MemorySync MCP MCP server

MemorySync provides two hosted Model Context Protocol servers: one for persistent AI memory management and another for accessing official documentation. The memory server allows assistants to search, add, and manage user preferences and context across sessions, while the documentation server enables coding agents to search and read specific documentation pages to ensure accurate code generation.

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 MemorySync

MCP endpoint (Streamable HTTP)

https://docs.memorysync.io/mcp

Vendor documentation

What you can do with it

Search and read official documentation for coding agents
Manage persistent user memory and preferences across AI sessions
Sync content from sources like GitHub, Slack, and Notion
Handle memory conflicts and retention policies

Tools advertised by the last live check:

search_docs
read_doc
list_doc_sections

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 memorysync-mcp https://docs.memorysync.io/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 memorysync-mcp --url https://docs.memorysync.io/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable memorysync-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "memorysync-mcp": {
      "url": "https://docs.memorysync.io/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": {
    "memorysync-mcp": {
      "type": "streamableHttp",
      "url": "https://docs.memorysync.io/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start memorysync-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "memorysync-mcp": {
      "type": "http",
      "url": "https://docs.memorysync.io/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 memorysync-mcp https://docs.memorysync.io/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": {
    "memorysync-mcp": {
      "url": "https://docs.memorysync.io/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": {
    "memorysync-mcp": {
      "serverUrl": "https://docs.memorysync.io/mcp"
    }
  }
}

See all 957

Do you run MemorySync 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