Contexel MCP MCP server

Contexel provides a shared AI memory layer that allows multiple AI applications to read and write the same context. It enables teams and individuals to persist decisions, preferences, and rules across different AI agents, ensuring consistency and reducing token usage by providing relevant context only when needed.

Endpoint and access

OAuth sign-in: the first time you connect, your client opens the vendor's own authorization prompt in a browser.

OAuth sign-inEndpoint checked 2026-10-05Operated by Contexel

MCP endpoint (Streamable HTTP)

https://contexel.ai/mcp

Vendor documentation

What you can do with it

Share team decisions and rules across multiple AI apps
Persist personal preferences and project context for AI agents
Reduce token usage by providing targeted memory lookups
Maintain a tamper-evident activity log of AI interactions

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 contexel-mcp https://contexel.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 contexel-mcp --url https://contexel.ai/mcp

Cursor

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

Cursor configuration

{
  "mcpServers": {
    "contexel-mcp": {
      "url": "https://contexel.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": {
    "contexel-mcp": {
      "type": "streamableHttp",
      "url": "https://contexel.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

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

VS Code configuration

{
  "servers": {
    "contexel-mcp": {
      "type": "http",
      "url": "https://contexel.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 contexel-mcp https://contexel.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": {
    "contexel-mcp": {
      "url": "https://contexel.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": {
    "contexel-mcp": {
      "serverUrl": "https://contexel.ai/mcp"
    }
  }
}

See all 1,687

Do you run Contexel 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