:

memory_typestring

Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %.default: %

output_jsonboolean

Return a machine-readable JSON response instead of a human-readable summary.default: false

path_filterstring

Memory path filter; % matches all paths.default: %

scopestring

Optional scope that narrows memory access; leave blank for the token default.default:

sincestring

Only include memories or activity on or after this ISO 8601 timestamp.default:

sourcestring

Optional source filter for system statistics.default:

statusstring

Memory status filter or update value, such as active, archived, deleted, or %.default: %

team_idstring

Optional team/workspace identifier for team-scoped memory access.default:

top_ninteger

Maximum number of aggregate groups to return.default: 20

untilstring

Only include memories or activity on or before this ISO 8601 timestamp.default:

Configuration

XMEMO_KEYsecret

Bearer token issued by XMemo for the stdio proxy. Optional for discovery; required for tool execution.

XMEMO_URL

Optional XMemo service base URL. Defaults to https://xmemo.dev.

Readme

XMemo: Memory OS for AI Agents

XMemo logo

View the full README on GitHub

Details

Repository: github.com/yonro/memory-os-cli
Website: xmemo.dev/product/mcp
Category: AI & LLM Tools
Package: @xmemo/client
Transport: STDIO, HTTP
Auth: Required
Registry: MCP registry, active

Related AI & LLM Tools MCP servers

View all

Formio Uagformio/uagThe Universal Agent Gateway (UAG) enables in-process agentic automation using Form.io.12stars

DataDoe MCPdeltologic/datadoe-mcpHosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.9stars

Dakera Mcpdakera-ai/dakera-mcpAgent memory engine — 106 MCP tools, self-hosted, single Rust binary9stars

Lorejordanhindo/loreLightweight MCP for infinite agent memory. Any agent, any session, anytime.9stars

Mementoveerps57/mementoLocal-first, LLM-agnostic memory layer for AI assistants.9stars

Token Compressorbase76-research-lab/token-compressorCompress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.8stars