Skip to main content
Glama

cursor-mcp

Run Cursor's coding agent from Claude Code, with any model your Cursor plan offers.

Install

curl https://cursor.com/install -fsS | bash && agent login     # the Cursor CLI
claude mcp add --scope user cursor-cli -- npx -y @qmediat.io/cursor-mcp

Related MCP server: cursor-agent-bridge

Try it

Use cursor_agent to add input validation to src/form.ts

Tools

Tool

Does

cursor_agent

Run a prompt with Cursor's agent

cursor_reply

Continue a session

cursor_models

Models your plan offers

cursor_sessions

Sessions of this server

cursor_health

Installation and login check

Supports · version 1.2.3

Works in

Claude Code · Claude Desktop

Model families

Composer · Claude · GPT · Gemini · Grok

Runs on

macOS · Linux

Docs

Read

File

Claude Desktop, local build, environment variables

docs/CONFIGURATION.md

Modes, models and parallel runs

docs/TOOLS.md

Claude supervises, Cursor codes

docs/SUPERVISED-CODING.md

Security

SECURITY.md

Contributing

CONTRIBUTING.md

For AI agents

AGENTS.md

Node.js 22 or newer · MIT · Quantum Media Technologies · Trademarks

Available Tools

5 tools
cursor_agentA

Execute a prompt using Cursor's AI agent with any model id the installed cursor-agent accepts (Composer, Claude, GPT, Gemini, Grok families on your plan; run cursor_models for ids). Modes: 'agent' (tools, terminal, search), 'plan' (design-focused), 'ask' (read-only). In headless mode cursor-agent only PROPOSES file changes unless the server operator set CURSOR_ALLOW_YOLO=true (then --force applies them; CURSOR_SANDBOX=enabled confines them). The result lists the files changed and the model used; a client that sends a progress token gets a progress notification per tool call.

Inputs: prompt (required), mode, model, workspace, +1 more. Returns: model, result, status, stderr, +10 more

cursor_healthA

Check Cursor CLI installation, authentication, and server configuration. Run this first to verify everything is set up correctly.

Inputs: no named parameters.

cursor_modelsA

List the model ids the installed cursor-agent offers (its models command), or a known list when it offers none. Pricing is on cursor.com/docs/models-and-pricing. Use an id with cursor_agent's 'model' parameter.

Inputs: no named parameters.

cursor_replyA

Continue an existing Cursor agent session. Send a follow-up message in the same conversation context. Requires a session_id from a previous cursor_agent call.

Inputs: prompt (required), session_id (required), model, timeout_seconds. Returns: model, result, status, stderr, +10 more

cursor_sessionsA

List Cursor agent sessions created during this MCP server instance. Shows session IDs, models, and prompts. Use session IDs with cursor_reply to continue a conversation.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool targets a distinct operation: starting an agent session, continuing it, listing models, listing sessions, and checking health. The session_id requirement in cursor_reply clearly separates it from cursor_agent, leaving no ambiguity.

    Naming Consistency4/5

    All tools share the consistent `cursor_` prefix and snake_case, but suffixes mix nouns (agent, models, sessions, health) with a verb-like action (reply). This minor deviation is still readable and predictable.

    Tool Count5/5

    Five tools is well-scoped for a Cursor agent wrapper, covering execution, continuation, discovery, and diagnostics without redundancy. Each tool clearly earns its place.

    Completeness4/5

    Core workflows for interacting with the Cursor agent are covered: starting, continuing, listing models/sessions, and health checks. Minor gaps like session cancellation or status inspection exist but are not essential for typical use.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables MCP clients like Claude Code and Codex to delegate coding tasks to Cursor's CLI agent, which implements changes in the workspace and returns clean, structured results for review.
      3
      580 npm
      9
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI assistants and other MCP clients to launch and steer Cursor Cloud Agents on repositories or as repo-less research tasks, including model selection, mid-run follow-ups, cancellation, result retrieval, and run listing. Also exposes authentication checks and per-agent or per-run token usage and cost reporting.
      9
      MIT