Agentify MCP server
io.github.sani-savaliya/agentify·v0.1.1·1 starsTurn any OpenAPI/Swagger spec into an MCP server - every API operation becomes an agent tool.
1 stars43 downloads/wk
Reviews
Write oneNobody has reviewed Agentify yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Agentify tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan21 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 103 days ago8/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Agentify compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 72/100
- higher than 40% of 4,460 AI and agents servers
- GitHub stars
- 1
- more than 50% of 2,711 AI and agents servers
- Downloads a week
- 43
- more than 35% of 1,538 AI and agents servers with a package
Install Agentify in Claude Code, Cursor or VS Code
Runs npx -y agentify-openapi on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add agentify -- npx -y agentify-openapi
What the publisher says
From the Agentify repository's README, as published. We do not edit it. Read it on GitHub
agentify
Turn any OpenAPI / Swagger spec into an agent-ready MCP server.
Listed on the official MCP Registry (io.github.sani-savaliya/agentify) and Smithery.
Point it at a spec — a URL, a file, OpenAPI 3.x or Swagger 2.0 — and every operation becomes a tool an AI agent can call. No code generation, no per-API boilerplate, no hosting. One command.
npx agentify-openapi https://petstore3.swagger.io/api/v3/openapi.json --listSwagger Petstore - OpenAPI 3.0 v1.0.27
Base URL: https://petstore3.swagger.io/api/v3
Tools: 19
getPetById
Find pet by ID.
findPetsByStatus
Finds Pets by status.
...Why
*"Today, agents have to operate software designed for humans. The interfaces of
the future will be built for agents — APIs, MCPs, CLIs — with agents as
first-class citizens."* — YC RFS: Software for Agents
There are tens of thousands of APIs that already describe themselves with an OpenAPI document. agentify makes every one of them agent-native, instantly, without anyone hand-writing an integration.
Use it with Claude, Cursor, Windsurf — any MCP client
Add it to your client's MCP config. The same command/args shape works in Claude Desktop, Claude Code (claude mcp add), Cursor (.cursor/mcp.json), Windsurf, Cline, and anything else that speaks MCP:
{
"mcpServers": {
"petstore": {
"command": "npx",
"args": ["-y", "agentify-openapi", "https://petstore3.swagger.io/api/v3/openapi.json"]
}
}
}The agent now has one tool per API operation. Calling a tool builds the HTTP request (path params, query string, headers, JSON body) and returns the live response.
Big API? Pick just the tools you need
Pointing at GitHub (1000+ operations) or Stripe (400+) would flood your agent with hundreds of tools and wreck its tool-selection accuracy. Filter down to what matters — by tag, HTTP method, or name glob — and cap the total:
# GitHub, read-only, just the repo endpoints
npx agentify-openapi https://api.github.com/openapi.json --tag repos --read-only
# Stripe customer endpoints only, hard cap at 25 tools
npx agentify-openapi ./stripe.json --include "*Customer*" --max-tools 25{
"mcpServers": {
"github-repos": {
"command": "npx",
"args": ["-y", "agentify-openapi", "https://api.github.com/openapi.json",
"--tag", "repos", "--read-only", "--max-tools", "30"],
"env": { "AGENTIFY_BEARER_TOKEN": "ghp_your_token" }
}
}
}--read-only (GET/HEAD/OPTIONS) is also a simple safety rail — expose a giant API to an agent without exposing anything that can mutate state.
Auth
Provide credentials via environment variables — agentify reads the spec's declared security scheme to find the right header name when it can:
You can also inject raw headers from the CLI: --header "X-Org-Id: 42" (repeatable).
CLI
agentify <spec-url-or-file> [options]
--base-url <url> Override the API base URL from the spec
--header "K: V" Add a raw header to every request (repeatable)
--name <name> Override the MCP server name
--list Print the discovered tools and exit (no server)
-h, --help Show helpShortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Agentify: common questions
- Is Agentify MCP server safe?
- Mostly: it is graded B (72/100). Read the Agentify safety report
- How do I install Agentify?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Agentify need an API key?
- Yes. The registry entry asks for
AGENTIFY_BEARER_TOKEN,AGENTIFY_API_KEY,AGENTIFY_BASIC_PASS. - Is Agentify maintained?
- The last commit was 142 days ago (2026-06-15). The latest release is v0.1.1.
- How does Agentify compare with other AI and agents MCP servers?
- safety score 72/100 (higher than 40% of 4,460 AI and agents servers); github stars 1 (more than 50% of 2,711 AI and agents servers); downloads a week 43 (more than 35% of 1,538 AI and agents servers with a package). Full comparison.