MemOS

A Model Context Protocol (MCP) implementation for theMemOSAPI service. This package provides a command-line interface to interact with MemOS API using MCP standards.

{ "mcpServers": { "memos-api-mcp": { "command": "npx", "args": ["-y", "@memtensor/memos-api-mcp"], "env": { "MEMOS_API_KEY": "your-api-key", "MEMOS_USER_ID": "your-user-id", "MEMOS_CHANNEL": "the-site-where-you-are-seeing-this-document" } } } }

- command: Usesnpxto run the package
- args: Arguments passed to npx to run the package
- env: Environment variables

- MEMOS_API_KEY: Your Memos API key for authentication (Get your API Key in Dashboard[https://memos-dashboard.openmem.net/cn/apikeys/])
- MEMOS_USER_ID: Stable per-human identifier. MUST be deterministic and non-PII, and MUST remain the same for the same person across devices/sessions. NEVER reuse across different people. DO NOT use random values, device IDs, or model/chat session IDs. Recommended: SHA-256(lowercase(trim(email))) or your SSO subject/employee ID.
- MEMOS_CHANNEL: The site where you are seeing this document. Candidate values:MODELSCOPE,MCPSO,MCPMARKETCN,MCPMARKETCOM,GLAMA,PULSEMCP,MCPSERVERS,LOBEHUB,MEMOS(meaning the MemOS official website),GITHUB(meaning this README file)

This package provides the following MCP tools:

- Adds a new message to a conversation
- Parameters:

- conversation_id: Unique identifier of the conversation associated with the feedback.
- messages: Array of messages containing role and content information.

- role: Role of the message sender (userorassistant).
- content: Message content.
- chat_time: (Optional) Message timestamp.

- Searches for memories in a conversation.
- Parameters:

- query: Text content to search within the memories. The token limit for a single query is 4k.
- filter: (Optional) Filter conditions, used to precisely limit the memory scope before retrieval.
- knowledgebase_ids: (Optional) Array specifying the knowledge bases to search.

- DO NOT USE THISunless the user explicitly mentions "knowledge base" or "KB".
-
- If the user explicitly asks to search ALL knowledge bases -> pass["all"].
- If the user specifies particular KB IDs -> pass those IDs.
- If the user DOES NOT mention knowledge bases -> OMIT this parameter (do not send it).

- Delete specific memories by their IDs.
- Parameters:

- user_ids: List of user IDs whose memories will be deleted.
- memory_ids: List of memory IDs to delete.

- Submit user feedback to the MemOS system.
- Note: Feedback is applied asynchronously —add_feedbackreturns immediately (often with atask_id), and the effect may take a short time to appear.
- Parameters:

- user_id: The user identifier associated with the feedback.
- conversation_id: Unique identifier of the conversation associated with the feedback.
- feedback_content: The specific content of the feedback.
- agent_id: (Optional) Agent ID associated with the feedback.
- app_id: (Optional) App ID associated with the feedback.
- feedback_time: (Optional) Feedback time string (default: current UTC time).
- allow_public: (Optional) Whether to allow public access (default: false).
- allow_knowledgebase_ids: (Optional) List of knowledge base IDs allowed to be written to.

- Get the user's full memory profile (facts, preferences, and tool trajectories).
- Parameters:

- include_preference: (Optional) Whether to include preference memories.
- include_tool_memory: (Optional) Whether to include tool trajectory memories.
- current: (Optional) Page number.
- size: (Optional) Number of entries per page.

- Create a named knowledge base container.
- Parameters:

- knowledgebase_name: Name of the knowledge base.
- knowledgebase_description: (Optional) Description of the knowledge base.

- Remove a knowledge base association.
- Parameters:

- knowledgebase_id: Target knowledge base ID.

- Upload document(s) to a specified knowledge base.
- Parameters:

- knowledgebase_id: Target knowledge base ID.
- file: Document list.

- content: Local absolute path, public URL, or Base64 Data URI.
- file_name: (Optional) File name.
- mime_type: (Optional) MIME type. Required whencontentis a local file path.

- Get document metadata in batches by file IDs.
- Parameters:

- file_ids: List of document IDs.

- Delete specified documents from the knowledge base by file IDs.
- Parameters:

- file_ids: List of document IDs.

All tools use the same configuration and require theMEMOS_API_KEYenvironment variable.

- MCP-compliant API interface
- Command-line tool for easy interaction
- Built with TypeScript for type safety
- Express.js server implementation
- Zod schema validation

- Node.js >= 18
- npm or pnpm (recommended)

You can install the package globally using npm:

After installation, you can run the CLI tool using:

git clone <repository-url> cd memos-api-mcp

- pnpm build- Build the project
- pnpm dev- Start development server using tsx
- pnpm start- Run the built version
- pnpm inspect- Inspect the MCP implementation using @modelcontextprotocol/inspector

memos-mcp/ ├── src/ # Source code ├── build/ # Compiled JavaScript files ├── package.json # Project configuration └── tsconfig.json # TypeScript configuration

- @modelcontextprotocol/sdk: ^1.0.0
- express: ^4.19.2
- zod: ^3.23.8
- ts-md5: ^2.0.0

Cloud memory for Claude Code, Cursor, and any MCP-compatible agent. Context persists across sessions, projects, and teams.

Persistent cognitive memory for Claude Code. Cloud-based semantic search, Ai-powered extraction, project scoping, and compaction recovery.

Human-like memory layer for AI agents with semantic, episodic, and procedural memory types, cognitive profiling, knowledge graph, and 12 MCP tools.

The media memory layer for AI agents and their humans. Track books, movies, music, shows, and anime.

Engram is a hosted MCP server that provides reliable memory for AI agents:

Persistent memory for AI agents. Store and retrieve files via 14 MCP tools with OAuth 2.0 auth. Free 10GB tier.

Agent memory with git-like version control. Custom LLMs turn conversations into structured facts with automatic conflict detection - your agent sees how decisions evolved, not four contradictory text blobs. 80% token reduction vs RAG/graph systems. MCP + REST.

A self-hosted MCP server that gives AI Agents persistent memory across sessions, projects, and machines.

Decentralized persistent memory for AI agents — encrypted vault storage built on Walrus and Sui.

AI trading memory layer for MT5/forex with 15 MCP tools — store/recall trades, pattern discovery, strategy evolution, and Outcome-Weighted Memory.