MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Scores any public URL on whether AI agents can discover, understand, call, and trust it. Machine-payable via x402 — USDC on Base, no account.
MIT ★ 1 -
Accessibility audit for chart color palettes: WCAG non-text contrast, Machado 2009 CVD simulation, OKLab dE separation. One engine, four faces: API, CLI, CI gate, MCP server.
MIT -
Open-source database, API access & deployment governance platform A SQL, NoSQL, and API proxy that puts review, approval, and audit between your team and production data and services.
Apache-2.0 ★ 13 -
Meta Ads MCP server + Python client for the Marketing API. An AI agent can read Facebook and Instagram campaigns, ad sets and ads and propose changes; every write goes through a preview a human approves, with guardrails, a kill switch and an audit log.
MIT -
mcp-enterprise-startergithub.com/InkByteStudio/mcp-enterprise-starterupdated this year
Production-grade MCP server giving AI agents secure, read-only PostgreSQL access — API key auth, SQL sandboxing, PII masking, rate limiting, and audit logging
MIT -
id.wisperagithub.com/gecochief/id.wisperaupdated this year
Passport & visa system for AI agent credentials. Detect, classify, and govern API keys, tokens, and secrets across MCP, OpenAI, Anthropic, LangChain, and more. Encrypted vault, policy engine, audit trails, delegation chains. Drop-in MCP server replaces plaintext credential storage.
MIT ★ 4 -
Vorim AIno update data
Identity, permissions, and signed audit trails for AI agents. Every agent gets an Ed25519 cryptographic identity, scoped permissions, and an append-only audit trail. Permission checks run in under 5 milliseconds. Audit events export with a SHA-256 manifest for tamper-evident, offline verification. Trust scores and identity verification are publicly accessible via REST endpoint. Anchored to the IETF Internet-Draft for VAIP (the Vorim Agent Identity Protocol). **17 tools** covering agent registration, ephemeral agents (W3C did:key), permissions, audit events, audit export, credential delegation, scoped token issuance, and public trust verification. **Get an API key:** [vorim.ai/settings/api-keys](https://vorim.ai/settings/api-keys) **Docs:** [vorim.ai/docs](https://vorim.ai/docs) **Open protocol:** [github.com/Kzino/vorim-protocol](https://github.com/Kzino/vorim-protocol)
smithery -
Free, open-source on-page SEO audit: web app, JSON API, CLI, TUI and MCP server. https://seo.rank
MIT -
Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No external API required for local memory. Install with pip: pip install atmem
Apache-2.0 ★ 14 -
@qexle/seo-mcpactive
Keyless SEO radar MCP: live trends, keyword demand, SERP composition and on-page audits. No API keys required.
npm MIT -
Remote MCP server for smart-contract audits of Solidity (any EVM chain) and DAML/Canton, plus the Agent Transaction Check: one API call before an AI agent signs a crypto payment. Paid from a prepaid balance.
-
Evidence-grade landing page audit via MCP. Detects conversion leaks across 9 signals. Free, no API key.
-
SEOBolt for Cursor: MCP config, rule and skills for SEO audits and fix plans (API key)
NOASSERTION -
Pandaone Guard — Free open-source MCP server for AI code audit. L1-L6 defense (file lock + audit log + pre-commit hooks) for Claude/Cursor/Trae. Local stdio, no API key, MIT.
MIT ★ 1 -
MCP server exposing the Tenable Vulnerability Management audit log as analysis tools: per-actor baselines, API-key usage attribution, and explained anomaly detection.
MIT -
fdl-mcp-servergithub.com/Nareshdevelop/fdl-mcp-serverupdated this year
MCP server for fivedaylaunch.com - lets Claude audit, compare, and check AI-visibility of any small business website. No API key required.
MIT -
One scored audit of everything you ship: code, sites, apps, APIs, containers, IaC, cloud and mobile. CLI, CI and MCP for AI agents.
npm MIT ★ 1 -
agent-receipts-mcpgithub.com/dhanushs1912-svg/agent-receipts-mcpupdated this year
Prove what your AI agents did - EU AI Act-ready audit trails: signed, tamper-evident receipts with offline verification. MCP server + HTTP API.
MIT ★ 1 -
MCP server for Raposa Aval: request_human_approval — a named person approves or rejects, silence is not consent, hash-chained audit log. Local (uvx) or remote at dcescrypt.com/api/mcp
MIT ★ 1 -
aximur-mcpupdated this year
MCP server for the AXIMUR verification API — verify a claim against grounding evidence and get SUPPORTED / UNSUPPORTED / UNCERTAIN with confidence and an audit trail.
npm MIT -
passare-mcpgithub.com/sanjibani/passare-mcpupdated this year
First MCP server for the Passare Public API - read funeral-home case data (cases, acquaintances, addresses, contacts) from Claude / Cursor / any MCP client. MIT, ruff + mypy --strict clean, 30 tests, JSONL audit logging per the Blackwell MCP security audit pattern.
MIT -
roasr-mcpgithub.com/RoASr-com/roasr-mcpupdated this year
MCP server for RoASr — connect Claude, ChatGPT, Codex or Cursor to Meta / Google Ads / Yandex Direct ad-audit findings, KPIs, competitor spy and Vision creative analysis. Dependency-free client over the public /v1 API.
MIT -
IGL, Identity Governed Logic: a governed identity graph, policy engine and signed audit chain for AI agents. Every answer cites its records; every action leaves a receipt. Runtime, platform API, MCP server and the id-me.ai site.
Apache-2.0 ★ 1 -
A Model Context Protocol server that lets Claude and other AI assistants look up customers, orders and stock and take real actions, with a role for every API key, hard business rules in code and a tamper-evident audit log of every call.
MIT -
Security-focused MCP server for Claude Desktop - Read-only access to KnowBe4 GraphQL API with 92+ optimized queries, PII filtering, and audit logging
MIT ★ 1 -
Website audit, tech-stack detection, page-to-Markdown, broken links & PDF/OCR in one API. Sold via RapidAPI, x402 pay-per-call (USDC) and MCP.
GPL-3.0 -
Local-first MCP credential broker: agents use gated APIs through scoped, audited requests without ever seeing the secret.
Apache-2.0 ★ 3 -
httptoolkit-mcpgithub.com/NinjaScout77/httptoolkit-mcpupdated this year
MCP server that lets LLMs drive HTTPToolkit for automated API security testing — replay, mutation, and audit on captured mobile, desktop, and CLI traffic
MIT ★ 2 -
APIMeshgithub.com/mbeato/APIMeshupdated this year
APIMesh — 23 pay-per-call web analysis APIs + 16-tool MCP server with autonomous API generation. Security audits, SEO, tech stack detection. x402 + Stripe MPP payments.
MIT ★ 6 -
Google Tag Manager API v2 MCP server for inspecting, auditing, drafting, and publishing GTM containers and tags.
-
SEO MCP for Gemini CLI: keyword research, Google SERP API, rank tracking, backlinks, site audits and a free Google Search Console MCP
MIT -
SEO, AEO and GEO audit MCP server for Claude Code, Cursor and Codex. Audit a page as AI search crawlers see it, get a fix pack, apply and verify. Free, no API key.
MIT -
Audit: Give AI coding agents (Claude Code, Cursor) API keys without pasting them in chat; macOS Keychain, sealref:// refs, MCP server
MIT -
dynamic-db-mcp-servergithub.com/hand-by-hand/dynamic-db-mcp-serverupdated this year
Turn any relational database into a secure MCP server by configuration: API Key auth, table ACL, SQL AST validation, audit log and a web admin console.
npm MIT -
trustmeshgithub.com/labrat-akhona/trustmeshupdated this year
Agentic AI fraud prevention for African mobile money. 6 CAMARA APIs via Nokia Network as Code with hash-chained audit. Africa Ignite Hackathon 2026 (GSMA + Nokia).
MIT -
Tailscale MCP server: admin-API tools for devices, ACLs, DNS, auth keys, users, and audit logs, plus a CLI to validate and deploy ACLs.
npm MIT -
15 production data, monitoring and audit APIs on Apify — MCP-ready, pay-per-event, x402/USDC, 30 public task examples with verified outputs
★ 2 -
Free on-page SEO audits from Claude Code or Cursor — titles, meta, canonicals, robots, JSON-LD; local, no API keys.
npm MIT -
Send real faxes from any MCP-enabled AI assistant. Wraps the FaxDrop API (PDF/DOCX/JPG/PNG, international numbers, status polling) with rate limits, dry-run mode, and audit logging.
npm MIT -
Agent-first TikTok Content Posting API CLI and MCP server with dry-run publishing, OAuth readiness and privacy audit tools.
npm MIT -
Self-hosted MCP server to operate Google Ads (API v25) and Google Merchant Center from Claude — read/write with human confirmation, MCC isolation, and audit logging.
MIT ★ 4 -
Send real faxes from any MCP-enabled AI assistant. Wraps the FaxDrop API (PDF/DOCX/JPG/PNG, international numbers, status polling) with rate limits, dry-run mode, and audit logging.
MIT ★ 5 -
gaiia-mcp-servergithub.com/dapooleygmailcom/gaiia-mcp-serverupdated this year
API Interrogator to produce MCP, A2A and OpenAPI specifications, and audit/review codebases with Expert Proxies
★ 5 -
Read Google Trends, autocomplete, SERPs & page audits from your agent. No API key.
MIT -
@mbeato/apimesh-mcp-servergithub.com/mbeato/conwayupdated this year
MCP server for APIMesh — 76 x402-payable tools for AI agents (74 APIs + wallet usage + spend caps). Covers web vitals, security headers, SEO audits, email security and verification, tech-stack detection, brand assets, redirect chains, indexability, brand
npm MIT -
cpp-espace-mcpgithub.com/norm613/cpp-espace-mcpupdated this year
MCP server exposing the eSpace facilities management REST API to Claude Code or any MCP client. Per-user API key deployment — each user runs their own instance for correct audit attribution.
NOASSERTION -
Self-hosted HTTP API and MCP server that reads, organizes, drafts, replies to and sends mail across multiple IMAP/SMTP accounts, with per-token scopes, send limits, an audit log and signed new-mail webhooks.
WTFPL ★ 9 -
mintsoft-mcpgithub.com/AhamadFalah/mintsoft-mcpupdated this year
MCP server for the Mintsoft WMS API — read-only by default, allowlist-gated writes, full audit log
Apache-2.0 -
The most complete Mailchimp Marketing API MCP server: 227 tools across campaigns, audiences, reports, segments, automations and full e-commerce, with multi-account support and runtime-security guardrails (read-only, dry-run, audit, per-tool risk metadata).
MIT ★ 25 -
@pofky/appstore-connect-mcpupdated this year
MCP server for Apple App Store Connect API - check review status, read customer reviews, download sales reports, pre-submission audit, daily briefings. Works with Claude Code, Cursor, Windsurf, or any AI coding agent. Free tier included.
npm MIT -
Audit AI plugin for Claude Code and Cursor: finds authorization holes in Next.js + Supabase apps and live Supabase databases. No API key.
NOASSERTION -
Hosted MCP server and A2A agent that audits landlord CAM reconciliations against the commercial lease. No API key.
NOASSERTION -
Free read-only MCP server: audit API-key privileges, check idempotency patterns, explain AI-agent guard patterns.
MIT -
Model Context Protocol server for SignalSumo — lets Claude and other LLMs read SEO data, run audits, and check rankings via the SignalSumo API.
npm MIT -
MCP server for WordPress and WooCommerce. Lets AI assistants and agents read and manage posts, products and orders through the REST APIs. Read-only by default, drafts instead of publishing, trash instead of delete, with an audit log for every write.
MIT -
MCP server that lets AI agents safely read and edit EPLAN Electric P8 / Pro Panel projects through the EPLAN .NET API, with approval for real-project writes and an audit trail. 让 AI 代理通过 MCP 安全地操作 EPLAN:查询、绘图、报表、导出,真实项目写入逐次审批。
MIT ★ 6 -
BurlyMCPgithub.com/Wolfeitz/BurlyMCPupdated this year
Production-ready MCP server with HTTP API that gives AI agents secure, audited access to Docker, file systems, and notifications. Zero-config container startup, graceful degradation, and enterprise-grade security controls.
MIT ★ 1 -
A modular suite of MCP (Model Context Protocol) servers for Audiokinetic Wwise, enabling AI agents to browse, edit, audition, profile, and build Wwise projects through the Wwise Authoring API (WAAPI).
Apache-2.0 ★ 5 -
The memory layer that can be corrected: provenance-first agent memory with a real corrections API and a one-command junk audit.
MIT ★ 1 -
Prove a money move and audit the source: dated decisions, public calibration, and every future miss. Free, no API key.
npm MIT