Quickchat AI MCP

This official MCP server allows users to manage their Quickchat AI agents directly from AI applications like ChatGPT, Claude, or Cursor. It enables agents to analyze performance metrics, review conversation logs, update agent settings, and create new AI agents without requiring API keys, using a single sign-in authentication method.

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 2026-10-19Operated by Quickchat AI

MCP endpoint (Streamable HTTP)

https://app.quickchat.ai/v1/api/mcp/rpc

Vendor documentation

What you can do with it

Analyze AI agent performance metrics
Review and dig into conversation logs
Update AI agent settings
Create new AI agents

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 quickchat-ai-mcp https://app.quickchat.ai/v1/api/mcp/rpc

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 quickchat-ai-mcp --url https://app.quickchat.ai/v1/api/mcp/rpc

Cursor

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

Cursor configuration

{
  "mcpServers": {
    "quickchat-ai-mcp": {
      "url": "https://app.quickchat.ai/v1/api/mcp/rpc"
    }
  }
}

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": {
    "quickchat-ai-mcp": {
      "type": "streamableHttp",
      "url": "https://app.quickchat.ai/v1/api/mcp/rpc",
      "disabled": false
    }
  }
}

VS Code

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

VS Code configuration

{
  "servers": {
    "quickchat-ai-mcp": {
      "type": "http",
      "url": "https://app.quickchat.ai/v1/api/mcp/rpc"
    }
  }
}

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 quickchat-ai-mcp https://app.quickchat.ai/v1/api/mcp/rpc

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": {
    "quickchat-ai-mcp": {
      "url": "https://app.quickchat.ai/v1/api/mcp/rpc"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "quickchat-ai-mcp": {
      "serverUrl": "https://app.quickchat.ai/v1/api/mcp/rpc"
    }
  }
}

Ground your agent in cited data

Quickchat AI MCP gives your agent tools. Koskamo gives it reviewed, cited facts to check its answers against. Add it as a second MCP server; public reads need no API key.

Connect Koskamo Browse datasets

See all 1,050

Do you run Quickchat AI 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