{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_gepcrrrvnf9y","handle":"prompt-to-mcp","url":"https://wellknown.network/agents/prompt-to-mcp","links":{"self":"https://wellknown.network/agents/prompt-to-mcp/record.json","html":"https://wellknown.network/agents/prompt-to-mcp","markdown":"https://wellknown.network/agents/prompt-to-mcp/record.md","api":"https://wellknown.network/api/v1/agents/prompt-to-mcp","status":"https://wellknown.network/api/v1/agents/prompt-to-mcp/status","claim":"https://wellknown.network/agents/prompt-to-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/prompt-to-mcp/claim.json","badge":"https://wellknown.network/agents/prompt-to-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:prompt-to-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"prompt-to-mcp","summary":"Describe the MCP server you want, point at an OpenAPI spec, and get a small curated FastMCP server (a few workflow-level tools, not hundreds of endpoint clones) plus a built-in eval harness that measures it.","description":"# prompt-to-mcp\n\n[![tests](https://github.com/KnaniOussama/prompt-to-mcp/actions/workflows/test.yml/badge.svg)](https://github.com/KnaniOussama/prompt-to-mcp/actions/workflows/test.yml)\n[![PyPI](https://img.shields.io/pypi/v/prompt-to-mcp)](https://pypi.org/project/prompt-to-mcp/)\n[![Python](https://img.shields.io/pypi/pyversions/prompt-to-mcp)](https://pypi.org/project/prompt-to-mcp/)\n[![License: MIT](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)\n\nDescribe the MCP server you want. Point at an OpenAPI spec. Get a small, curated\nFastMCP server as editable code.\n\n```bash\npip install prompt-to-mcp        # or run it without installing: uvx prompt-to-mcp\n```\n\nBig APIs make bad MCP servers when converted one tool per endpoint: Stripe's spec\nbecomes 587 tools and ~463,000 tokens of definitions, more than 14 times a 32k context\nwindow. prompt-to-mcp compiles the server you describe instead, with just the tools\nthat serve your use case, and ships an eval harness that measures the result.\n\n## Contents\n\n- [Quick start](#quick-start)\n- [Example: 587 Stripe operations, 6 tools](#example-587-stripe-operations-6-tools)\n- [How it works](#how-it-works)\n- [Use the generated server](#use-the-generated-server)\n- [Models and providers](#models-and-providers)\n- [Evidence](#evidence)\n- [Coverage tradeoff](#coverage-tradeoff)\n- [CLI reference](#cli-reference)\n- [Development](#development)\n- [License](#license)\n\n## Quick start\n\nYou need Python 3.12+ and one LLM. A local Ollama model works; so does any key that\nspeaks the Anthropic or OpenAI protocol. Nothing to clone.\n\n```bash\n# grab a small example spec\ncurl -o petstore.yaml https://raw.githubusercontent.com/KnaniOussama/prompt-to-mcp/master/tests/fixtures/petstore.yaml\n\n# 1. see what a naive 1:1 conversion would cost (free, no LLM involved)\nuvx prompt-to-mcp inspect petstore.yaml\n\n# 2. describe the server you want (the one step that calls an LLM)\nuvx prompt-to-mcp plan petstore.yaml \"a server for looking up pets and thei…","publisher":{"name":"Oussama Knani","url":null},"homepage":null,"repository":null,"version":"0.1.1","license":"MIT","protocols":["mcp"],"tags":["agents","codegen","eval","fastmcp","llm","mcp","model-context-protocol","openapi","tools"],"pricing":null,"endpoints":[{"url":"pypi:prompt-to-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"data.apis","name":"API Access","confidence":1,"provenance":"declared"},{"slug":"ai.prompting","name":"Prompt Management","confidence":1,"provenance":"derived"},{"slug":"code.generation","name":"Code Generation","confidence":1,"provenance":"declared"}],"categories":["ai","code","data"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"prompt-to-mcp","registry":"pypi","observedAt":"2026-09-10T10:25:40.564Z","publishedAt":"2026-07-19T07:46:19.110809Z","latestVersion":"0.1.1"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"prompt-to-mcp","url":"https://pypi.org/project/prompt-to-mcp/","firstSeenAt":"2026-09-10T10:24:05.940Z","fetchedAt":"2026-09-10T10:24:05.940Z","normalizedAt":"2026-09-10T10:24:05.940Z"}]},"firstSeenAt":"2026-09-10T10:24:05.940Z","updatedAt":"2026-09-10T10:25:40.564Z"}