It avoids manually defining each API operation as an agent tool when the API is already described by OpenAPI files.

museum-api — MCP server by ephrin/openapi-mcp-bridge

museum-api

museum-api is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from ephrin/openapi-mcp-bridge. Its token cost is not measured, scanned A, original, MIT.

A local bridge that turns OpenAPI definitions—descriptions of web APIs—into MCP tools that an agent can use. It connects those tools to an API using configured credentials.

In plain words

What is it for?: Use it to expose an API described by OpenAPI definitions to an MCP-compatible agent. It requires a definitions path plus a username and password.
Why use it?: It avoids manually defining each API operation as an agent tool when the API is already described by OpenAPI files.

Written for no agent in particular: it speaks MCP, so any client can run it. Also seen: listed in a Claude config.

Good fit Use it to expose an API described by OpenAPI definitions to an MCP-compatible agent. It requires a definitions path plus a username and password.

Compare 6 mcp servers from other repositories ↓

Install with agentmods

npx agentmods add mcp/ephrin/openapi-mcp-bridge/claude-desktop-museum-api

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/ephrin/openapi-mcp-bridge

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/ephrin/openapi-mcp-bridge/claude-desktop-museum-api/github.svg)](https://agentmods.dev/mcp/ephrin/openapi-mcp-bridge/claude-desktop-museum-api)

Your own site

<a href="https://agentmods.dev/mcp/ephrin/openapi-mcp-bridge/claude-desktop-museum-api"><img src="https://agentmods.dev/badge/mcp/ephrin/openapi-mcp-bridge/claude-desktop-museum-api/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/ephrin/openapi-mcp-bridge/claude-desktop-museum-api"><img src="https://agentmods.dev/badge/mcp/ephrin/openapi-mcp-bridge/claude-desktop-museum-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

museum-api scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

examples/claude-desktop/claude_desktop_config.json · 14 lines

What it actually says

{
  "museum-api": {
    "command": "npx",
    "args": [
      "openapi-mcp-bridge",
      "--definitions",
      "/absolute/path/to/your/api-definitions"
    ],
    "env": {
      "MUSEUM_API_USERNAME": "demo_user",
      "MUSEUM_API_PASSWORD": "demo_password"
    }
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 14 lines scan A 850eac6cb580

Subscribe to this mod's changes

museum-api is an MCP server published in the GitHub repository ephrin/openapi-mcp-bridge (1 stars, last pushed 1y ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs Building agents

museum-api next to 6 mcp servers from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
museum-apiephrin/openapi-mcp-bridge	MCP server	1	1y ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
mcp-serverIgniteUI/igniteui-cli	MCP server	137	today	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
workospraveenjuge/teak	MCP server	24	yesterday	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
pocket-id-mcpX1pheR/pocket-id-mcp	MCP server	0	yesterday	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
admin-mcphellocoop/admin-mcp	MCP server	4	2mo ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
final-docsFinal-Commerce/final-pos-mcp	MCP server	0	19d ago	Apache-2.0	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
ainative-strapi-mcp-serverAINative-Studio/ainative-strapi-mcp-server	MCP server	0	3mo ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode