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.
-
Verified CPU-only Vendi Score MCP tools: unchanged research functions, real stdio calls and reproducible scientific evidence.
MIT -
MCP server for the ModelRefs Evidence API: governed benchmark evidence, model retirement dates and comparisons that refuse to compare incomparable scores.
npm MIT -
Marketplace-evidence trust scores for AI agents — a 0-100 Evidence Score with observed/missing signals for Amazon, Walmart, Target, and Best Buy listings. Public streamable HTTP endpoint at https://mcp.gobuy.ai/mcp, no API key.
npm MIT -
infraweaver-mcpgithub.com/infraweaver-io/infraweaver-mcpupdated this year
Model Context Protocol server for Infraweaver Cloud — read a repo's Terraform findings, health score, compliance evidence and crosswalk from Claude Code, Cursor or Windsurf.
npm AGPL-3.0-or-later -
Helixgithub.com/Al1Abdullah/Helixupdated this year
Clinical evidence synthesis engine. Scored, explainable access to ClinicalTrials.gov, PubMed, and openFDA in a single API call. REST + MCP server. No API key required.
pypi MIT ★ 1 -
Find vegan-friendly restaurants and menus: dietary dish evidence, scores and places near you.
npm MIT -
Discover, enrich, and rank GitHub repos for an objective with weighted, evidence-based scoring.
npm -
Tauri 2 desktop intelligence platform — Cesium.js 3D globe, 185 live panels, MCP server for Claude Code, and an explainable algorithm intelligence layer (truth scoring, evidence graph, compound risk, forecast calibration) plus shortage / weather / insights engines. 600+ deterministic tests.
NOASSERTION ★ 12 -
Curates kidney-disease genes and their evidence from 17 sources into an evidence score, with a web app, REST API and read-only MCP server; research use only
MIT -
MCP server that estimates a home's ARV from scored, gated sold comps and returns the evidence behind the number.
pypi MIT ★ 2 -
Wasl-AI-github.com/krish2105/Wasl-AI-updated this year
Scores whether a business is legible to AI agents on a 100-point index, then generates the MCP server that makes it legible. Deterministic scoring, cited evidence, published refusals.
MIT -
Local-first completion-evidence system for AI-built apps: read-only audit, verifier-executed challenges, evidence-based 0-100 score, guided fixes, learning plan, CLI, and MCP.
npm Apache-2.0 ★ 7 -
@cjsqbn/resume-screening-mcpactive
Evidence-verified deterministic resume screening, hard-gate evaluation, timeline calculation, scoring, ranking and audit MCP server.
npm MIT -
mcp-security-advisorygithub.com/zavora-ai/mcp-security-advisoryupdated this year
Security Advisory MCP Server — search advisories (CVE/GHSA/OSV/RustSec), map to dependencies, score risk, generate patch plans, export evidence
cargo Apache-2.0 -
stargraphgithub.com/arkaigrowth/stargraphupdated this year
Turn your GitHub stars into a searchable, evidence-backed analytics layer. CLI + MCP, deterministic scoring you can read in one file.
MIT -
Personal job search agent: rule-based filtering, Claude fit scoring, and evidence-grounded application draft tailoring via a local MCP server
-
MCP stdio server that keeps bug-hunting agents inside an authorized scope: scope verdicts, evidence redaction, CVSS v3.1 scoring and a findings ledger.
MIT -
repo-doctorgithub.com/Infojitsu/repo-doctorupdated this year
LLM agent with a hand-written tool loop and a custom MCP server that produces scored, evidence-cited audits of GitHub repos.
MIT -
Three-way invoice reconciliation in integer cents, exception scoring, evidence-grounded LLM routing, REST APIs, an MCP server and a Docker dashboard.
MIT -
quorumgithub.com/marklynd/quorumupdated this year
A council of language models that scores a claim against a rubric, using only evidence you supply. Bounded timeouts, anonymised deliberation, hash-verified transcripts, MCP server.
MIT -
Factual resume and cover-letter tailoring for Grok Bot. Public setup, fictional examples, release notes and optional evidence-linked MCP job-fit scoring.
-
cynical-sallygithub.com/w1ckedxt/cynical-sallyupdated this year
Brutally honest senior-engineer code reviews for Claude Code, Cursor & Windsurf - and your terminal. Scores, evidence-backed issues, usable fixes.
npm MIT ★ 102 -
evidencechaingithub.com/tejasprasad2008-afk/evidencechainupdated this year
Autonomous forensic investigation agent with self-correction for SANS SIFT Workstation. 21 typed MCP tools, 7 contradiction detectors, evidence-weighted confidence scoring. Built for SANS Find Evil! Hackathon.
MIT -
Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination. MCP server, REST API, Python SDK.
npm Apache-2.0 ★ 20 -
Incident-Investigatorgithub.com/stackrail-io/Incident-Investigatorupdated this year
Stateful MCP server for incident investigation: dynamic evidence planning, competing hypotheses, confidence scoring, timelines, blast radius, and postmortems. Works with Cursor, Claude Code, Codex, and any MCP client.
MIT ★ 1 -
bullet-mcpgithub.com/nikkoxgonzales/bullet-mcpupdated this year
MCP server for evidence-based bullet point validation. Scores lists against cognitive research (Miller's Law, serial position effects) with actionable feedback.
MIT ★ 1 -
MCP server that scores your resume against a job posting, tailors it from your own evidence, and renders an ATS-ready PDF. Built on LangGraph. Never fabricates.
MIT -
MCP server wrapping RSPCA Assured farmed trout (2025.07) and salmon (2024.05) welfare standards. Gap analysis, compliance scoring, audit-ready evidence pack generation, signed welfare attestations. From MEOK AI Labs.
pypi MIT License -
Forest carbon credits that prove themselves: satellite AI scores, zkML proofs verified on-chain (Base Sepolia), ML-DSA-65 signed evidence, living credits, MCP server for agents.
MIT -
🔌 Exposes AI risk assessment over MCP — NIST AI RMF-aligned risk register with scoring, treatments, controls, and signed evidence trail.
pypi MIT -
icp-scoutgithub.com/GrimmReaper0/icp-scoutupdated this year
Evidence-first company discovery from the public web. Search, crawl, score & export qualified companies with source URLs behind every fact. CLI + dashboard + MCP server. Zero dependencies.
MIT ★ 1 -
Multi-agent freelancer copilot: LangGraph agents find jobs, score fit, and draft evidence-grounded proposals with claim verification. Human-in-the-loop approval, MCP servers, RAG ablations, FastAPI + Next.js.
-
jobsearch-dashboard-aigithub.com/carlwelchdesign/jobsearch-dashboard-aiupdated this year
Local-first AI job search dashboard that discovers and scores roles, manages candidate evidence, generates truthful application materials, tracks outcomes, and supports controlled application workflows with human approval gates.
AGPL-3.0 ★ 3 -
Evidence-first LinkedIn research workspace for Agent Reach and Codex—find ICP prospects, scan sourced trends, score fit and timing, and draft outreach and content.
★ 2 -
ephor-gateupdated this year
Ephor gate — the identity & policy layer for AI agents. Standard MCP gateway (stdio + HTTP): every agent action risk-scored, policy-checked, human-approved when it matters, and recorded in a tamper-evident audit chain. https://ephor.dev
npm SEE LICENSE AT https://ephor.dev -
MCP server for MaveDB: quantitative variant-effect scores from Multiplexed Assays of Variant Effect (MAVE) and deep mutational scanning — functional evidence as typed tools for LLM agents.
MIT -
Public Tender Intelligence Agent — unifies UK + EU procurement notices (Find a Tender, Contracts Finder, TED) into one governed dataset and serves it to AI agents via MCP, with evidence-scored evals
MIT -
ai-transformation-90github.com/benmfzen/ai-transformation-90updated this year
A transformation copilot for the first 90 days of an AI program — playbook, opportunity portfolio, costed business cases, operating model, plus the software to run it: MCP assistant with evidence-gated scoring, prototypes with eval gates, weekly autopilot (fictional cases)
-
Local-first SEC 8-K research lab: score filings point-in-time with Jev, OpenAI or local LLMs, and label which results can count as evidence. Never places orders.
MIT -
@veriify/mcpupdated this year
Veriify MCP server — scan any website or your localhost dev server for security, accessibility, performance, and dark patterns from inside Claude Code, Cursor, Windsurf, and other AI dev tools. One Product Health Score with evidence for every finding.
npm UNLICENSED -
ai-test-failure-analyzergithub.com/aks-builds/ai-test-failure-analyzerupdated this year
8-phase evidence pipeline for Playwright, pytest, Jest, Cypress, Newman, k6, and JUnit failures. Scans git history, application logs, and config to produce confidence-scored root-cause hypotheses. Exposes as MCP server, CLI, and streaming web UI.
pypi ★ 1 -
MCP server for Lookalike Company Finder. Find companies similar to your best customers or a competitor, ranked by a 0 to 100 similarity score with the evidence behind it. Runs on Apify. Clay-ready output.
npm MIT -
ultraspeed-cliactive
One-click website speed test in your terminal or AI tool: score, named causes with evidence, and an apply-able fix plan. Includes the Ultraspeed MCP server (report, plan, apply, remeasure) for Claude Code, Cursor, Codex, and Gemini CLI.
npm MIT -
MCP server for Manufacturer and Supplier Finder. Find manufacturers, wholesalers, and distributors for any product in 20 countries, each checked on its own website, with quoted evidence, domain, and a confidence score. Runs on Apify. Clay-ready output.
npm MIT -
Management OS inside Claude, Claude Code, Gemini CLI, Grok and other MCP clients. Share a CRM record, call notes and emails; get the forecast call, risks and next moves, every scored point quoted from your evidence.
MIT ★ 1 -
Explain-it-back as an MCP connector: it grounds a check in your own sources, scores it with verified evidence (not model vibes), and resurfaces what you don't yet know. Local-first, opt-in, no telemetry.
MIT -
Passive OSINT radar that scores investment websites for Ponzi and pyramid scheme risk. Python DAG pipeline + MCP server for Claude: RDAP, DNS, certificate transparency, Wayback, company and regulator lookups, evidence-checked answers and a chain-of-custody risk dossier. EN / PT-BR.
-
Persistent organisational intelligence for AI agents. Turn codebases, documents, policies and decisions into a knowledge graph so Claude Code, Cursor and Copilot reason over architecture, dependencies and prior lessons — with confidence scores and evidence. 13 LLM backends + custom, fully offline capable.
pypi Apache-2.0 -
Financial crime screening MCP server that connects your AI agent or compliance workflow to 13 live data sources for AML/CFT due diligence. Give it an entity name and it returns a structured AML Risk Tier — LOW, MEDIUM, HIGH, or PROHIBITED — with dimensional scores, SAR filing recommendations, and supporting evidence.
MIT -
Claude Code plugin for site audits you can re-run and trust: scripted SEO, Core Web Vitals, links, signs of a hacked site, images and video, with evidence for every finding, repeatable scores, a client-ready report and fixes verified by a second audit.
MIT -
Pathmodeno update data
Deterministic preflight for the intent you hand a coding agent. check_intent_readiness scores a spec against six calibrated gates - title, objective, outcomes, constraints, edge cases, verification - and names the exact blockers. No model call, no account. Specs live in intent.md in your repo as plain markdown you own. Add a Pathmode API key to sync intent and evidence across a team and check pull requests against the outcomes you agreed to.
smithery -
agentsgategithub.com/agentsgate/agentsgateupdated this year
Undo for AI agents: an MCP proxy that checkpoints every tool call before it runs, so a bad `DROP TABLE` or `rm -rf` rolls back in seconds. Risk scoring, human-in-the-loop approval, tamper-evident audit log, dashboard, and MCP servers for PostgreSQL/MySQL/SQLite. Local-first, MIT, TypeScript, Node 20+.
npm MIT -
whichlibgithub.com/josifb/whichlibno update data
Ask your agent which library to use and get evidence back. whichlib returns GitHub repositories for a need in plain words, ranked by a transparent 0-100 score (momentum 40%, maintenance 25%, adoption incl. npm/PyPI weekly downloads 25%, license 10%) with a tier and a one-line verdict like "Gaining steadily, 145M downloads/wk, pushed 3 days ago, MIT". Tools: recommend_repos (best repos for a need), compare_repos (2-10 repos side by side), trending_repos (most-starred new repos by day/week/month). Local, Node 22+, MIT, no account. Optional GitHub token raises GitHub's rate limit.
smithery -
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 -
MCP server for research workflows — findings, scoring, ADRs
MIT ★ 1 -
Enhanced Subject Researcher MCP - Iterative target-driven research with multi-vertical search, quality metrics, and sophisticated claim mining
pypi MIT -
Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns, and memory, so they use fewer tokens, spend less time, and produce better, more familiar output.
npm NOASSERTION ★ 68 -
brain-in-the-fishgithub.com/fabio-rovai/brain-in-the-fishupdated this year
Score any document. Prove every claim.
MIT ★ 101