Cursor MCP Bridge — AI skill for Claude Code
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.
How to install Cursor MCP Bridge
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open JaimeJunr/cursor-mcp-bridge and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Cursor MCP Bridge does
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.
Alternatives in AI
- Discover — Discovery phase - Multi-AI research and exploration 2.8k ★
- Jcodemunch MCP — Cut AI token costs 95%+ on code exploration 2.6k ★
- Browserwing — BrowserWing turns your browser actions into MCP commands Or Claude Skill, allowing AI agents to control browse 1.2k ★
README
cursor-mcp-bridge
MCP server that lets **any** agent or MCP host delegate to headless **Codex, Grok, and Claude Code CLIs**, with Cursor available as an opt-in fallback. Use the fleet for implementation, planning, and project exploration without burning the caller's context on raw worker output.
Worker tools take optional **model** and **effort** overrides, return a `session_id`, and support `follow_up`. Difficulty levels select a distinct default model across the three active subscriptions.
Tools
The server exposes ten tools:
| Tool | Purpose |
|---|---|
delegate |
Run a task with full read/edit/shell access in cwd. Required level: 1=GPT-5.6 Luna max (codex), 2=Grok 4.5 high (grok), 3=GPT-5.6 Sol xhigh (codex), 4=Grok 4.6 high (grok), 5=Opus max (claude). Optionally accepts an agent persona by name or inline {prompt}. |
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. |
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. |
generate_image |
Generate or edit an image through Codex's built-in image tool and save it inside cwd. |
plan |
Phase 1: read the codebase and return an implementation plan without editing. Defaults to level 3 (Codex Sol xhigh, hard read-only); level 5 Opus max is read-only by prompt only. |
build |
Phase 2: implement an approv |
Related Skills
Expert Dispatch
new Specialist Dispatch Pattern -- let cheap AI assistants delegate complex tasks to Claude Code CLI. Bash ada
Smart Context Delegation
Cut coding-agent token usage by ~90%: a PreToolUse hook blocks large file reads; bulk-read/code-write delegate
Synthetic Market Research
Agent skill for fast, cheap market research using LLM synthetic surveys + Semantic Similarity Rating (SSR). No
Task Automation AI Agent
A Python agent that breaks natural-language requests into sub-tasks and calls tools (calculator, knowledge sea
Stacklit
One command gives AI agents instant codebase context. ~250 tokens replaces 50,000+ tokens of exploration. Auto
Agent Belay
Let your AI move fast without breaking things.
Related Agents
Security Sentinel
Deep security review focused on OWASP Top 10, injection, auth/authz, data exposure, and dependency vulnerabili
Verify
Claude Code runner adapter. 격리 snapshot에서 Codex/Antigravity/Tailscale Aperture reviewer를 조합해 교차검증. 보안 결정권 없음,
Plugins
Agent Plugin System - manages the pluggable AI agent architecture (Claude, Cursor, Gemini). Use proactively wh