Skip to main content
Glama

sevdesk-mcp

The whole sevDesk API in two MCP tools. A local, open-source MCP server that lets AI assistants (Claude Desktop, ChatGPT Desktop, Claude Code, Codex CLI, …) work with sevDesk through just search and execute: instead of one tool per endpoint, the model writes small JavaScript snippets that run in a local sandbox against the sevDesk API ("Code Mode").

Status: early development. The server starts, but has no tools yet. Do not use it with a real sevDesk account yet.

Not developed or endorsed by sevDesk. (Nicht von sevDesk entwickelt oder unterstützt.)

Development

Requirements: Bun ≥ 1.4.4 and Node.js ≥ 22.18.

bun install       # dependencies + git hooks
bun run verify    # everything CI checks
bun run build && node dist/cli.js   # start the server on stdio

The product requirements live in docs/prd/PRD-sevdesk.md, the foundation decisions in docs/decisions/0001-foundation.md.

Related MCP server: universal-dev-mcp

License

MIT

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that enables AI agents to execute sandboxed JavaScript and TypeScript code instead of calling individual tools directly. It significantly reduces token usage by allowing agents to filter, aggregate, and transform data locally before returning results.
      13 npm
      28
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that exposes any OpenAPI REST API via two tools: search for discovering endpoints and execute for making API calls. It uses Code Mode to keep token footprint low and runs user-written JavaScript in a sandbox.
      9 npm
      3
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Enables AI clients to access modular tools for file and data handling, statistical analysis, local NLP, automation, and system information over stdio or HTTP, with automatic module discovery and built-in sandboxing and security controls.
      31
      MIT