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.
git clone --depth 1 https://github.com/swayam5342/api2mcpWrote 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.
[](https://agentmods.dev/mcp/swayam5342/api2mcp/api2mcp)<a href="https://agentmods.dev/mcp/swayam5342/api2mcp/api2mcp"><img src="https://agentmods.dev/badge/mcp/swayam5342/api2mcp/api2mcp/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.
<a href="https://agentmods.dev/mcp/swayam5342/api2mcp/api2mcp"><img src="https://agentmods.dev/badge/mcp/swayam5342/api2mcp/api2mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
api2mcp 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 1mo 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.
What it actually says
{ "api2mcp": { "command": "npx", "args": [ "-y", "@swayam5342/api2mcp" ] } }
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.
- 1mo ago First seen · 9 lines scan A 900f346667fc
api2mcp is an MCP server published in the GitHub repository swayam5342/api2mcp (1 stars, last pushed 2mo 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.
Other mcp servers, from other repositories
toolport-openapi-mcp
Turn any OpenAPI/Swagger spec into an MCP server: one tool per endpoint. A showcase for Toolport (toolport.app). Runs locally from the toolport-openapi-mcp npm package.
mcpify
CLI tool that generates an MCP server from OpenAPI specs automatically. Runs locally from the @bahridev/mcpify npm package.
x-openapi-flow-mcp
OpenAPI lifecycle guard and MCP sidecar for policy-driven API orchestration. Runs locally from the x-openapi-flow npm package.
mcp-openapi-bridge
Generic MCP server that bridges any OpenAPI 3.x REST API to Claude Code — one tool per endpoint, auto-discovered from the spec. Runs locally from the mcp-openapi-bridge npm package. Needs 15 environment variables to run.
zoom-agent-cli
CLI and MCP server for the Zoom API — built for humans and AI agents. Runs locally from the zoom-agent-cli npm package.
markovo
Customer-only Markovo API, CLI, and MCP client. Runs locally from the markovo Python package. Needs 2 environment variables to run.