Koskamo

MemoryRouter MCP MCP server

MemoryRouter provides a persistent memory layer that allows AI agents to retain context across different platforms and sessions. The MCP server enables clients to connect to a unified memory store, ensuring that user preferences, project details, and conversation history are preserved and accessible regardless of the AI tool being used, such as ChatGPT, Claude, or coding agents.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

No sign-inEndpoint checked 2026-10-05Operated by MemoryRouter
MCP endpoint (Streamable HTTP)
https://mcp.memoryrouter.ai/mcp
Vendor documentation

What you can do with it

  • Share persistent memory across ChatGPT, Claude, and coding agents
  • Transfer context from ChatGPT to Claude to avoid starting over
  • Maintain project state and preferences across different AI sessions
  • Connect any MCP client to a unified memory store
Tools advertised by the last live check:
  • search_memories
  • date_search_memories
  • store_memory
  • memory_status
  • forget_all_memories
  • consolidate_memories
  • commit_reflections
  • inspect_memory
  • delete_memories
  • search

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http memoryrouter-mcp https://mcp.memoryrouter.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add memoryrouter-mcp --url https://mcp.memoryrouter.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable memoryrouter-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "memoryrouter-mcp": {
      "url": "https://mcp.memoryrouter.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.
Cline configuration
{
  "mcpServers": {
    "memoryrouter-mcp": {
      "type": "streamableHttp",
      "url": "https://mcp.memoryrouter.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start memoryrouter-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "memoryrouter-mcp": {
      "type": "http",
      "url": "https://mcp.memoryrouter.ai/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http memoryrouter-mcp https://mcp.memoryrouter.ai/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "memoryrouter-mcp": {
      "url": "https://mcp.memoryrouter.ai/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "memoryrouter-mcp": {
      "serverUrl": "https://mcp.memoryrouter.ai/mcp"
    }
  }
}

Do you run MemoryRouter MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing