Cursor Agent
This MCP server provides a wrapper for the cursor-agent CLI tool, exposing multiple specialized tools for AI-powered code interaction including chat, file editing, code analysis, repository search, task planning, and raw command execution. Built by sailay1996 using Node.js with the MCP SDK and Zod validation, it offers seven distinct tools that compose prompts for different cursor-agent operations while handling timeouts, environment configuration, and output formatting across text, JSON, and markdown formats. The implementation includes comprehensive error handling, configurable model and force flags, debug logging, and both legacy single-shot execution and modern multi-tool approaches, making it valuable for developers who want to integrate cursor-agent's code intelligence capabilities into AI assistant workflows without direct CLI interaction.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/sailay1996/cursor-agent-mcp
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Cursor Agent from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.