- 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.
Veratum
"Veratum - The production AI coding harness & skill for Antigravity, Claude Code, Cursor, and Windsurf. Prevents AI hallucinations, scope creep, and untested code."
Vaerion
Open-source verification layer for AI agents — signed receipts, fail-closed policies, deterministic proof. Local-first, zero telemetry.
Sourced
Sourced — the corroboration primitive. Confirmed by sources, never 'true'. Cryptographic provenance & trust engine.
Touchstone
A deterministic first-pass filter for unsupported claims in LLM output, computed without calling another LLM. Not a standalone hallucination detector. A spec plus reference implem…
Tribunal
Governed verification and synthesis for Massive Intelligence (IM) outputs: configurable Thinker, Worker, and Verifier panels, model-as-judge, and Ed25519-signed, SHA-256-chained t…
Agent Skills Resources
Source-backed companion guide for agent skills, AI agent workflows, framework resources, evaluation templates, and rollout playbooks.
Awesome Horizon Shield
Every database, MCP server and verification ledger operated by The HORIZONs K.K. — each row with its DOI, official registry entry and daily conduct measurements. Nothing here asks…
Cursor AI Agent Tooling Projects
Local-first TypeScript tooling for AI coding agents: MCP governance, multi-agent control room, and verification-as-a-tool.
Dlx Public Kit
# DLX Public Kit DLX Phase 1 is a public evaluator kit for a thin MCP-native trust proxy. The public face is intentionally narrow: evaluators call `extract`, then `get_execution`…
Dlx Kernel
Legacy/public companion repo for DLX kernel context. The current public Phase 1 evaluation entry is dlx-public-kit, centered on a thin MCP-native trust proxy.
Veyra Commit Core
Landing page and public docs for Veyra, the commit mode layer for production AI agent actions.
Nestor
Has a human checked this? Seal/serve/audit over verified-match memory — ledger, MCP, and CLI.
Awesome Verified Agents
Tools that produce evidence about what an AI agent actually did — gates, attestation, output verification, benchmarks. Inclusion bar: name the artifact a human can inspect later.
Codevetter
Verify AI-generated code with execution evidence — deterministic, local-first verification for coding-agent changes via a macOS app, CLI, and MCP server.
Diffgate
Verify declared code edits against tree-sitter structural differences and expose deterministic verdicts through CLI or MCP.
Opensource Everything
Study an existing product, turn it into build-ready artifacts, and verify your clone against the reference.
Patchwork Harness
The verifying harness for AI coding agents: test gates, independent cross-vendor review and grounded answers, with every action on the Patchwork audit trail.
Prancheta
Draw complex figures as verified vector output - a render/inspect/repair loop over TypeScript, with a Python module protocol for figure classes that need real domain libraries.
Server
🗄 Archived 2026-07-14 — superseded by teta-pi/mcp, the real deployed MCP server
Evidence Map
MCP-first review and evidence-mapping harness for AI-generated and human-drafted deliverables.
AI Driven Development
A quality methodology for AI-assisted software development. Six layers, adopted incrementally.
AgentForge
Open-source infrastructure for trusted AI agents — identity, permissions, execution, evidence, verification and agent-to-agent networking.
Svalinn
Experimental gateway for verified-container operations. The only runnable gateway is a legacy Deno/TypeScript MVP; its AffineScript migration artifacts are incomplete and not prod…
MCP
MCP server exposing the TETA+PI verified entity registry to AI agents — 7 tools: search, resolve intent, verify entity/endpoint/claim, get profile, get proof.
MCP
DidWork for Cursor — independently verify that the outcomes your software claims are actually true
ScopeBlind/verify-mcp
2.0.
Agentoracle MCP
MCP server for AgentOracle — claim verification for AI agents. Verify before you act. x402-native on Base, SKALE, Stellar.
Donnyclaude
Verified workflow engine for Claude Code: durable project memory, phase planning, subagents, and deterministic completion gates.
Nikolife2016/pulsefeed-x402
mcp`
Agent Proof MCP
Cryptographic proof of agent work via MCP. Receipts, verification.
Conduct Register
Not a curated list. A machine generated register of MCP servers with nightly verdicts, recomputable SHA-256 records, and Bitcoin anchored history. Nobody chooses the rows, and no…
Open Mind MCP Server
MCP server that exposes Open Mind's verification-first codebase context to AI agents — glossary, architecture, flows, and claim validation, with file:line evidence for every answe…
Claims Ledger
Source-anchored claims ledgers for codebases and AI agents — CI-gated evidence verification. No anchor, no claim.
Rework
MCP server for verified, evidence-based project completion tracking in Claude Code
Veritap
Check whether a real-world fact can be verified before an agent acts on it. Business-exists claims answered free with registry evidence (GLEIF, SEC EDGAR, Wikidata). MCP, no auth.
Claimcheck
An MCP server that settles a claim about code instead of asserting it — runs a test with and without the fix it guards
PolicyNIM
PolicyNIM is a policy-aware engineering preflight layer for AI coding agents.
Execution Proofs
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.
Cdv
Conservative Dual-Verify — judging AI agent work with a deterministic floor + LLM critic (stricter score wins) and Bayesian stopping. Research preview, frozen at v1.0.1; active de…
Agentgate Governed Writefile Demo
Smallest outsider-readable proof path through AgentGate + MCP Firewall: governed write_file, independent on-disk verification, and inspectable audit artifacts.
Howdex
The audit and verification layer for AI agents - verified procedural memory with compliance reports (SOC 2, EU AI Act, NIST AI RMF), a public procedure registry, and the verifier…
Connector Forge 2
Build and verify portable MCP/CLI bridges for Codex, Claude Code/Cowork, and Antigravity.
Litmuz Agent
Claim-level verification for life-sciences research agents: honest, auditable, per-claim traffic-light verdicts against the primary literature and genomic reference data. MCP-nati…
Agent Skill Forge
Spec-driven AI agent skill generator and verification pipeline for building, testing, repairing, and packaging production-ready agent skills.
Heydey
Local-first AI OS that proves every answer: per-sentence receipts, a fail-closed check by a different model family, cite-or-silent refusals. Interactive knowledge graph, artifact…
AI Fact Gate
Checks receipts on LLM claims (as a json), verifies and kicks it back for lyin'
Membrane
MCP server for post-deploy verification — DORA metrics, deploy checks, gamified XP/LOVE rewards, and artifact minting
Verification Security
Public verification, security review, and skill quality process for Agent Skill Exchange
OpenARD
Neutral self-hosted registry and toolkit for Agentic Resource Discovery.
Hermes Satellite
Remote Hermes execution and satellite verification over authenticated MCP. Dispatch tasks to a shared Mac mini running Hermes Agent, poll for terminal status, fetch transcript evi…