- Conduid
- Marketplace
- #verification
MCP servers tagged verification
154 live MCP servers tagged "verification", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with verification.
Verahelm Decision Envelope
Offline verifier and GitHub Action for signed, revision-bound change gates; the private decision engine is not published.
Oh No My Claudecode
The coding harness that measures itself. Wraps Claude Code / Codex / OpenCode, blocks false "done" with an independent verifier, mediates side effects, writes tamper-evident recei…
Claude Workflow Kit
Evidence-first Claude Code workflow as a plugin: verification standards with claim-class proofs, a 7-phase methodology with adversarial spec review, subagent model-tier enforcemen…
AgentVerify
AgentVerify is an open source outcome verification for action-taking AI agents. It checks that high-risk actions reached the required final state in your systems of record and pre…
Edgeverdict
A code review gate that verifies changes by executing tests, not by judging diffs. LLM proposes; a deterministic gate decides.
Prfrail
Provable rails for unattended AI engineering — every code change, gate, evidence and rollback is auditable. / ProofRail 为 AI 无人值守编程铺设可证明的轨道——代码变更、门禁、证据、回滚，全程可审计。
Factgate
The deterministic verification gate for AI research agents — fake CVEs 404, quotes must be on the page, a verified=yes it can't confirm is a FAIL.
Locale
Agent policy layer for safe tool use across MCP, A2A, and orchestrated agents.
Acceptora Php
Framework-independent PHP client for the Acceptora verification API and MCP server.
Parallax Claudecode
Evidence-first protocol gates, verification, traces, Hyperplan, and durable Horizon orchestration for Claude Code.
ConstantX
MCP workflow for turning engineering plans into evidence-backed, spec-driven, verifiable implementations.
Trustos MCP Server
Official MCP Server for AI decision verification with Trust OS.
nhantour/inferenceview-mcp
check claims before an AI agent acts. Wallet keys remain local; paid calls settle in USDC on Base.
Purr Verify MCP
Self-hosted MCP verification and VPS operator runtime for AI agents, with durable jobs, isolated builds, browser QA, deployment, and redacted evidence.
Casper Ledger MCP
👻 Your Casper verdict ledger as a queryable MCP resource. Ask any model: 'have we overridden this gate before, and did it bite us?' Dependency-free, local-only.
Assay Protocol
MCP boundary spec and notary layer for verifiable Assay evidence.
Agent Trust Suite
Trust infrastructure for multi-agent systems. Define contracts. Observe behavior. Verify traces.
VouqisVerify
Vouqis Verify (VouqisVerify) generates AI Change Evidence Packs from merged GitHub pull requests, with AI change classifications, CI checks, and reviewer evidence exported to Exce…
CortexIQ AI
CortexIQ AI is an open platform that make AI more useful, reliable, transparent, and controllable.
Ontario Protocol MCP Listing
Public MCP/x402 listing packet plus inbound readiness check for Ontario Protocol.
Epistemics MCP
MCP server that verifies capability/version/freshness claims before AI agents ship them. Institutionalizes 'zero-hop verify' as callable tools.
Proofjson
ProofJSON MCP server for AI agents. Local stdio tools to assess invoices before payment using supplied data and configured policy. Returns allow, review or block with scope, reaso…
Doneproof MCP
Evidence-bound completion proofs for software changes through MCP
Verified Unreal MCP
A verification layer for AI agents driving Unreal Engine 5.8: Claude has to PROVE a change works with evidence (fresh-process reads, validated screenshots, 3-source verdicts) inst…
Heor Studio
Turn a study protocol into machine-verified SAS + SQL for claims-data (MarketScan) studies: 2,563 executed checks across 24 groups, mutation-tested, honest refusals
Xerify
Verify before you trust. Cross-provider verification with LLMs and Jev. CLI, library & MCP.
NilCore
The tiny, trustworthy coding agent leverages sandboxed execution, verifier-owned completion, human gates, and a replayable audit trail.
Godot Verify Plugin
Validation-driven AI development harness for Godot 4.x (Claude Code plugin): headless SceneTree matrix oracle + live MCP game channel.
MeatLoop
MeatLoop exists to offer AI agents a way to consult a human on simple questions, such as about an image or comparison between two images, via email.
Manual CLI
Self-verifying repository operating manual: every claim about a repo is backed by an executable check, stamped fresh/stale/broken/blocked, and compiled into token-budgeted briefs…
Aeon Skill Pack Claim Audit
Aeon community skill pack: verify whether what your unattended instance reported is actually true, not just whether the run succeeded.
Vet402
vet402 — independent verification of the x402 agent-payment economy: it buys what endpoints actually sell, verifies fulfillment against the seller's own declaration, and publishes…
Pdverify
Render Pure Data patches headless and verify what they actually sound like — the audio-verification piece missing from Pd LLM harnesses.
Dcl SDK
TypeScript SDK for the DCL Trust Oracle protocol — verify agent audit chains client-side, no server round-trip required
Bindagt
AGT-9303 — the agent identity standard. Verify that an AI agent belongs to the domain it claims.
Aip MCP Server
MCP server for AI agent identity verification via AIP — verify agents, check trust, sign content, exchange encrypted messages
GlassPane
GUI testing and verification for AI coding agents on macOS: 14 MCP tools let an agent drive a Mac app, assert what actually changed, and produce replayable evidence instead of scr…
Checkedflow
Evidence-preserving multi-agent runtime for signed tasks, shared budgets, independent verification and conditional code reuse. A2A, MCP, CometBFT and gVisor.
Insumer Examples
Code examples and multi-attestation spec for InsumerAPI: wallet auth across 37 chains, x402 pay-per-call (no key needed), ERC-8004/ERC-7710 agent verification, composable trust ac…
Svr Verify
Signed Verification Receipts for deterministic AI verification: CPU-only, Ed25519-signed, reproducible, independently verifiable.
Verifikator MCP
A deterministic verification gate for AI agent harnesses MCP server, zero dependencies.
Sshi MCP System
Helps autonomous AI coding agents build projects more reliably — audited phases, real sandboxed tests, anti-mockup validators, MCP-native, tool-agnostic. AGPL-3.0 + commercial dua…
Flect
Independent intent verification for AI-written patches.
Hashkit
Agentic-first hash computation and verification service. Compute MD5, SHA1, SHA256, SHA512 hashes, verify data integrity, and generate HMAC signatures. Plain text API, agent-drive…
Calma
Re-run the work, recompute the number, block the wrong one before it ships — a deterministic guardrail for AI-computed results. CLI · Claude Code hook · MCP.
Jep MCP Wrapper
JEP accountability wrapper for MCP tool execution and delegation replay.
Groundlens Dev
Guardrails for LLM answers. GroundLens checks an LLM answer against its sources without a model, decides PASS, REVIEW or FAIL under your policy, and keeps a signed record.
Factstamp Skill
Agent skill + remote MCP server: cited, dated, Ed25519-signed answers for checkable claims (figures, entities, citations, packages, documents). Paid per call via x402 on Base.
Seaworthy
Seaworthy verifies websites for agents: one command checks any built static site and returns a versioned report with locations and fix hints. CLI, MCP, Agent Skills, GitHub Action.
Claude Code Fact Verification Hook
Claude Code hooks to fix stale factual answers in Opus 4.7 and force verification before unsupported assertions