- 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.
Ddddocr
ddddocr rust 版本，ocr_api_server rust 版本，二进制版本，验证码识别，不依赖 opencv 库，跨平台运行，AI MCP 支持，a simple OCR API server, very easy to deploy。
Heimdall
Open Source Observability Platform for MCP Servers & Apps
Reverify
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Re…
co-browser/attestable-mcp-server
Verify that any MCP server is running the intended and untampered code via hardware attestation.
AegisTrace
Verifiable execution for durable AI agents: policy-bound workflow compiler, hash-chained journal, offline replay, and Merkle + Ed25519 proofs. Go.
Opencode Plusplus
OpenCode++：面向 OpenCode 的 AI 编程可靠性增强框架，为其增加上下文管理、编辑边界、命令证据、验证门禁、影响分析与修复闭环能力。OpenCode++: a Coding Agent Reliability Harness for OpenCode, adding context, edit boundaries, command ev…
RobloxForge Intelligence
RobloxForge Docs 2026: Official MCP Vertical Slice Verification Layer for Studio
Agent Inbox
Give any AI agent a disposable email inbox in one tool call. MCP server for email verification, auth flows, and testing.
AI Driven Development
A quality methodology for AI-assisted software development. Six layers, adopted incrementally.
Xenon
🚀 Xenon — Agent Harness for AI coding agents. 证据导向架构 + 7种推理范式 + 执行隔离边界 + SWE-bench 40% 通过率（+6.7pp）。可信、可验证、可评测的 AI Agent 运行时。
Tenet
TypeScript AI agent framework with multi-judge hallucination verifier + Vectara HHEM-2.1, pre-tool-call governance/approval/audit, WASM-sandboxed tools, MCP OAuth gateway. 10 surf…
Jev Judge MCP
Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy de…
Melra
The open-source autonomy kernel MELRA — Modular Execution Layer for Reliable Autonomy. An agent-independent effect runtime for governed, durable, and verifiable autonomous executi…
Attestable MCP
TLS](https://gramine.readthedocs.io/en/stable/attestation.html). This allows an MCP client to verify the server before connecting.
Gutenberg CLI
From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.
Tools Factory
From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.
Oh My Dag
The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside the model — exit codes, write-set check…
Tardygrada
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 L…
Cladding
For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI coding agent: your intent goes in befor…
Red Team Blue Team Agent Fabric
AI agent security harness, adversarial testing: 611 executable tests in the v4.20.0 release, across MCP, A2A, x402/L402, decision governance, benchmark integrity, human-in-the-loo…
AegisTrace
AegisTrace - verifiable execution for durable AI agents. Compile policy-bound workflows, record every effect, replay without the network, and prove individual events.
Treeship
Portable trust receipts for agent workflows. Signed, chained, verifiable.
SchemaPin
The SchemaPin protocol for cryptographically signing and verifying AI agent tool schemas to prevent supply-chain attacks.
Claimchain
Verify that an AI agent's on-chain claims are actually true. A claim-level groundedness checker for Solana / memecoin agents.
MCP
Maina MCP server — Model Context Protocol bridge for AI host agents
Tether Name MCP Server
MCP server for tether.name - AI agent identity verification
Parity Studio
MCP server for Parity Studio. Lets coding agents capture existing app routes, decompose them into ui_kit/ bundles, and import them for iteration.
Prism Verify
prism-verify — runtime LLM verifier (family-different, reasoning-stripped, multi-lens, signed Ed25519 receipts). Zero-prerequisite npx install via a verified binary launcher.
Rivet
Rivet — SDLC traceability, validation, and MCP server for safety-critical systems (ISO 26262, DO-178C, ASPICE, STPA)
Dod Guard
Anti-cheat Definition of Done verification with locked proofs. Claude Code plugin with MCP server and /interview skill.
Exnos
Live browser-state verification for AI coding agents. One MCP call, milliseconds, truth. Free, by GOL Productions.
Notdone
Model Context Protocol server for NotDone
Verigent MCP Server
MCP server for Verigent — AI agent verification & counterparty due diligence. Check who you're transacting with, carry your own VG credential, flag bad actors.
Telesign
MCP server for TeleSign APIs - phone verification, intelligence, and messaging
Server
MCP server for Verigent — AI agent verification & counterparty due diligence. Check who you're transacting with, carry your own VG credential, flag bad actors.
MCP
FDKEY verification middleware for MCP servers — gate AI-agent access behind LLM-only puzzles. Runs on Node 18+, Cloudflare Workers, Bun, and Deno.
Daksh-create349/Contradiction-MCP
mcp`
Heimdall
Verification gates for AI coding agents — nothing ships unproven. Falsifiable oracle gates, team wall, receipts. Works with Claude Code today; Cursor, Codex, Gemini CLI & every gi…
Uum8dSolarResearch
Deterministic no-float Math Court MCP clients for agent builders. Bind affine.earth. Integers sealed. Floats refused. Server is not in this git.
Gozzle
ClickHouse verification CLI & MCP
MissionControl
Control plane for human-directed, agent-executed software delivery—with governed execution, verification, evidence, and human-approved pull requests.
HOLDLINE
Ask many places one question by phone through CALL-E, and get back only the answers the call actually established. A value returned for a question the agent never asked comes back…
Uatp
Signed receipts for AI-agent actions. Verifiable memory without trusting the runtime.
Accountable Surface
Gate AI-agent actions with explicit grants, durable journals, MCP server support, and verification.
Nobulex Registry
Python prototype for financial decision integrity: evidence checks, deterministic PERMIT/BLOCK/ESCALATE decisions, and signed receipts. Includes offline failure examples. Not a pr…
Soma Governance
Autonomous Agent Architectural Steering Engine. Prevents architectural drift, circular rework loops, and breaking edits when running headless AI coding agents (Claude Code, Antigr…
Groundcheck MCP
MCP connector that verifies a claim's grounding against reality (quotes, citations, code, repos, math) with no LLM in the verification path. Works in Claude and Gemini.
Cadence
Verification layer for AI-assisted development. Agents don't get to self-certify — settle gates re-check declared acceptance criteria and refuse until the evidence holds. CLI · Cl…
Sentinel
OSS safety runtime for sponsored recommendations in AI conversations; API/MCP verification, signed receipts, deterministic gates.
Aegis Guardrails
Deterministic governance and guardrails for autonomous AI coding agents. Features AST verification, evidence-based rule execution, and native MCP support for Antigravity and Claud…