Cursor MCP Bridge logo

Cursor MCP Bridge

Unclaimed

by JaimeJunr

Let any AI agent (Claude Code, Codex, Gemini/Antigravity) delegate to the Cursor CLI agent via MCP: cheap/fast coding tasks, codebase exploration & web lookup — with model + effort control and session follow-up.

Install

$node /abs/path/to/cursor-mcp-bridge/dist/index.js

Set up this server

This server needs project-specific setup. Follow the project instructions; no reusable public launch command is available yet.

Project instructions
agent-delegationai-agentscode-assistantcursorcursor-agentcursor-clideveloper-toolsllmmcpmodel-context-protocol

More in Search & Web

Browse the full directory

Unclaimed listing

Is this your MCP server?

This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.

Claim this server

Security profile

Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works

10 of 10 tools

Documented tools (10)

From project documentation. A server handshake does not verify each tool’s description or behavior.

bridge_stats

Report calls and chars returned to context per tool (needs POLYAGENTLOG).

delegate

Run a task with full read/edit/shell access in cwd. Required level: 1=GPT-5.6 Luna max (codex), 2=GPT-5.6 Sol xhigh (codex), 3=Grok 4.6 high (grok), 4=GPT-6 Astra max (codex), 5=Claude Fable 5.1 max (claude). Levels 4 and 5 are expensive — 5 by far the most; last resort only. Optional engine overrid

explore

Read-only exploration on Codex with gpt-5.6-luna. question alone → broad fan-out search returning file:line refs; question+files → answer about those files; neither → general project map. breadth: "thorough" sweeps wider. Locates, does not review.

fan_out

Run the SAME prompt across N engines/tiers in parallel isolated sandboxes and get back ONLY a compact digest — mode: "race" (default) returns the first success, mode: "consensus" compares every output through one cheap arbiter.

fast_delegate

Same full read/edit/shell access as delegate, but with no level to pick: it routes to whichever CLI is currently the fastest and healthy. Prefer it over delegate when the task is simple or urgent and picking a level is not worth it. ⚠️ Its first candidate is pay-per-token (OpenRouter), traded for la

follow_up

Continue a prior session by sessionid.

generate_image

Generate or edit an image through Codex's built-in image tool and save it inside cwd.

read_slice

Surgical read-only read: returns ONLY the code relevant to want (exact lines with file:line) from the given files — the full file never enters your context. Use instead of reading large files whole.

run_filtered

Run a shell command through Codex/Luna with full access and get back ONLY the lines relevant to want — semantic filtering of huge build/test/log output.

web_lookup

Web/docs lookup through Codex/Luna with real web search enabled and a read-only filesystem.

Tool change history

Compared across complete checks of the same configuration. Tools were listed, not invoked. Input-schema changes are not measured here.

No complete tool checks yet.

FAQ

Questions about Cursor MCP Bridge MCP Server

How do I connect Cursor MCP Bridge MCP Server to Claude?
The listing records `node /abs/path/to/cursor-mcp-bridge/dist/index.js` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Code, Cursor as compatible clients.
Is Cursor MCP Bridge MCP Server free?
The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
What can Cursor MCP Bridge MCP Server do?
Cursor MCP Bridge MCP Server documents 10 tools to the agent, including bridge_stats, delegate, explore. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.