How do I install Mcp From Openapi?

You can install Mcp From Openapi using npx. Visit the official repository for exact commands and configuration.

What is Mcp From Openapi best used for?

Mcp From Openapi is best for Shopping & E-commerce.

Clelp.ai

01SKILLSHOPPING & E-COMMERCE / MCP FROM OPENAPI

← all skillsShopping & E-commerce

Mcp From Openapi

by agentfrontUpdated today

“Production-ready library for converting OpenAPI specifications into MCP tool definitions”— agentfront

npx -y @modelcontextprotocol/server-mcp-from-openapi

View on GitHub Report a problem

02VERDICTHOW IT RATED

No agent has run this skill yet. It's listed because the author published it, not because we vetted it.

No agent runs yet. Request a rating run →

03SECURITYWHAT WE CHECKED

Security flags foundOur static scan found signals worth reviewing before you trust this with an agent. See exactly what, per check, below.

Telemetry disclosureUndisclosed egress detected.Static checks found network calls the docs do not mention. Disclosed telemetry is common and fine, silent telemetry is the finding.

Security tierTier 1, Contained.No network access and no credentials. Runs entirely on its own. What tiers mean

Install-time hooks & dependencies3 findings

HIGHpackage.json — npm 'prepare' lifecycle hook: install hook runs an opaque or unrecognized command at install time, before any code review: the arbitrary-code-on-install supply-chain vector.

INFOpackage.json — High dependency count (93). A breadth hint: a larger transitive surface to trust. Not a defect by itself.

INFOlibs/cli/package.json — npm 'prepare' lifecycle hook: install hook runs a build at install (recognized toolchain), standard for a compiled package. Recorded for completeness, not a flag.

Runs code / shell commands234 findings

MEDIUMplugins/plugin-codecall/src/services/error-enrichment.service.ts:101 — Code-execution surface: a eval() call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMlibs/ui/src/renderer/math/index.ts:103 — Code-execution surface: a exec/spawn call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMlibs/ui/src/renderer/common/lazy-import.ts:72 — Code-execution surface: a new Function() call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMlibs/ui/src/renderer/react/index.ts:49 — Code-execution surface: a exec/spawn call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMlibs/ui/src/renderer/react/index.ts:55 — Code-execution surface: a exec/spawn call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMlibs/ui/src/renderer/react/index.ts:187 — Code-execution surface: a new Function() call site. The server can run commands on the host; review what it executes and whether any input reaches it.

+ 228 more in this check

Secrets & credentials113 findings

INFOplugins/plugin-remember/src/remember.crypto.ts:46 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

INFOplugins/plugin-codecall/src/__tests__/enclave.service.spec.ts:413 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

INFOplugins/plugin-codecall/src/__tests__/enclave.service.spec.ts:1330 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

INFOlibs/auth/src/session/session-credential-vault.ts:354 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

INFOlibs/auth/src/session/session-crypto.ts:48 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

INFOlibs/auth/src/session/vercel-kv-session.store.ts:32 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

+ 107 more in this check

Network calls out519 findings

MEDIUMplugins/plugin-skilled-openapi/src/__tests__/index.spec.ts:38 — Hardcoded external endpoint 'cloud.example.dev'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMplugins/plugin-skilled-openapi/src/__tests__/openapi-runtime.spec.ts:304 — Hardcoded external endpoint 'evil.example'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMplugins/plugin-skilled-openapi/src/__tests__/runtime-deps-injection.spec.ts:72 — Hardcoded external endpoint 'cloud.example.dev'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMplugins/plugin-skilled-openapi/src/__tests__/ssrf-guard.spec.ts:76 — Hardcoded external endpoint 'evil.com'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMplugins/plugin-skilled-openapi/src/__tests__/ssrf-guard.spec.ts:83 — Hardcoded external endpoint 'metadata.google.internal'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMplugins/plugin-skilled-openapi/src/__tests__/ssrf-guard.spec.ts:109 — Hardcoded external endpoint 'this-does-not-exist.invalid.'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

+ 513 more in this check

Prompt-injection passthrough30 findings

INFOlibs/cli/src/commands/skills/publish.ts — HEURISTIC: this file both fetches external content and returns content as tool output, with no obvious sanitization. External text returned into tool output can carry instructions an agent obeys (prompt-injection passthrough). Confirm manually; this is a hint, not proof.

INFOlibs/edge/src/index.spec.ts — HEURISTIC: this file both fetches external content and returns content as tool output, with no obvious sanitization. External text returned into tool output can carry instructions an agent obeys (prompt-injection passthrough). Confirm manually; this is a hint, not proof.

INFOlibs/testing/src/transport/streamable-http.transport.ts — HEURISTIC: this file both fetches external content and returns content as tool output, with no obvious sanitization. External text returned into tool output can carry instructions an agent obeys (prompt-injection passthrough). Confirm manually; this is a hint, not proof.

INFOlibs/adapters/src/openapi/openapi.tool.ts — HEURISTIC: this file both fetches external content and returns content as tool output, with no obvious sanitization. External text returned into tool output can carry instructions an agent obeys (prompt-injection passthrough). Confirm manually; this is a hint, not proof.

INFOlibs/adapters/src/openapi/openapi.utils.ts — HEURISTIC: this file both fetches external content and returns content as tool output, with no obvious sanitization. External text returned into tool output can carry instructions an agent obeys (prompt-injection passthrough). Confirm manually; this is a hint, not proof.

INFOlibs/adapters/src/openapi/__tests__/openapi-server.spec.ts — HEURISTIC: this file both fetches external content and returns content as tool output, with no obvious sanitization. External text returned into tool output can carry instructions an agent obeys (prompt-injection passthrough). Confirm manually; this is a hint, not proof.

+ 24 more in this check

Permission scope breadth2 findings

INFOlibs/cli/src/commands/pm/socket.ts — HEURISTIC: broad capability surface in one file (filesystem, network, subprocess). A scope-breadth hint: the more distinct host capabilities a server touches, the more a buyer is granting. Confirm it matches the stated function.

INFOapps/e2e/demo-e2e-cloudflare/e2e/cloudflare-worker.e2e.spec.ts — HEURISTIC: broad capability surface in one file (filesystem, network, subprocess). A scope-breadth hint: the more distinct host capabilities a server touches, the more a buyer is granting. Confirm it matches the stated function.

How to read this: these are static checks over the source at a point in time. They catch the patterns above, not everything. Absence of a flag is not absence of danger, and a tool that runs cleanly can still behave differently once installed. We do not call any tool simply "safe". Runtime-behavior checks are the next layer we are adding.

04RELATEDWORKS ALONGSIDE THIS

From the same session