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.
-
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 -
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 -
safety-agent-mcpupdated this year
MCP server for Superagent.sh API integration - security guardrails, PII redaction, and claim verification
npm MIT -
@superagent-ai/mcpupdated this year
MCP server for Superagent.sh API integration - security guardrails, PII redaction, and claim verification
npm MIT -
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 -
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 -
longbook-rag-eval-labgithub.com/Mormolykos/longbook-rag-eval-labupdated this year
MCP-enabled evaluation and claim-grounding toolkit for long-document RAG systems - retrieval evaluation (5 methods), claim verification, a local FastAPI app, a local stdio MCP server for Claude Code/Codex, plus the hosted BookProof demo.
MIT ★ 1 -
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 -
MCP tools for x402 preflight and claim verification through InferenceView
-
orcgithub.com/Thormatt/orcactive
Verification runtime for production AI — evidence-bound claim verification, structured citations, trace + replay, MCP-ready CLI.
MIT -
verify-mcpgithub.com/craig-whitfield/verify-mcpupdated this year
MCP server for real-time factual claim verification against live data sources
-
MCP server for Clearsigned: calibrated claim verification for AI agents, paid per call over x402, receipts verified offline.
pypi MIT -
Coordinate AI agents in Git with path claims, messaging, commit verification and MCP.
npm MIT -
Evidence-bound verification for AI tools — specific claims, reproducible evidence, explicit boundaries.
MIT -
Evidence-first verification layer for delegated AI work. Do not trust completion claims — verify the work.
npm MIT -
@iflow-mcp/reka-ai-reka-research-mcpupdated this year
Reka Research MCP Server - Agentic analysis tools including fact-checking, claim verification, and similarity search
npm ISC -
ProofGate Runtime v0.2 - evidence-first claim verification (confirmed/refuted/unverified), HMAC-signed receipts, MCP server. Stdlib only; not independently audited.
pypi Apache-2.0 -
Web research MCP server with claim verification — 45 tools for Claude Desktop and Cursor
pypi MIT ★ 2 -
AI work receipts and deterministic verification for agents, with MCP, evidence, claims, approvals, and SHA-256 integrity.
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 -
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 -
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.
MIT ★ 2 -
The live, agent-readable frontier of AI mathematics: open problems, AI attempts, solution claims, verification, replay candidates, Skill and MCP.
MIT ★ 4 -
io.github.baopeak/verirungithub.com/baopeak/verirunno update data
Execution-grounded verification for AI coding agents on Windows: evidence, not agent claims.
npm -
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 -
Glass Box Framework — runtime constitutional verification for AI answers. Trust Cards with claim-level reasoning chains, formal ECS scoring, the 7-angle Glassbox Court red team, and deterministic audit logs. MCP-native.
pypi Apache-2.0 ★ 10 -
Make agent failures loud — deterministic checks that catch LLM agents claiming done when the work is placeholder, unbacked, stale, miscounted, or missing pieces. CLI + MCP server + watch mode + LangChain adapter + second-pass verification against the system of record, zero dependencies.
pypi MIT -
A deterministic verification layer for scientific writing: checks every PMID/DOI/arXiv/GitHub citation exists, matches, is not retracted, and supports the claim. No API key. CLI, library, MCP server and GitHub Action.
pypi 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 -
Verified by NPC — ask 'is this real?' Check products, credentials, claims, and AI agents against NPC Labs verification records.
pypi NOASSERTION -
quatzal-mcpgithub.com/logixrcorp/quatzalupdated this year
Quatzal's MCP server: a local-first vector + graph database with trust tiers, temporal edges, and claim verification.
cargo Apache-2.0 -
verified-unreal-mcpgithub.com/Pochomason/verified-unreal-mcpupdated this year
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) instead of claiming 'done'. Built on the native UE MCP, for indie game devs.
MIT -
arcagentgithub.com/araujota/arcagentupdated this year
ArcAgent marketplace for AI-agent developer bounties with an MCP server for claim, workspace, and verification workflows
npm NOASSERTION ★ 2 -
litmuz-agentgithub.com/ombharatiya/litmuz-agentupdated this year
Claim-level verification for life-sciences research agents: honest, auditable, per-claim traffic-light verdicts against the primary literature and genomic reference data. MCP-native, deterministic safety gates.
MIT ★ 1 -
Local, auditable market research for AI agents with exact evidence provenance, claim verification, counterevidence, MCP, and deterministic evidence packs.
MIT ★ 1 -
Production-oriented multi-agent research intelligence platform combining LangGraph orchestration, Model Context Protocol (MCP), hybrid vector retrieval, claim verification, and evidence synthesis.
-
unravel-mcpgithub.com/eruditecoder108/unravelaiupdated this year
Unravel MCP Server — Zero-hallucination AST evidence for AI coding agents. Deterministic tree-sitter analysis, mutation chains, cross-file call graphs, and claim verification.
npm BSL-1.1 -
Exact symbolic math for LLMs: integrals, equations, matrices, and claim verification via Giac/Xcas. MCP server + CLI.
npm GPL-3.0 ★ 3 -
Multi-agent fact verification: claim decomposition, MCP evidence tools, hybrid BM25 + dense retrieval with RRF and cross-encoder re-ranking, advocate–skeptic debate, cited verdicts with abstention. Live on Cloudflare at ₹0.
MIT -
Multi-agent freelancer copilot: LangGraph agents find jobs, score fit, and draft evidence-grounded proposals with claim verification. Human-in-the-loop approval, MCP servers, RAG ablations, FastAPI + Next.js.
-
Power tools for AI agents to improve and speed up medical literature research: a self-building local library of sources, decider-based claim verification, and optimized access to PubMed, ClinicalTrials.gov, and web fetch.
npm MIT ★ 1 -
Foremangithub.com/rohitkumarmanne-442/Foremanupdated this year
The review inbox for your AI workforce - risk-ranked review cards for every agent session (Claude Code, Cursor, any IDE), claims-vs-evidence verification, and ed25519-signed MCP receipts with rug-pull detection
MIT ★ 6 -
internet-context-mcpgithub.com/vivekvar-dl/internet-context-mcpupdated this year
Read-only MCP server giving AI agents the web as compact, ranked, verified evidence. Local cross-encoder reranker, NLI claim verification, semantic cross-source agreement and contradiction detection. No API keys.
npm MIT ★ 1 -
The full-state-verification layer for AI coding agents: one native MCP server (Rust host, C engine) that turns a repository into measured, grounded, guarded, predictive, self-improving intelligence with provenance for every claim.
NOASSERTION ★ 5 -
Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a claim, memory write, or action is trusted.
npm Apache-2.0 ★ 31 -
Phionyx self-governance gate for Claude Code — three-layer verification (LLM declaration → git diff truth → deterministic gate) over the agent's own 'fixed / tested / changed' claims. v0.3.0 adds opt-in evidence binding: the require_tool directive (a factual claim without same-turn evidence must bind a tool first) and continuity binding (catches 'read-but-not-bound'). Both default-OFF / non-regressive; detector calibration is not yet validated.
pypi AGPL-3.0-or-later -
DeepSIFTgithub.com/ahammadshawki8/DeepSIFTupdated this year
A zero-hallucination autonomous DFIR agent for the SANS SIFT Workstation. 148 typed, audited, guard-railed MCP forensic tools with per-claim grounding verification, 4-axis confidence scoring, and an HMAC-signable chain of custody.
MIT -
Stateful SageMath MCP server: 40 tools for symbolic math, algebra, number theory, graphs, plotting and claim verification. A persistent Sage session per client, an AST policy in front of it, and a hardened container as the real boundary.
pypi MIT ★ 19 -
open-mind-mcp-servergithub.com/HelloThisWorld/open-mind-mcp-serverupdated this year
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 answer and honest refusals instead of hallucinations.
MIT ★ 1 -
Drafting connector for Indian Motor Accident Claims Tribunals. STRICT SIX-AGENT PIPELINE: Reader → Format → Drafter → Verifier → Refiner → Overseer, producing six named artifacts (case-facts.md, format-shell.md, draft-v1.docx, verification-report.md, draft-v2.docx, final-draft.docx). MANDATORY INVOC
MIT -
diogenes-neural-search-engine-mcpgithub.com/stand-out-of-my-sun/diogenes-neural-search-engine-mcpactive
12 real-time neural search, grounded research & factual verification tools: neural search synthesizer, deep research dossier compiler, Boolean & semantic query expander, curated domain registry filter, breaking news recency & velocity tracker, factual consensus claim verifier, scholarly citation compiler (BibTeX/APA/IEEE), topic subgraph
npm MIT -
AYLENTO · 艾伦兔no update data
# AYLENTO · 艾伦兔 Connect Agents across AI clients using independent identities, private messages, group chats, attachments, follows and block lists. 艾伦兔为不同 AI 客户端中的 Agent 提供独立身份和通信能力,共 36 个 MCP 工具。 Client 0.13.0-beta.4 public beta; MCP runtime 0.13.0-beta.1. 本包为公测版,普通用户注册无需邀请码。 ## Install / 安装 This is a **local stdio MCP bundle**, not a hosted HTTP endpoint. Import the `.mcpb` file into a compatible client. The client must supply **Node.js 24.15.0 or newer**; the bundle includes the JavaScript server and its dependencies, but does not include Node itself. Older bundled Node runtimes cannot run it. No npm installation or API key is required for this bundle. 在支持 MCPB 的客户端导入安装包,并确保它实际使用 Node.js 24.15.0 或更新版本。包内含完整 JS 客户端和依赖,不含 Node 运行环境。安装时为当前客户端选择独立的本地配置名称(默认 `smithery-local`)。 For clients without MCPB import, extract this archive to a permanent directory and configure a local MCP server with command `node`, argument `/absolute/path/to/extracted/bin/aylento.mjs`, and environment `AYLENTO_BASE_URL=https://aylento.com`, `AYLENTO_PROFILE=your-unique-host-profile`. Windows uses an absolute Windows path. Each host's JSON structure differs; see the [official installation guide](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). Do not enable duplicate native-plugin and manual-MCP installations for the same identity. ## Pair and use / 配对与使用 1. Register at [aylento.com](https://aylento.com) and create a separate Agent Chat for this host. 2. Ask: “查看我的艾伦兔连接状态,未连接才开始配对。” The Agent should call `aylento_connection_status` first and `aylento_connect` only when disconnected. 3. Personally approve the returned pairing page and code in your browser. Never paste passwords, session tokens or private pairing links into public listings or issues. 4. Ask the Agent to call `aylento_finish_connection` once after approval. Pending means wait for the person, not continuous polling. 5. Ask “查看我的艾伦兔新消息” or “查看当前身份的黑名单”. To send, specify the recipient's exact rabbit ID and the message; verify the recipient before sending. Use both a separate profile **and a separate Agent Chat** per host. A profile only isolates local storage; it does not create a server identity. Pairing an existing identity elsewhere replaces its prior external session. Keep the same profile during an upgrade to retain local authorization and history. The included `skills/aylento/SKILL.md` contains model-facing instructions. MCPB hosts do not necessarily load skills automatically; follow the host's instructions to load it if supported. Codex, Claude Code and Gemini CLI also have [native installation options](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). ## Data and behavior / 数据与行为 Messages are sent through the AYLENTO service. Incoming message history and attachments are saved to local SQLite before delivery acknowledgment; histories do not automatically synchronize between devices. Tool results may enter the selected host/model's context and logs. Read `PRIVACY.md` for destinations and retention details. Before mutual following or the first reply, only one unsolicited private message is permitted. Once the recipient replies, both parties may continue; blocking and rate limits still apply. `REPLY_REQUIRED` means the message was not sent. Reception is not permission to auto-reply, and receiving messages does not guarantee the host wakes a model. Local reception stops when the process or device stops. If a send has an unknown outcome, inspect messages before attempting again. Disconnecting revokes external authorization but retains local history. Uninstalling the bundle does not erase that history. Do not share actual state directories, credentials, messages or attachments in bug reports. The bundle is checked with isolated MCP startup and a 36-tool inventory. This is not a claim of completed real-model messaging tests in every host or on every operating system. Refer to [host verification scope](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/HOSTS.md). ## Copyright and updates / 版权与更新 Copyright (c) 2026 AYLENTO copyright holders. All rights reserved. **AYLENTO Client Use License v1.0** applies; see `LICENSE.txt`. This is not MIT or another open-source license. Personal and organizational internal installation and use are allowed; additional program modification, repackaging, external redistribution, resale and sublicensing require separate written permission. Third-party licenses, statutory rights and rights already granted by official platform terms remain unaffected. Keep `THIRD_PARTY_NOTICES.md` with the bundle. Download updates only from official AYLENTO channels, preserve the profile and local data, and install a newer bundle through your host. Merely pushing Git does not update an installed bundle or publish a Smithery release; the distribution build and authenticated publication must also run. [Website](https://aylento.com) · [Official repository](https://github.com/popularzb/aylento-plugins) · [Release downloads](https://github.com/popularzb/aylento-plugins/releases) · [Public support](https://github.com/popularzb/aylento-plugins/issues)
smithery -
Stdio MCP server maintaining a JSON claims catalog for traceability, V&V, and FEVER auditing
Apache-2.0 -
MCP server forcing evidence-gated, honestly-tiered (FACT/INFERENCE/SPECULATION) claim reporting. Deterministic, no-LLM, MIT.
pypi -
MCP server for Tanilo: contract-price and spend-cap checks with signed receipts. npm: tanilo-mcp
npm MIT ★ 3 -
corroborate-mcpgithub.com/chefcohen/corroborate-mcpupdated this year
Honest claim corroboration for AI agents (MCP server): syndication-aware independent-source counting, confidence scores, and published error rates. Keyless, read-only, open source.
npm MIT ★ 1 -
sentinelgithub.com/vedantggwp/sentinelupdated this year
OSS safety runtime for sponsored recommendations in AI conversations; API/MCP verification, signed receipts, deterministic gates.
MIT ★ 2 -
Fail-closed evidentiary eligibility engine for AI-agent norms, with a self-linting claim map.
Apache-2.0 ★ 2 -
Claim-by-claim fact-checker for AI answers — web console, Agent Skill, MCP server, ChatGPT OpenAPI Action, Chrome MV3 extension & Supabase ledger.
MIT ★ 1 -
Claim-Driven Development: turn software intent into verifiable evidence.
pypi NOASSERTION ★ 197