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.
-
MCP server that compiles ISO 20022 readiness findings, remediation diffs, and simulated responses into sealed audit evidence packs.
pypi Apache-2.0 OR MIT -
Read-only blockchain evidence for AI agents. Reproducible Base/Solana cases, local MCP, Core/Hub/Lens and NE Maps. No wallet or signing.
Apache-2.0 ★ 1 -
Local MCP server that compiles ISO 20022 readiness findings into sealed, tamper-evident audit evidence packs. Part of the ISO 20022 MCP Suite.
pypi Apache-2.0 ★ 1 -
agent-evidence-mcpgithub.com/xiexie-qiuligao/agent-evidence-mcpupdated this year
面向 agent 长任务的本地 MCP,自动保存截图、短录屏、打码副本和可复盘证据。
MIT ★ 4 -
mcp-evidence-ledgergithub.com/brianpelow/mcp-evidence-ledgerupdated this year
An MCP server providing an append-only, hash-chained evidence ledger for agent actions. Tamper-evident receipts over real local state; deterministic, no LLM. Agents are non-deterministic; their audit trail should not be.
Apache-2.0 ★ 1 -
AI-operated Weio; local consistency checks of supplied OAuth test evidence and release IDs. Linux alpha.
MIT -
Persistent project workflow for Codex that connects intent, sources, plans, tools, evidence, and continuity, with a read-only Windows Studio.
MIT -
Open-source, evidence-provenance-first scientific literature MCP server: 35 tools for literature search, citation/retraction checks, full-text quote verification, methodology audits, PRISMA-style screening, hash-chained evidence ledger, BM25 retrieval and NLI assessment. Apache-2.0.
Apache-2.0 ★ 5 -
Cross-check collected data across sources, with provenance, before trusting it. Zero-dependency MCP server.
pypi MIT -
An MCP server for agents that do literature research in medicine: a self-building local library of sources, decider-based claim verification, and optimized access to PubMed, ClinicalTrials.gov, and web fetch.
MIT ★ 1 -
MCP server for evidence-disciplined genealogy: read/write access to a self-hosted Gramps Web tree where every fact carries a citation, plus a read-only reference layer over legacy GEDCOM exports.
pypi MIT -
evidence-gategithub.com/LopezDray/evidence-gateupdated this year
Stop your AI from making up facts about your own data. A pre-generation grounding gate for LLM/RAG apps — zero-dep, MIT, JS + Python, with an MCP server.
MIT -
Is that trading record skill, or could it be luck? Check any Hyperliquid wallet, rescore leaderboards for best-of-N selection, and audit AI backtests for knowledge-cutoff leakage. Python stdlib, MCP server, agent skill.
pypi MIT -
Font discovery and typography tools for AI agents. Explore local open and proprietary collections, refine by visual similarity, compare real text in context, and resolve exact assets through a JSON CLI and MCP. Fonts and model inference stay local; usage rights vary by source.
MIT ★ 1 -
Project-based auto-research AI agent framework. Problem × Evidence Matrix, evidence grading, MCP Server. Python 3.10+. | 项目制自动研究 Agent 框架:问题 × 证据矩阵、证据分级。
MIT ★ 1 -
Evidence-graded scientific literature search for AI agents — multi-database (PubMed, Europe PMC, ChinaXiv, RussiaRxiv), built for medical, clinical and supplementation research.
npm MIT -
Evidence-graded scientific literature search for AI agents: an MCP server for PubMed, Europe PMC, ChinaXiv and RussiaRxiv.
npm MIT -
Policy hook (fail-closed for checked tools) and tamper-evident evidence log for Claude Code. The code runs locally. Evidence supporting audits. Not a sandbox. PolyForm Noncommercial.
NOASSERTION -
Local codebase intelligence for AI coding agents: structural repo map, change-safety gates, MCP security receipts, and tamper-evident ChangeEvidence packets. Local analysis, zero API keys, no source-code egress.
pypi Apache-2.0 -
Operator attribution and digital evidence tools specialized for the digital advertising ecosystem—aggregating websites linked to suspicious connections into operator clusters and generating reproducible evidence packages. 操弄者歸因與數位證據工具,特化於數位廣告生態——把可疑連結背後的網站聚合成操作者群組,輸出可重現證據封包。
MIT ★ 3 -
MCP server for Attest Capture - evidence-grade screenshot, PDF and HTML capture for AI agents. SHA-256 + timestamp + public evidence page per capture.
MIT -
APEX PSI MCP server - append-only evidence receipts for AI decisions and documents: seal a record, verify a hash against the public ledger, check a chain, cite a receipt, read Bitcoin anchoring status. Verification is free and needs no account.
npm MIT -
compliance-shield-mcpgithub.com/mdfifty50-boop/compliance-shield-mcpupdated this year
EU AI Act compliance audit trails and evidence generation for AI agent systems — risk classification, decision logging, gap analysis, and auditor-ready evidence packages
npm MIT -
IronTrellis evidence MCP server: one bounded local tool that copies operator-selected files into an evidence packet when the configured agent still holds the authority, exactly once per operation id. Agents change. The structure holds.
npm Apache-2.0 -
truthstack-mcpgithub.com/truthstack1/truthstack-mcpupdated this year
TruthStack MCP Server — Structured supplement interaction and evidence data for AI agents
npm MIT -
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 -
research-connector-hubgithub.com/nicks2025fk/research-connector-hubupdated this year
Local-first research evidence and structured brief MVP with CLI and a bounded MCP adapter.
MIT -
Multi-Source Medical Literature Router for Evidence-Based Medicine. MCP Server + CLI, Go + Shell + Rust. Depends on via54Design.
NOASSERTION ★ 2 -
Evidence-first CLI and optional MCP server for timestamped video transcript search and citation validation.
MIT ★ 1 -
MCP server for SourceMed — a source-verified medical evidence library built for agents (sourcemed.io)
MIT -
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 -
Evidence-first codebase analysis for coding agents (runs the Python package verinoda through uvx, pipx or a private venv)
npm Apache-2.0 -
hexwitnessgithub.com/siaginw/hexwitnessupdated this year
Evidence-first reverse-engineering workbench for humans and AI agents
npm Apache-2.0 -
arkhive-ledgergithub.com/sammyboi81/arkhiveupdated this year
ArkHive — self-contained, tamper-evident memory ledger for AI agents. SQLite + SHA-256, zero dependencies, nothing leaves the box.
pypi Apache-2.0 -
Honesty MCP | One server that gives AI assistants tools for checking citations, evidence, claims, and decisions. Requires the sibling kit repositories.
npm MIT -
agent-replay-debugger-mcpgithub.com/csoai-org/agent-replay-debugger-mcpupdated this year
Agent Replay Debugger MCP — record every agent step + replay deterministically. Step-debugger for agentic loops. Audit-evidence signed exports. By MEOK AI Labs.
pypi MIT -
evidra-lockgithub.com/vitas/evidra-lockupdated this year
MCP Kill-switch for AI agents. Validates infrastructure operations before execution. Fail-closed. Evidence-backed.
Apache-2.0 ★ 8 -
Open-source task commons where AI agents do bounded public-good work, publish evidence, and review results.
MIT -
Python SDK, CLI and MCP server for ThinkerWave — an autonomous research agent that shows its evidence.
Apache-2.0 -
Zero-dependency security auditor for Dockerfiles, compose files and .dockerignore — three passes, evidence-first, SARIF for CI.
MIT -
7+1 task boundary analysis and native calculation verification for AI agents, with evidence reports and a local MCP workbench
npm MIT -
@iflow-mcp/grainulation-wheatgithub.com/grainulation/wheatupdated this year
Research-driven development framework — structured claims, compiled evidence, deterministic output
npm MIT -
Private, evidence-first document agent with persistent local memory, exact citations, reversible actions, and bounded Nemotron reasoning.
MIT ★ 1 -
Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.
npm Apache-2.0 ★ 113 -
Free open-source search, API and MCP for attributed SEO and AI-visibility evidence from expert videos.
Apache-2.0 -
Open-source, tamper-evident logbook for AI agents. Runs on your own EU servers, works with any model (MCP).
Apache-2.0 -
Tamper-evident audit log for B2B SaaS: hash-chained, anchored to Sigstore Rekor and OpenTimestamps, verifiable offline. Claude MCP connector included.
npm NOASSERTION ★ 3 -
MCP bridge for Hermes Plant action safety, spend assurance, signed evidence, and deterministic x402 APIs.
MIT ★ 2 -
A desktop tool that turns GitHub repositories into evidence-based project reports and AI-readable indexes.
★ 1 -
MCP server for memory forensics with Volatility 3 — tamper-evident evidence store, DKOM/rootkit detection, and evidence-grounded LLM investigation.
Apache-2.0 -
rag-db-advisorgithub.com/kenimo49/rag-db-advisorupdated this year
An evidence-based advisor for RAG stack decisions — every claim backed by rag-retriever-bench measurements. MCP + CLI.
MIT -
zoom-searchgithub.com/goofrey/zoom-searchupdated this year
MCP search and evidence tool for AI agents with query rewriting, source zoom-in, sourced answers, and runtime metrics.
pypi MIT ★ 4 -
Codex-native-long-video-memorygithub.com/NitcanKen/Codex-native-long-video-memoryupdated this year
Local-first Codex plugin that indexes long videos with OCR/ASR and answers with timestamped, SHA-verified visual evidence.
Apache-2.0 ★ 4 -
Python CLI and MCP for evidence-driven product research: document citations, research reports, lifecycle management and portable backups | 知微
MIT -
An evidence-chain whiteboard and MCP server that keeps AI research agents honest: every claim traces back to the run and the code that produced it.
npm AGPL-3.0-or-later -
Readproof — the lockfile and replay primitive for what AI agents read: stable identity, freshness policy, content-addressed snapshots, per-run manifests, diff, byte-exact replay, evidence bundles.
npm Apache-2.0 -
Agent action evidence ledger: append-only, hash-linked record of agent proposals, executions, redactions and annotations with an independent verifier. Reference implementation of the public SHPBL behaviour specification.
MIT -
Evidence-first cybersecurity MCP server with persistent SQLite graph memory, vulnerability triage, scoped testing and reports for Antigravity and Codex.
MIT ★ 1 -
Evidence-first reverse engineering workbench with bounded binary analysis, extensible static adapters, MCP and reproducible local investigations.
MIT -
Multi-source clinical lab analysis pipeline: lab tests + PubMed evidence + MRI cross-validation, with DSPy dual-track LLM, quant gates and MCP server.
MIT ★ 1