Context Pod
A remote MCP server that gives AI agents persistent memory through vector-based context with certainty scoring. Agents call get_pod_summary at session start, save_event to record new observations, apply_learning when corrected, and update_session at shutdown. Certainty starts at 0.3 and rises with corroboration. The chat lane lets you audit what any agent learned, correct drift, and add context no agent can observe alone. Multi-pod setups let coding agents, workflow agents, and personal assistants share context or stay isolated. Connects via SSE transport at context.nervousmachine.com/mcp. Useful when you want agents to remember across sessions without re-teaching every time, or when multiple agents need to build on shared knowledge.
- GitHub stars
- 2
- tools
- 39
- auth
- Required
- transport
- SSE
- last updated
- Feb 25, 2026
Tools
39 toolsPublic tool metadata for what this MCP can expose to an agent.
get_pod_summaryCondensed readable overview -- top signals with glosses and freshness
Condensed readable overview -- top signals with glosses and freshness
No parameter schema in public metadata yet.
get_podFull pod state including all events
Full pod state including all events
No parameter schema in public metadata yet.
get_eventsAll events, optionally filtered by signal_type
All events, optionally filtered by signal_type
No parameter schema in public metadata yet.
get_relevant_contextEvents most relevant to a task -- scored by match + certainty
Events most relevant to a task -- scored by match + certainty
No parameter schema in public metadata yet.
query_podNatural language question across all events
Natural language question across all events
No parameter schema in public metadata yet.
get_low_certaintyEvents below a certainty threshold -- best validation candidates
Events below a certainty threshold -- best validation candidates
No parameter schema in public metadata yet.
get_curiosity_triggersEvents that need validation, are stale, or under-observed
Events that need validation, are stale, or under-observed
No parameter schema in public metadata yet.
get_gap_analysisHigh-value, low-certainty signals ranked by investigation priority
High-value, low-certainty signals ranked by investigation priority
No parameter schema in public metadata yet.
get_convergence_reportNew events, certainty changes, and stale signals since last report
New events, certainty changes, and stale signals since last report
No parameter schema in public metadata yet.
create_podInitialize a new pod for a user or entity
Initialize a new pod for a user or entity
No parameter schema in public metadata yet.
save_eventSave or update any event
Save or update any event
No parameter schema in public metadata yet.
record_observationLog a raw behavioral signal (correction, engagement, etc.)
Log a raw behavioral signal (correction, engagement, etc.)
No parameter schema in public metadata yet.
apply_learningUpdate an event's value and certainty based on an observation
Update an event's value and certainty based on an observation
No parameter schema in public metadata yet.
update_sessionIncrement session and interaction counters -- call once at end
Increment session and interaction counters -- call once at end
No parameter schema in public metadata yet.
delete_eventRemove a specific event by key
Remove a specific event by key
No parameter schema in public metadata yet.
delete_podPermanently delete pod and all data -- irreversible
Permanently delete pod and all data -- irreversible
No parameter schema in public metadata yet.
link_eventsCreate a semantic relationship between two events
Create a semantic relationship between two events
No parameter schema in public metadata yet.
get_event_clusterBFS traversal from an event through its links
BFS traversal from an event through its links
No parameter schema in public metadata yet.
suggest_linksAuto-suggest relationships based on keyword overlap
Auto-suggest relationships based on keyword overlap
No parameter schema in public metadata yet.
detect_contradictionsSurface conflicting high-certainty events
Surface conflicting high-certainty events
No parameter schema in public metadata yet.
suggest_synthesisFind high-certainty events that could be consolidated
Find high-certainty events that could be consolidated
No parameter schema in public metadata yet.
export_cluster_diagramMermaid diagram of event relationships
Mermaid diagram of event relationships
No parameter schema in public metadata yet.
export_argument_outlineHierarchical markdown outline from linked events
Hierarchical markdown outline from linked events
No parameter schema in public metadata yet.
get_argument_chainTrace logical dependencies for a claim or topic
Trace logical dependencies for a claim or topic
No parameter schema in public metadata yet.
save_agent_contextPersist agent task history, decisions, errors per agent_id
Persist agent task history, decisions, errors per agent_id
No parameter schema in public metadata yet.
get_agent_contextRetrieve agent task history, decisions, errors per agent_id
Retrieve agent task history, decisions, errors per agent_id
No parameter schema in public metadata yet.
save_repo_contextCodebase metadata across sessions, namespaced by repo
Codebase metadata across sessions, namespaced by repo
No parameter schema in public metadata yet.
get_repo_contextCodebase metadata across sessions, namespaced by repo
Codebase metadata across sessions, namespaced by repo
No parameter schema in public metadata yet.
save_service_contextExternal service health and status data
External service health and status data
No parameter schema in public metadata yet.
get_service_contextExternal service health and status data
External service health and status data
No parameter schema in public metadata yet.
save_life_contextUser-shared life patterns (health, goals, routine, schedule)
User-shared life patterns (health, goals, routine, schedule)
No parameter schema in public metadata yet.
get_life_contextUser-shared life patterns (health, goals, routine, schedule)
User-shared life patterns (health, goals, routine, schedule)
No parameter schema in public metadata yet.
link_resourceAttach files, URLs, and projects linked to events
Attach files, URLs, and projects linked to events
No parameter schema in public metadata yet.
get_resourcesRetrieve files, URLs, and projects linked to events
Retrieve files, URLs, and projects linked to events
No parameter schema in public metadata yet.
unlink_resourceDetach files, URLs, and projects linked to events
Detach files, URLs, and projects linked to events
No parameter schema in public metadata yet.
add_sourceRegister a data source with a credibility score for intelligence pipeline pods
Register a data source with a credibility score for intelligence pipeline pods
No parameter schema in public metadata yet.
export_podExport complete pod data as JSON (GDPR Article 20)
Export complete pod data as JSON (GDPR Article 20)
No parameter schema in public metadata yet.
compare_podsCompare events across two pods -- agreements, divergences, gaps
Compare events across two pods -- agreements, divergences, gaps
No parameter schema in public metadata yet.
get_learning_rateShow current learning rate for an event based on its certainty
Show current learning rate for an event based on its certainty
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Event Pod
Agent context. Human alignment.
Agents build their world model autonomously -- observing, learning, updating certainty across every session. Humans can join at any time: audit, revise, and collaborate in plain language. A chat is all it takes.
- MCP endpoint:
https://context.nervousmachine.com/mcp - Full docs: https://context.nervousmachine.com/docs
- Landing page: https://context.nervousmachine.com
- Substack: https://nervousmachine.substack.com
- Research: https://www.techrxiv.org
Agents build autonomously. Humans align naturally.
Every lane writes to the same pod structure. A coding agent, a workflow agent, and a personal chat agent can all share context -- or each maintain their own. Either way, the Chat lane is the alignment interface for all of them. One conversation to audit what any agent learned, correct what drifted, and add what no agent can observe on its own. Most people start with one lane. The pods compose naturally as you add more.
Details
- Repository
- github.com/nervous-machine/context-pod
- Transport
- SSE
- Auth
- Required
- Registry
- MCP registry, active