How to connect OnCrawl MCP to Claude Desktop
Add this block to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Cursor and Codex use a similar schema.
{
"mcpServers": {
"oncrawl": {
"command": "npx",
"args": ["-y", "<server-package-name>"],
"env": {
"ONCRAWL_API_KEY": "your-api-key-here"
}
}
}
}
// Server source: https://github.com/Amaculus/oncrawl-mcp-server
// Check the server's README for the exact "command" and required env vars.Some MCP servers require an API key. Check the source page for setup: github.com/Amaculus/oncrawl-mcp-server.
Does OnCrawl MCP cost extra?
The OnCrawl MCP server is community-built — free to run, but you still pay for your OnCrawl subscription.
- Community MCPs are normally self-hosted from a GitHub repo. There's no extra license fee.
- Your OnCrawl account still needs whatever plan is required to access the data the MCP server queries.
- Trade-off: zero MCP cost, but no guarantee it'll keep working when OnCrawl changes their UI or API.
OnCrawl also publishes a REST API
OnCrawl publishes an API, but per-tier gating wasn't extracted automatically.
See OnCrawl API pageWhat you can do with OnCrawl from an AI agent
Three shapes of agent workflow. Pick the row that matches how you actually use Claude / Cursor / Codex day to day.
Skip the dashboard, ask Claude
- "What keywords moved this week?" answered in seconds
- Quick one-off questions without leaving the editor
- Pipe OnCrawl data into your personal notes / docs without writing a script
Run client analysis at agent speed
- Hand the MCP server to your team — every consultant can ask Claude about any client's OnCrawl account
- Multi-account workflows without context-switching the OnCrawl UI
- Reports you'd normally spend hours on, done before standup
Production agent workflows
- Embed in your internal Codex / Cursor agents that triage OnCrawl data daily
- Combine with other MCP servers in a multi-step agent chain
- Constrain agents to read-only roles to keep production OnCrawl safe
Limits and gotchas
- Community MCP — not maintained by OnCrawl. Check the README and last-update date before depending on it.
- Fallback: the REST API works for any flow the MCP server doesn't cover.
- Rate limits: MCP calls count against your underlying OnCrawl API quota. Burst usage from a curious agent can drain a daily allowance fast.
Agent-readiness verdict
Moderate agent potential with community MCP support. OnCrawl has a documented public API and ChatGPT integration, plus an active community-built MCP server for broader LLM compatibility. The lack of official OpenAPI specs and Claude integration limits its native accessibility in modern agent stacks.
Scored 2026-05-21 by Joonas (TMB).
OnCrawl MCP & API FAQ
Is the OnCrawl MCP server official?+
Can I use the OnCrawl MCP with Cursor or Codex?+
Does OnCrawl have a public API?+
Which LLMs does OnCrawl integrate with directly?+
Sources
- OnCrawl official site: https://www.oncrawl.com
- MCP server page: https://github.com/Amaculus/oncrawl-mcp-server
- API docs: https://developer.oncrawl.com
Data verified by Joonas on the dates shown. MCP server status auto-rechecked weekly.

