Konfig MCP Engine
Allows ingesting OpenAPI/Swagger v3.0 and v3.1 specifications and transforming their REST endpoints, parameters, headers, and JSON request bodies into validated MCP tool schemas.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Konfig MCP Engine turn my petstore openapi.json into MCP tools"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
โก Konfig MCP Engine
Enterprise OpenAPI v3.0 / v3.1 to Live Model Context Protocol (MCP) Generator & Tool Bridge.
Transform existing enterprise Swagger/OpenAPI specifications into typed, agent-ready MCP tools on the fly โ zero code, zero boilerplate, zero hallucinated parameters.
๐ก The Problem
Enterprise architectures run on thousands of REST endpoints documented via OpenAPI / Swagger. However, bringing these APIs to autonomous AI agents (Claude Code, Cursor, Antigravity, AutoGen, CrewAI) currently requires:
Manual Glue Code: Handcrafting boilerplate MCP servers for each microservice.
Schema Inconsistencies: Parameter types, headers, and request bodies often get mistranslated, causing LLM tool call failures.
Maintenance Hell: Every upstream API update breaks hardcoded tool implementations.
Konfig MCP Engine bridges this gap: Derived from years of production-grade AST engineering at Konfig (Ex-C3-AI), it dynamically ingests OpenAPI v3.0 and v3.1 specs and transforms them in-memory into fully validated, typed Model Context Protocol tool schemas with zero external dependencies.
Related MCP server: API-to-MCP Converter
โก Key Capabilities
๐ Instant OpenAPI to MCP Transformation: Ingests raw OpenAPI JSON objects or files and outputs JSON-RPC 2.0 MCP
tools/listschemas instantly.๐ฏ Strict Schema Mapping: Maps path parameters, query parameters, headers, and
application/jsonrequest bodies directly to compliant JSON Schema v7 definitions.๐ชถ Zero External Dependencies: Built with pure ECMAScript standard libraries (
node:readline,node:fs). Zero bloat, instant startup, hermetic execution.๐ก๏ธ Anti-Carbonara Architecture: Clean separation of concerns:
src/core/: Pure deterministic transformation logic (100% in-memory, no I/O side effects).src/cli/: Lightweight command-line interface for pipelines and automation.src/mcp/: Native Stdio JSON-RPC 2.0 server for Claude Desktop, Cursor, and Antigravity.
๐ค Autonomous Multi-Agent Friendly: Agents can dynamically discover API capabilities at runtime by passing any OpenAPI spec into
konfig_transform_openapi.
๐ค Model Context Protocol (MCP) Setup
Add to Claude Desktop / Cursor / Antigravity
Add the engine to your claude_desktop_config.json or Antigravity MCP settings:
{
"mcpServers": {
"konfig-mcp-engine": {
"command": "node",
"args": ["/path/to/konfig_mcp_engine/src/mcp/server.js"]
}
}
}Or run via npx (when installed from npm):
{
"mcpServers": {
"konfig-mcp-engine": {
"command": "npx",
"args": ["-y", "konfig-mcp-engine"]
}
}
}Available MCP Tools
Tool Name | Description | Parameters |
| Transforms an OpenAPI 3.0/3.1 specification JSON object into ready-to-call MCP Tool schemas for AI agents. |
|
Example Tool Invocation
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "konfig_transform_openapi",
"arguments": {
"spec": {
"openapi": "3.0.0",
"info": { "title": "Petstore API", "version": "1.0.0" },
"paths": {
"/pets": {
"get": {
"operationId": "listPets",
"summary": "List all pets",
"parameters": [
{ "name": "limit", "in": "query", "schema": { "type": "integer" } }
]
}
}
}
}
}
}
}๐ป CLI Usage
You can also use Konfig MCP Engine directly from the command line:
# Generate MCP Tools JSON from an OpenAPI specification
node src/cli/index.js generate path/to/openapi.jsonOr when installed globally:
konfig-mcp generate ./swagger.json > mcp-tools.json๐งช Testing & Verification
Run the hermetic test suite:
npm testExpected output:
โถ Konfig MCP Engine
โ transforms OpenAPI endpoints into MCP tools
โ handles empty or invalid specs gracefully
โ handles MCP handshake, notifications, and ping
โ Konfig MCP Engine (5ms)๐๏ธ Architecture
konfig_mcp_engine/
โโโ src/
โ โโโ core/
โ โ โโโ transformer.js # Pure OpenAPI -> MCP Tool AST Transformer
โ โ โโโ index.js # Core module export
โ โโโ cli/
โ โ โโโ index.js # CLI entry point (konfig-mcp)
โ โโโ mcp/
โ โโโ server.js # Stdio JSON-RPC 2.0 MCP Server
โโโ tests/
โ โโโ transformer.test.js # Unit & Integration tests
โโโ package.json
โโโ server.json # MCP Registry Schema
โโโ smithery.yaml # Smithery deployment config
โโโ Dockerfile๐ Origin & Heritage
This project is part of the Diamantenschmiede (Pioneer #7) open-source initiative, refining and advancing abandoned or sunset software into hardened, zero-dependency tools for the modern agentic era.
Based on foundational AST research from konfig-dev/konfig (MIT, Copyright (c) 2021-2024 Konfig Inc.).
๐ License
MIT ยฉ 2026 tastenkasperle (Diamantenschmiede) & Konfig Inc.
Available Tools
1 toolkonfig_transform_openapiB
Transforms an OpenAPI 3.0/3.1 specification JSON object into ready-to-call MCP Tool schemas for AI agents.
Inputs: spec (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of confusion or misselection. Its purpose is stated precisely: transform an OpenAPI spec into MCP tool schemas.
The single tool uses a clear snake_case verb_noun pattern with a namespace prefix (konfig_transform_openapi). Consistency cannot really be violated with one tool, but the naming is readable and predictable.
A single tool is thin for something branded as an 'Engine'; it covers only the transform step of what could be a larger workflow. Still, the narrow stated purpose makes one tool defensible, so it sits at borderline rather than clearly wrong.
The surface covers transformation but offers no validation, listing, batch processing, or reverse conversion, leaving agents to handle errors and preprocessing themselves. It is usable for its core task but has notable gaps around it.
Maintenance
Related MCP Connectors
Convert, lint and generate LLM tool schemas for OpenAI, Anthropic, Gemini and MCP
Point Gecko at an OpenAPI spec; get first-call-correct, auth-hidden agent tools.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Discover and call 10,000+ production APIs from one MCP server. Pay-per-call billing for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceDynamically converts any REST service's OpenAPI specification into MCP tools, enabling interaction with REST endpoints through natural language. Supports Spring Boot services and includes auto-discovery for common API configurations.-
- AlicenseNot gradedqualityDmaintenanceConverts any REST API into MCP-compatible tools instantly by providing an OpenAPI/Swagger spec, enabling seamless integration with AI agents.19 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceTurns any OpenAPI/Swagger API into MCP tools, enabling AI assistants to call REST API endpoints directly.2MIT
- AlicenseNot gradedqualityDmaintenanceConverts any OpenAPI v3 spec into an MCP server with typed tools, resources, and prompts, enabling AI agents to call any REST API via natural language.18 npmMIT