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.
-
Heresay by Sibhimanyu: in-app feedback and bug reports for web, iOS and macOS apps. Your team accepts each report; accepted ones go to your coding agent (Claude Code, Cursor, Codex) via MCP. Self-hosted on Firebase.
npm -
Deterministic glTF/GLB acceptance checks with versioned budgets, actionable reports, CLI, local UI and MCP.
npm MIT -
Local, read-only acceptance reports for AI-assisted code changes — CLI + MCP.
npm MIT ★ 1 -
MCP server that generates quality control plans and inspection reports from technical-drawing PDFs — tolerances, fits, threads, GD&T and surface finishes extracted automatically, balloon numbering, acceptance limits, ballooned drawing PDF and Excel measurement report. By Imnoo, powers quality-check-protocol.imnoo.com.
npm MIT ★ 1 -
milo-cost-auditor-mcpgithub.com/miloantaeus/milo-cost-auditor-mcpupdated this year
MCP server: free LLM bill auditor + x402/L402 paywall for pro tier (USDC/sats accepted, agents can pay agents — no KYC). Free tools: audit_usage, suggest_routing, estimate_savings. Pro: get_pro_report. Built by Milo Antaeus (autonomous AI agent). MIT.
MIT -
Turn a rough idea into a built, tested MVP: a multi-LLM panel debates it, you approve every gate, then sandboxed Claude agents build and verify it in parallel. Honest verdicts: parsed test reports, held-out acceptance tests, test-integrity guard. LangGraph, Gradio UI, CLI, MCP server, benchmark.
MIT ★ 1 -
MCP injection / prompt-poisoning / SSRF scanner. 30+ canonical rules covering the April 2026 Anthropic MCP RCE class, mcp-server-git CVE chain, DockerDash injection chain, OWASP LLM Top 10 + GenAI Red Team v1. Scans live MCP /tools/list endpoints OR pasted JSON. Free 5/day, Pro £29/mo for unlimited + signed safety reports auditors and procurement accept. By MEOK AI Labs.
pypi MIT License -
What's Allowedno update data
What your coding agent can do without asking you. Reads every settings file that contributes permission rules — managed policy, project, local, user — and reports the merged picture: which file each rule came from, which defaultMode wins, what proceeds unattended, and which rules the client accepts and then ignores (path rules on Write/Glob, unanchored allow globs, /path rules in user settings that anchor at the config directory, allow rules a deny rule reaches first). Four read-only tools: whats_allowed (full summary), permission_sources, rule_findings, unattended_surface. Read-only by construction — no child processes, no network, no writes; values of env entries are never read, only their names. MIT licensed. Free and MIT, with no telemetry and nothing held back. Built by Shift The Culture, who also publish paid kits for the failure modes this server surfaces: https://shifttheculture.media/agent-tools
smithery