Purmemo

purmemo-ai/purmemo-mcp

Cross-platform memory layer that works across Claude Desktop, Cursor, Windsurf, Zed, and browser-based LLMs via Chrome extension. Exposes MCP tools for saving conversations, recalling memories through semantic search, and loading persistent identity context into new sessions. Includes living document primitives with append and replace modes, workflow automation, and a cognitive fingerprint system that frontloads who you are and what you're working on. Ships with a 30-second installer that handles Node setup and OAuth, or run it hosted via streamable-http if you don't want local processes. Free tier gives you 50 recalls per month with unlimited saves. Reach for this if you want conversational continuity across tools without manually copying context between sessions.

GitHub stars: 2
tools: 11
transport: STDIO
last updated: Mar 8, 2026

View on GitHub

Tools

11 tools

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

save_conversationSave complete conversations as living documents. REQUIRED: Send COMPLETE conversation in 'conversationContent' parameter (minimum 100 chars, should be thousands). Include EVERY message verbatim - NO summaries or partial content. Intelligently tracks context, extracts project d...5 params

Save complete conversations as living documents. REQUIRED: Send COMPLETE conversation in 'conversationContent' parameter (minimum 100 chars, should be thousands). Include EVERY message verbatim - NO summaries or partial content. Intelligently tracks context, extracts project d...

Parameters* required

conversationContentstring

COMPLETE conversation transcript - minimum 500 characters expected. Include EVERYTHING discussed.

conversationIdstring

Optional unique identifier for living document pattern. If provided and memory exists with this conversationId, UPDATES that memory instead of creating new one. Use for maintaining single memory pe...

prioritystring

Priority level for this memoryone of low · medium · highdefault: medium

tagsarray

Tags for categorization

titlestring

Title for this conversation memorydefault: Conversation 2026-03-23T00:47:35.459Z

recall_memoriesSearch and retrieve saved memories with intelligent semantic ranking. 🎯 BASIC SEARCH: recall_memories(query="authentication") → Returns all memories about authentication, ranked by semantic relevance 🔍 FILTERED SEARCH (Phase 2 Knowledge Graph Intelligence): Use filters when...10 params

Search and retrieve saved memories with intelligent semantic ranking. 🎯 BASIC SEARCH: recall_memories(query="authentication") → Returns all memories about authentication, ranked by semantic relevance 🔍 FILTERED SEARCH (Phase 2 Knowledge Graph Intelligence): Use filters when...

Parameters* required

contentPreviewboolean

Include content preview in resultsdefault: true

deadlinestring

Filter by deadline date from conversation context (YYYY-MM-DD format). Use when user asks about time-sensitive memories or specific deadlines. Example: deadline="2025-03-31" finds memories with Mar...

entitystring

Filter by entity name (people, projects, technologies). Use when user asks about a specific person, project, or technology by name. Example: entity="Alice" finds only memories mentioning Alice. Mor...

has_observationsboolean

Filter by conversation quality based on extracted observations (atomic facts). Set to true to find substantial, structured conversations with extracted knowledge (high-quality technical discussions...

includeChunkedboolean

Include chunked/multi-part conversations in resultsdefault: true

initiativestring

Filter by initiative/project name from conversation context. Use when user scopes search to specific project or goal. Example: initiative="Q1 OKRs" finds only Q1-related memories. Supports partial...

intentstring

Filter by conversation intent/purpose. Options: "decision" (decisions made), "learning" (knowledge gained), "question" (open questions), "blocker" (obstacles/issues). Use when user asks specificall...

limitinteger

Maximum number of memories to returndefault: 10

querystring

Search query - can be keywords, topics, or specific content

stakeholderstring

Filter by stakeholder (person or team) from conversation context. Use when user asks about specific person's or team's involvement. Example: stakeholder="Engineering Team" finds memories where Engi...

get_memory_detailsGet complete details of a specific memory, including all linked parts if chunked2 params

Get complete details of a specific memory, including all linked parts if chunked

Parameters* required

includeLinkedPartsboolean

Include all linked parts if this is a chunked memorydefault: true

memoryIdstring

ID of the memory to retrieve

discover_related_conversationsCROSS-PLATFORM DISCOVERY: Find related conversations across ALL AI platforms. Uses Purmemo's semantic clustering to automatically discover conversations about similar topics, regardless of which AI platform was used (ChatGPT, Claude Desktop, Gemini, etc). WHAT THIS DOES: - Sea...3 params

CROSS-PLATFORM DISCOVERY: Find related conversations across ALL AI platforms. Uses Purmemo's semantic clustering to automatically discover conversations about similar topics, regardless of which AI platform was used (ChatGPT, Claude Desktop, Gemini, etc). WHAT THIS DOES: - Sea...

Parameters* required

limitinteger

Maximum number of initial search results (will find related for each)default: 10

querystring

Natural language query for discovering related conversations across platforms

relatedPerMemoryinteger

Maximum related conversations to find per resultdefault: 5

get_user_contextGet the current user's cognitive identity and active session context. Call this at the START of a conversation to understand who you're talking to — their role, expertise, current project, and recent memory themes. This is the core of Purmemo's identity layer: once set in the...

Get the current user's cognitive identity and active session context. Call this at the START of a conversation to understand who you're talking to — their role, expertise, current project, and recent memory themes. This is the core of Purmemo's identity layer: once set in the...

No parameter schema in public metadata yet.

run_workflowRun a Purmemo workflow — structured, memory-powered processes for product, engineering, business, and operations tasks. Your relevant memories and identity are automatically loaded to personalize every workflow. WHEN TO USE THIS TOOL: - User wants to write a PRD, debug an issu...2 params

Run a Purmemo workflow — structured, memory-powered processes for product, engineering, business, and operations tasks. Your relevant memories and identity are automatically loaded to personalize every workflow. WHEN TO USE THIS TOOL: - User wants to write a PRD, debug an issu...

Parameters* required

inputstring

What you want to accomplish, the problem to solve, or context for the workflow.

workflowstring

Workflow name (e.g., "prd", "debug", "sprint"). Use list_workflows to see all available options including custom workflows. Optional — if omitted, auto-routes from input.

list_workflowsList all available Purmemo workflows — structured, memory-powered processes you can run. WHEN TO USE THIS TOOL: - User asks "what can you help me with?" or "what workflows do you have?" - User wants to see available capabilities before choosing one - User says "show me what's...1 params

List all available Purmemo workflows — structured, memory-powered processes you can run. WHEN TO USE THIS TOOL: - User asks "what can you help me with?" or "what workflows do you have?" - User wants to see available capabilities before choosing one - User says "show me what's...

Parameters* required

categorystring

Optional filter by category. Omit to see all workflows.one of product · strategy · engineering · business · operations · content

share_memorySet the visibility of a memory you own. VISIBILITY LEVELS: - private: Only you can see it (default) - unlisted: Anyone with the direct link can view it - public: Discoverable in the community tab by all users WHEN TO USE: - User says "share this memory" or "make this public" -...2 params

Set the visibility of a memory you own. VISIBILITY LEVELS: - private: Only you can see it (default) - unlisted: Anyone with the direct link can view it - public: Discoverable in the community tab by all users WHEN TO USE: - User says "share this memory" or "make this public" -...

Parameters* required

memory_idstring

UUID of the memory to share

visibilitystring

Target visibility levelone of private · unlisted · public

recall_publicSearch public memories shared by all Purmemo users. This is the community knowledge base. WHEN TO USE: - User asks "what have other people saved about X?" - User wants to explore community knowledge - User asks to search public/shared memories - Looking for solutions others ha...5 params

Search public memories shared by all Purmemo users. This is the community knowledge base. WHEN TO USE: - User asks "what have other people saved about X?" - User wants to explore community knowledge - User asks to search public/shared memories - Looking for solutions others ha...

Parameters* required

pagenumber

Page number (default 1)

platformstring

Filter by source platform (chatgpt, claude, gemini, etc.)

querystring

Search query for semantic search across public memories

sortstring

Sort order: recent (newest first) or popular (most recalled first)one of recent · popular

tagstring

Filter by tag

get_public_memoryRetrieve the FULL content of a public or unlisted memory by ID. WHEN TO USE: - After recall_public returns a preview and you need the complete content - When a user wants to read or implement from a shared community memory - When you have a public memory ID and need the full t...1 params

Retrieve the FULL content of a public or unlisted memory by ID. WHEN TO USE: - After recall_public returns a preview and you need the complete content - When a user wants to read or implement from a shared community memory - When you have a public memory ID and need the full t...

Parameters* required

memory_idstring

UUID of the public memory to retrieve in full

report_memoryReport a public memory for inappropriate content. WHEN TO USE: - User encounters spam, misleading, or inappropriate public content - User wants to flag content that contains personal information REASONS: spam, inappropriate, misleading, personal_info, other After 3 reports, a...3 params

Report a public memory for inappropriate content. WHEN TO USE: - User encounters spam, misleading, or inappropriate public content - User wants to flag content that contains personal information REASONS: spam, inappropriate, misleading, personal_info, other After 3 reports, a...

Parameters* required

descriptionstring

Optional additional details about the report

memory_idstring

UUID of the public memory to report

reasonstring

Reason for reportingone of spam · inappropriate · misleading · personal_info · other

Readme

pūrmemo

Memory for your AI tools. Claude remembers who you are, what you're working on, and what you said last time — across every session, on every platform.

Just want it in ChatGPT or Claude.ai in your browser? Get the Chrome Extension instead.

Install in 30 seconds

1. Paste this into your terminal

Mac or Linux:

curl -fsSL https://app.purmemo.ai/install | sh

Windows (PowerShell):

irm https://app.purmemo.ai/install.ps1 | iex

View the full README on GitHub

Details

Repository: github.com/purmemo-ai/purmemo-mcp
Categories: AI & LLM Tools, Search & Web Crawling
Package: purmemo-mcp
Transport: STDIO
Registry: MCP registry, active

Related AI & LLM Tools MCP servers

View all

Gemot Deliberation Serverjustinstimatze/gemotDeliberation primitive for multi-agent coordination: cruxes, vote clustering, consensus.2stars

Neurohiveadelelo13/neurohiveMulti-agent memory intelligence with expertise tracking and conflict detection1stars

Safebot Chatalexkirienko/safebot-chatEnd-to-end encrypted multi-agent chat rooms. Client-side crypto; zero chat logs.1stars

Boardcheckecholonius/boardcheckFlags deceptive signals in AI-agent marketplace listings, from fake engagement to prompt injection1stars

Dailyhotmcpfrankxmx/dailyhotmcp聚合55+平台热门榜单数据的AI工具，支持微博、知乎、B站、GitHub等平台。适用于LLM/RAG场景。1stars

AI Skill Storegarasegae/aiskillstoreAgent-first skill marketplace with USK open standard for Claude, Cursor, Gemini, Codex CLI.1stars