openapi-to-mcp

openapi-to-mcp is a standalone proxy that loads an OpenAPI/Swagger specification at startup and exposes it as an MCP (Model Context Protocol) server. It creates one MCP tool per API operation (filtered by include/exclude env vars) and executes tool calls as HTTP requests to the backend REST API. It supports Streamable HTTP transport via GET/POST /mcp and provides correlation-id logging and optional instruction text customization.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ DevTools mcp openapi swagger proxy streamable-http nodejs typescript api-proxy
⚙ Agent Friendliness
60
/ 100
Can an agent use this?
🔒 Security
42
/ 100
Is it safe for agents?
⚡ Reliability
28
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
74
Error Messages
0
Auth Simplicity
70
Rate Limits
20

🔒 Security

TLS Enforcement
30
Auth Strength
45
Scope Granularity
10
Dep. Hygiene
70
Secret Handling
60

TLS usage for the inbound MCP server is not specified (Streamable HTTP endpoints are described without HTTPS/TLS enforcement). Outbound backend authentication supports Basic or Bearer via env vars. No inbound auth/authorization or fine-grained access control is described. Correlation IDs are supported (could aid auditing) but secret-handling/log redaction behavior is not explicitly documented.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
35
Error Recovery
40
AF Security Reliability

Best When

You already have a REST API with a valid OpenAPI 3.x JSON and you want to make those endpoints callable as MCP tools with minimal integration work.

Avoid When

Avoid if you cannot trust or control the OpenAPI spec content (tool schemas/descriptions) or if you require strict transport security and auth/authorization at the MCP server boundary.

Use Cases

  • Expose an existing OpenAPI-defined REST API to MCP-capable AI clients without rewriting the API
  • Rapidly generate MCP tools from an OpenAPI spec for internal automation
  • Use a single source of truth (OpenAPI) for both REST documentation and MCP tool schemas
  • Bridge AI agents to legacy/back-end HTTP services by letting them call MCP tools

Not For

  • APIs without an OpenAPI/Swagger spec (or where the spec is incomplete/incorrect)
  • High-security environments that require strong inbound authentication/authorization at the MCP server layer (not described)
  • Workloads that need advanced rate-limiting, pagination semantics, or complex streaming beyond basic Streamable HTTP proxying

Interface

REST API
Yes
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: HTTP Basic auth to backend API (optional) via MCP_API_BASIC_AUTH Bearer token to backend API (optional) via MCP_API_BEARER_TOKEN
OAuth: No Scopes: No

Authentication described applies to outbound requests to the backend API (Basic/Bearer). No inbound MCP-server authentication/authorization mechanism is documented in the provided content.

Pricing

Free tier: No
Requires CC: No

No hosted pricing information; repository describes a self-hosted MCP server.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Tool naming is derived from path/method and may change if the OpenAPI spec changes; ensure the spec is stable.
  • If include/exclude env vars are misconfigured, expected tools may not be registered.
  • Backend API errors are likely surfaced as MCP/tool call failures, but the specific error mapping and retry behavior are not described.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for openapi-to-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered