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.
-
Grounding/hallucination guard: verify a claim against evidence (Supported/Refuted/NEE).
npm -
Zero-dependency verifiable-claims MCP: validate safely, verify with allow_execution, self-test.
pypi -
MCP server forcing evidence-gated, honestly-tiered (FACT/INFERENCE/SPECULATION) claim reporting. Deterministic, no-LLM, MIT.
pypi -
Is this true? Verify a claim, URL, file, or AI answer: up to 20 claims (configurable) judged against web sources, with confidence, the evidence span, and the reason. CLI + MCP server.
npm Apache-2.0 -
Verified by NPC — ask 'is this real?' Check products, credentials, claims, and AI agents against NPC Labs verification records.
pypi NOASSERTION -
An MCP server that gives an agent a way to be checked — tools that verify its claims against reality, and that never report 'I could not check' as 'it is fine'.
MIT -
Anti-confabulation MCP server — verify_claim returns raw observed facts, never verdicts. No API keys, no LLM calls.
MIT ★ 1 -
Claim-Driven Development: turn software intent into verifiable evidence.
pypi NOASSERTION ★ 197 -
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 -
Verify whether a public source supports a factual claim. MCP tool for source verification, citation checking, and fact verification; caller pays $0.02 USDC on Base. mcprush.com-claim-truthpal-mcp-b968778a771fd3b015104dd1
npm MIT -
Evidence-first verification layer for delegated AI work. Do not trust completion claims — verify the work.
npm MIT -
MCP server that fact-checks claims — verify_claim tool with signed receipts
npm -
Evidence-first entity and knowledge graph MCP server for AI agents to verify claims, trace cryptographic provenance, and retrieve 90% less context.
MIT ★ 1 -
heor-studiogithub.com/andey0Saikiran/heor-studioupdated this year
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
NOASSERTION -
atlas-mcpgithub.com/Ispau/atlas-mcpupdated this year
MCP server for Claude Desktop that applies Popperian falsifiability to verify claims from social media, news and blogs — with real academic sources, not opinions.
MIT ★ 2 -
Physics assistant: checked equations, live simulations, claims verified against arXiv papers
pypi MIT ★ 1 -
Build any paper, prove every claim. IRP turns a research paper into working code and a verifiable, claim-by-claim reproduction report, driven by your AI coding agent over MCP or the CLI.
pypi MIT ★ 3 -
aximur-mcpupdated this year
MCP server for the AXIMUR verification API — verify a claim against grounding evidence and get SUPPORTED / UNSUPPORTED / UNCERTAIN with confidence and an audit trail.
npm MIT -
Verify every spec requirement is claimed by an issue, PR, or code reference; list gaps.
npm MIT -
Verify a PR really addresses the issue it claims to close: closing keywords plus diff scope.
npm MIT -
mcpgithub.com/teta-pi/mcpactive
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.
★ 1 -
proofledger-mcpupdated this year
ProofLedger MCP server — verify ASC 606 claims with formal proofs
npm MIT -
Evidence-bound reverse-engineering harness for AI agents, served over MCP. Ghidra or IDA static analysis, a claim verifier that rejects claims without quoted evidence, Windows Sandbox runs for behaviour claims. Core edition, Apache-2.0.
Apache-2.0 -
MCP server that verifies capability/version/freshness claims before AI agents ship them. Institutionalizes 'zero-hop verify' as callable tools.
MIT -
MCP server exposing TypeSafe Jev as purpose-built judgment tools: verify claims, screen for injection, find, rerank, classify, decide, compare passages, extract fields, review patches, and gate completion claims, each with typed probabilities.
npm MIT -
Deterministic factual grounding and claim cross-check verifier for AI agents (A2A & MCP)
MIT ★ 1 -
Local citation verifier — checks that sources actually say what LLMs claim. MCP server + CLI. No cloud, no API keys.
pypi -
VERITY — Real-time fact-checking agent. Verifies claims against live web sources. Returns CURRENT/OUTDATED/DISPUTED/UNVERIFIABLE verdicts with confidence scores. x402 payments, MCP + A2A.
npm MIT -
@veroq/x-bridgegithub.com/veroq-ai/veroq-x-bridgeupdated this year
MCP bridge — verify X posts, get social sentiment, fact-check trending claims
npm MIT -
MCP server for Clearsigned: calibrated claim verification for AI agents, paid per call over x402, receipts verified offline.
pypi MIT -
MCP server for verifying AI agent claims vs reality — inline grounding-check on retrieval context, swallowed-exception scanner on agent-written code, and multi-turn transcript review for unverified completions + cross-turn contradictions. Sub-second, local, free, MCP-native — the lightweight complement to dashboard-based eval frameworks (DeepEval, Phoenix, LangSmith).
pypi MIT License -
Evidence and environment awareness for AI agents. Verify claims, catch mismatches, and inspect the local environment.
pypi Apache-2.0 -
MCP server for NIGHTGATE on Midnight. Anchors documents, proves zero-knowledge claims over hidden fields, grants disclosure, and verifies records and claims against live contract state; swaps shielded tokens over an offer board and mints them on a token factory
npm Apache-2.0 ★ 3 -
Checks receipts on LLM claims (as a json), verifies and kicks it back for lyin'
MIT -
Voice concierge that never calls a claim done — ISNAD-verified agent-fleet status and hash-bound approvals over MCP 2025-11-25
MIT -
mcp-cite-fragmentgithub.com/ryo63-bot/mcp-cite-fragmentupdated this year
MCP server for verifying claims against source documents and generating citation links with W3C Text Fragments
npm Apache-2.0 -
mcp_citation_checkergithub.com/ethanchand/mcp_citation_checkerupdated this year
An MCP server that independently verifies whether a claim is actually supported by the source text at a given citation — pluggable storage backend, ships with Weaviate support out of the box.
MIT -
mcp-health-coachgithub.com/HamzaOuadid/mcp-health-coachupdated this year
An MCP server exposing 31 wellness tools where every factual claim is grounded in a verified public source (USDA, openFDA, MedlinePlus, PubMed) rather than model recall.
MIT -
obsidian-anchorgithub.com/Perfectio/obsidian-anchorupdated this year
Reliability-first MCP server for Obsidian — verifies AI claims against your notes and refuses what they can't support.
MIT ★ 2 -
CLI and MCP server that verifies AI coding agent context-reduction proxies' token and cost savings claims
pypi Apache-2.0 -
Frantic MCP plugin and stdio bridge for browsing, claiming, delivering, and verifying work on the public AI bounty board.
npm MIT ★ 2 -
A durable webhook-to-todo work queue for AI agents — verified inbound webhooks become scoped, leased todos that agents claim and complete over MCP.
MIT ★ 3 -
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 -
critic-orchestratorgithub.com/aureliocpr-ctrl/critic-orchestratorupdated this year
MCP server that spawns adversarial reviewers in parallel (Claude CLI, or any OpenAI-compatible / Anthropic API) to verify a claim/fix. Anti-confabulation layer for AI coding agents.
pypi MIT -
patinagithub.com/connor-worthen4/patinaupdated this year
Audit grade procedural memory for coding agents. Lessons from verified changes, served at planning time as cited claims. Local first MCP server.
Apache-2.0 -
Verify agent-authored change claims at exact Git commits with an evidence-first PR gate and local MCP.
npm MIT -
Local-first MCP server and dashboard that turns your own documents into a verifiable claim ledger for your LinkedIn profile. Windows, Node 24, SQLite.
MIT -
Your coding agent gaslights you. GODKILLER doesn't. Disk gates > vibes. claim_done only after verify.
pypi MIT ★ 30 -
MCP server for SmithTalks — a pseudonymous message network for AI agents. Claims with public adjudication, a marketplace between agents, and a sealed ledger you can verify without trusting the server.
npm MIT -
Self-organizing multi-agent platform in Go: LLM agents post, claim, execute and verify tasks. MCP adapter, Claude API, prompt-injection defenses, Telegram operator.
-
Cross-examine what any coding agent claims: verify CLI, MCP server, GitHub Action and transcript history for Claude Code, Codex, Gemini CLI, Cline, Aider and more.
npm MIT -
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
go MIT ★ 22 -
Agentizable: an open-source bounty network where AI agents post, fund, claim, solve, verify, and get paid for digital work.
NOASSERTION ★ 20 -
⚡ ChronoFact: 4-Pillar Epistemic AI Backbone. Real-time temporal cutoff calibration, active NLI claim verifier, zero-pollution memory, and mcplex TF-IDF cost optimizer.
MIT ★ 2 -
Verified technical documentation: every claim cites file#line. Java, Python, TypeScript. Incremental freshness, architecture drift, MCP server. No LLM, zero cost.
MIT -
CodeScope does not understand code. It verifies it. A high-performance code graph engine with MCP protocol for AI agents (Claude/Cursor) to ask "Does the code actually do what you claim?"
Apache-2.0 ★ 13 -
truthsea-mcp-servergithub.com/turfptax/truthseaupdated this year
TruthSea MCP Server — AI agents verify claims, build epistemological dependency graphs, and earn TRUTH tokens through on-chain scoring with security-hardened contracts on Base L2
npm MIT -
Decompose DAG: an epistemic scaffold for vibe coding. A claims graph the agent must verify bottom-up with evidence, an MCP server for agents, a live dashboard for humans.
npm MIT -
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 evidence, decompose claims, and verify outcomes from any MCP-capable client.
MIT ★ 2 -
MCP server for Pepiros: search, verify, and cite claims against a paper's actual text over stdio -- quote-located grounding, not vector similarity.
npm MIT