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.
-
Cybercentry MCP server: pay-per-call security verification for AI agents. Remote endpoint, no install.
MIT ★ 2 -
proofstream-mcpupdated this year
MCP server for ProofStream — real-time human verification API for AI agents
npm MIT -
MCP server for payment verification across IFTHENPAY and Klarna — check payment status, list transactions, and validate webhooks from any MCP-compatible AI agent
-
MCP server for Cascrow — trust infrastructure for the agent economy: AI verification, on-chain reputation, and non-custodial milestone escrow (MilestoneEscrowV3, native XRP; testnet for now)
npm MIT -
mcpgithub.com/5sim-net/mcpactive
Official 5sim MCP server: AI agents buy virtual numbers for SMS verification and receive SMS online. From $0.008, 150+ countries, 1,200+ services.
npm MIT -
MCP server for Verigent — AI agent verification tools
npm Apache-2.0 -
@projectjade/mcp-servergithub.com/jadegate/jade-coreupdated this year
JadeGate MCP Server — Deterministic security verification for AI agent skills
npm Apache-2.0 -
Free MCP server: score any AI agent output 0-100 and get a PASS/PARTIAL/FAIL verdict (VOP verification). Verification only, no money moves.
MIT -
Independent verification for AI coding agents. Real commands. Human-owned acceptance. Hash-manifested evidence.
NOASSERTION -
verifikator-mcpgithub.com/Nesoxy1/verifikator-mcpupdated this year
A deterministic verification gate for AI agent harnesses MCP server, zero dependencies.
MIT -
@proofslip/mcp-servergithub.com/johnny-z13/proofslipupdated this year
MCP server for ProofSlip — receipt-based verification for AI agent workflows
npm MIT -
Independent arithmetic verification for AI agents — hosted MCP server (io.github.zenoix888/agent-verifier)
-
@mailagent/mcpgithub.com/alex0nder/mailagentupdated this year
MailAgent MCP server (stdio) for Cursor and AI agents — email verification inboxes
npm MIT -
@trustthenverify/mcpgithub.com/schmoll86/trustthenverifyupdated this year
MCP server for TrustThenVerify — gives AI agents native escrow + verification tools (v2)
npm MIT -
@trustthenverify/trust-mcpgithub.com/schmoll86/trust-mcpupdated this year
MCP Server for AI agent trust verification — lookup, verify (9 chains), search, evidence, reviews.
npm MIT -
@webbula/mcpgithub.com/webbula/webbula-mcpupdated this year
Webbula MCP Server — email verification, hygiene, and data-quality trust layer for AI agents
npm MIT -
@wefi-ai/ekyc-suite-mcpgithub.com/wefi-ai/ekyc-suite-mcpupdated this year
KYC MCP server, eKYC MCP server, KYC onboarding MCP, remote KYC onboarding MCP, and identity verification MCP for AI agents: face comparison, selfie verification, face liveness, deepfake screening, document OCR, ID card OCR, Chinese ID card OCR, bank card
npm MIT -
Zuvo MCP Server — email verification, hygiene, and data-quality trust layer for AI agents
npm MIT -
codeloopgithub.com/orienjoji/codeloop-internalupdated this year
CLI tool for CodeLoop — automated verification for AI coding agents
npm MIT -
Evidence-based compatibility registry and verification layer for AI coding agents via MCP.
MIT -
shipcheck-mcpupdated this year
MCP verification server for AI coding agents — proves a feature works across UI, API, and database. Run with: uvx shipcheck-mcp
pypi MIT -
Email verification for Node.js and AI agents with local syntax checks, MillionVerifier, ZeroBounce, CLI, and MCP tools.
npm MIT -
Trulioo identity verification for AI agents - Claude Code plugin (KYC, KYB, AML, DocV, age assurance, business monitoring) over MCP.
Apache-2.0 -
policycheck-extensiongithub.com/vibegpt/policycheck-extensionupdated this year
Chrome extension that injects check_seller_policy WebMCP tool into e-commerce sites for AI agent trust verification
-
claims-ledgergithub.com/isatimur/claims-ledgerupdated this year
Source-anchored claims ledgers for codebases and AI agents — CI-gated evidence verification. No anchor, no claim.
★ 1 -
AI work receipts and deterministic verification for agents, with MCP, evidence, claims, approvals, and SHA-256 integrity.
MIT -
MCP server for Clearsigned: calibrated claim verification for AI agents, paid per call over x402, receipts verified offline.
pypi MIT -
agent-inboxgithub.com/gsd-build/agent-inboxupdated this year
Give any AI agent a disposable email inbox in one tool call. MCP server for email verification, auth flows, and testing.
npm MIT ★ 64 -
Swarm Verify: independent verification for software changes from AI coding agents or humans. Runs a project's real checks, separates what passed from what was established, names what stayed unmeasured, and records evidence anyone can check. CLI, GitHub Action, Claude Code hook, MCP server, pre-commit hook.
ISC ★ 2 -
Email verification for AI agents: send, hold or kill with the reason. CLI, MCP server and hosted API.
npm MIT ★ 2 -
cortexgithub.com/supernavyl/cortexupdated this year
Rust pre-apply verification gate for AI coding agents — sandbox-checks edits before they touch disk. MCP server + daemon + CLI.
MIT -
PRAMAN (प्रमाण) — evidence-driven verification toolkit for AI coding agents. Authored browser/command checks, strict proof gates, CLI + stdio MCP.
MIT -
MCP server for the VerifNer identity verification API: verification links, document checks, verdicts and webhooks from any AI agent
npm MIT -
codeloop-mcp-servergithub.com/orienjoji/codeloop-internalupdated this year
CodeLoop MCP server - verification, self-repair, and recommendation layer for AI coding agents
npm MIT -
MCP server for payfirewall: lets any AI agent verify a payee before paying (verify_payment, get_verification, block_payment).
npm MIT -
trustoraclegithub.com/ToolOracle/trustoracleupdated this year
FeedOracle Trust Layer — Verifiable evidence & verification MCP server for AI agents. 10 tools: claim verification, ES256K-signed facts, provenance tracing, freshness guard, hallucination detection, confidence gates, on-chain evidence anchoring. Standardized verdict schema with proceed/caution/abstain/escalate actions.
NOASSERTION -
Verification gate for AI coding agents: blocks the agent from finishing while its changes introduce typecheck, lint or test failures. Repo map, context, impact and probes over MCP.
MIT -
icme-preflight-mcpgithub.com/icme-lab/icme-preflight-mcpupdated this year
MCP server for ICME Preflight — cryptographic guardrails for AI agents. Formal verification + ZK proofs, pay per request via x402 or card.
npm MIT -
agentoracle-mcpgithub.com/tkcollective/agentoracle-mcpupdated this year
MCP server for AgentOracle — claim verification for AI agents. Verify before you act. x402-native on Base, SKALE, Stellar.
npm MIT -
steplockgithub.com/l0kifs/steplock-ai-skill-executorupdated this year
An MCP server gatekeeper runtime that enforces step-by-step AI skill execution with output verification, ensuring stable and reliable agent workflows regardless of LLM compliance.
pypi MIT License Copyright (c) 2026 Sergei Konovalov -
aip-mcp-servergithub.com/The-Nexus-Guard/aip-mcp-serverupdated this year
MCP server for AI agent identity verification via AIP — verify agents, check trust, sign content, exchange encrypted messages
MIT ★ 1 -
Verify AI-generated code with execution evidence — deterministic, local-first verification for coding-agent changes via a macOS app, CLI, and MCP server.
MIT ★ 1 -
sentinel-verifyupdated this year
A fully local, open-source verification layer for AI coding agents. Plugs into any MCP-compatible agent and lets it self-check its work before a human sees it.
npm MIT -
agent-guardgithub.com/sneiko/agent-guardupdated this year
Contract-based accountability runtime for AI agents. Define tasks with required evidence — no proof means not done. MCP server with multi-agent pipelines, independent verification, and append-only audit log.
MIT -
The live, agent-readable frontier of AI mathematics: open problems, AI attempts, solution claims, verification, replay candidates, Skill and MCP.
MIT ★ 4 -
mailfloss MCP server: email verification for AI agents. Cursor plugin, agent skill and MCP Registry entry for https://api.mailfloss.com/mcp
MIT -
Live browser-state verification for AI coding agents. One MCP call, milliseconds, truth. Free to use. Built by GOL Productions. By GOL Productions.
npm SEE LICENSE IN LICENSE -
unblockapi-mcpgithub.com/unblockapi/unblockapiupdated this year
MCP server for UnblockAPI — captcha solving, browser rendering, temp email, SMS verification, screenshots, and web search for AI agents
pypi MIT -
Sendly MCP Server — Full SMS platform for AI agents. Messaging, contacts, campaigns, templates, webhooks, OTP verification, voice calls, and more.
npm MIT -
Runtime artifact existence & freshness verification for AI agent completion claims. A lightweight, zero-LLM MCP gate that source-binds 'done' claims to real files. MIT.
npm MIT ★ 6 -
Agent Trust Layer — rule-based discriminator engine for AI agent output verification. 47 dimensions, 9 check layers, 131 MCP tools. Zero LLM dependency. Checks what AI says before it reaches humans and says "no" when something is wrong.
npm MIT -
Deployment truth verification for AI agents. Resolves where a domain actually serves from, verifies the live content matches the build, and catches stale caches and misrouted deploys.
npm MIT -
The deterministic trust layer for autonomous AI coding agents. Compiler-grounded verification of what an agent actually did vs. what it claimed, blast radius mapping, and persistent contract memory.
npm MIT -
Model Context Protocol (MCP) server connecting AI agents to remote Linux EDA clusters for digital IC design, SystemVerilog/UVM, and formal verification.
MIT ★ 1 -
-Omni-Pathgithub.com/Han-TechAIz/-Omni-Pathupdated this year
The local CLI that forces AI agents to prove their file edits against your actual filesystem. Zero slop, full verification - Strict Write Discipline, multi-provider routing, MCP, and receipts.
MIT -
MCP security server for AI agents — runtime verification and receipt verification for Claude Code, Cursor, Cline and Windsurf. 7-dimension CCS checks, Ed25519 tamper-evident receipts, offline verification, zero runtime dependencies.
npm Elastic-2.0 -
x402 pay-per-call tools for AI agents (USDC on Base): $0.001 OpenAI-compatible chat, web page reader, email verification, prompt-injection screen, crypto & market data. MCP server + agent skills.
npm -
Web navigation and verification for AI agents: a compact semantic page digest, a typed diff after each action, and assertions over that diff. MCP server and CLI on Playwright and SnapDOM.
npm MIT -
tardygradagithub.com/fabio-rovai/tardygradaupdated this year
A verified runtime for trustworthy AI agents: every claim passes an 8-layer verification pipeline before it counts. Deterministic checks, explainable verdicts, no LLM judging an LLM. Pure C, zero dependencies, MCP-native.
MIT ★ 26 -
traceon-cligithub.com/dhanushmurugesang/traceonupdated this year
Runtime verification for AI coding agents. MCP server that lets Claude Code verify code changes work end-to-end via Playwright + OpenTelemetry. Embedded OTel collector by default — no Docker, no SigNoz required.
npm MIT