#9494th of 111 in MCP servers for developers
mcp2cli
CLI that exposes MCP servers, OpenAPI specs and GraphQL endpoints as commands
- Stars
- 2.4k
- License
- MIT
- Last commit
- Nov 2026
- Language
- Python
1,963 on 21 Apr 20262,439 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
mcp2cli builds a command-line interface at runtime from an MCP server (HTTP/SSE or stdio), an OpenAPI spec, or a GraphQL endpoint, with no code generation. Its compact `--list` output and usage-based ranking cut the tokens an agent spends on tool schemas. It also handles OAuth, named sessions that reuse one MCP connection, and saved "baked" configurations.
Who it is for: Engineers wiring coding agents to MCP, REST or GraphQL APIs via shell
Strengths
- One tool covers MCP (HTTP/SSE, stdio), OpenAPI (JSON/YAML) and GraphQL sources
- OAuth with PKCE, client credentials and a manual-callback mode for headless hosts
- Persistent sessions keep one MCP connection alive across calls
- Secrets can be read from env: or file: references instead of CLI arguments
Weaknesses
- Only MCP sources support `--schema`; `--spec` and `--graphql` reject it
- Spec and tool-list caching has a 1-hour default TTL, so stale lists need `--refresh`
- No tagged release published
- Token-saving figures come from the project's own writeup, not the README itself
What it needs
- no GPU
- Needs uv, mcp Python SDK (>=1.26,<3)
Quick answers
Is mcp2cli open source?
Yes. Its code is on GitHub under the MIT license.
Also in MCP servers for developers
See all 111| Rank | Project | Score |
|---|---|---|
| 1 | gitnexusCode knowledge graph exposed to coding agents through MCP tools | 96 out of 100 |
| 2 | codegraphLocal code knowledge graph that coding agents query over MCP | 95 out of 100 |
| 3 | playwright-mcpMCP server that lets LLMs drive a browser through Playwright accessibility snapshots | 92 out of 100 |
| #4 | code-review-graphLocal Tree-sitter code graph that gives coding assistants review context over MCP | 92 out of 100 |
| #5 | serenaMCP server giving coding agents symbol-level code search, editing and refactoring | 91 out of 100 |