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.
-
Cryptographic data provenance toolkit for Swarm — SDK, CLI, MCP server, and gateway
MIT ★ 2 -
Model Context Protocol (MCP) server for AI agents to manage Swarm postage stamps and store provenance data on decentralized storage
MIT ★ 1 -
provenance-mcpgithub.com/stdiolabs/provenance-mcpupdated this year
MCP server for the Provenance platform — connect AI agents to your provenance data
pypi MIT License Copyright (c) 2025 STDIO Labs Perm -
Research-OSgithub.com/VibhavSetlur/Research-OSupdated this year
An AI-native operating system for reproducible research. Features citation-verified analysis, audited provenance, and automated data integrity pipelines.
MIT ★ 1 -
Cross-check collected data across sources, with provenance, before trusting it. Zero-dependency MCP server.
pypi MIT -
Governed, AI-safe access to customer data — an MCP server enforcing consent, PII removal, provenance, and audit on every agent read. Spec-first with Claude Code, 99 tests.
MIT -
An AI-native data foundry: turns messy, lawfully acquired sources into canonical, evidence-backed knowledge products served via web, REST, MCP and bulk exports. Provenance-first, vertical-agnostic.
MIT -
Deterministic web-evidence engine: trace one field across raw HTML, structured data, embedded state, rendered DOM and network JSON, with exact provenance. CLI and MCP. No LLM.
Apache-2.0 -
alchemylake-databricksgithub.com/zorost/alchemylake-databricksupdated this year
Governed, provenance-sealed creative rendering for Databricks — a Streamlit App + Unity Catalog ai_render() function that turns any governed source (Sample Lakehouse, UC, Genie, or BYO data) into infographics, reports, decks, video briefings, music, and podcasts.
Apache-2.0 ★ 118 -
seif-mcpgithub.com/and2carvalho/seifupdated this year
MCP server for the SEIF Protocol — provenance signing, transparency log, and data classification tools for AI agents (Cursor, Claude Code, Claude Desktop). Thin Node wrapper around the canonical Python implementation.
npm MIT -
Africa Data Bankgithub.com/africa-data-bank/afridb-platformno update data
Trusted African data, provenance, citations, and catalog search for AI agents.
oci -
leapable-mcpgithub.com/chrisroyse/leapablememoryupdated this year
Leapable — Context engineering MCP server. Query expert knowledge corpora, manage your data, and search with full provenance. One-line install: npx leapable-mcp
npm SEE LICENSE IN LICENSE -
nfl-data-mcpgithub.com/malav-majmudar/nfl-data-mcpupdated this year
A provenance-aware factual NFL data server for Model Context Protocol clients.
pypi Apache-2.0 -
prioritize4megithub.com/shailipankaj/prioritize4meupdated this year
A local-first personal AI OS: a provenance-checked memory and a commitment cockpit, with a trust boundary that keeps your private data off the network.
MIT ★ 1 -
MCP server for querying Ukrainian open data (data.gov.ua) with verifiable provenance
MIT -
EcoScopegithub.com/krnzt/ecoscopeno update data
Agent-native ecological data discovery, analysis, visualization, and provenance
mcpb -
Fractale MCP server — AI agent access to open data, gathered and structured with clear provenance
npm MIT -
pmq (Polymarket CLOB V2)github.com/crp4222/pmqno update data
Production-proven Polymarket CLOB V2 trading and data. Fail-closed fills; keys stay local.
pypi -
socioeconomic-data-mcpgithub.com/fpanier/socioeconomic-data-mcpupdated this year
Unified MCP access to the world's official socio-economic data (Eurostat, World Bank, OECD, IMF, FRED, ECB, ILO, UN, WHO, OWID, ARDECO + DBnomics/SDMX) — one interface, full provenance, no invented values.
NOASSERTION ★ 2 -
bluefieldgithub.com/danielvhofmann/bluefieldupdated this year
Local first web scraper that turns any URL into clean Markdown or JSON and signs every capture with an offline verifiable Ed25519 provenance manifest called BPM. Git like history and diff for web data, plus an MCP server so AI agents can prove what they read. TypeScript monorepo, AGPL-3.0 engine, Apache-2.0 spec and SDKs.
AGPL-3.0 ★ 1 -
Pinakes — a deterministic, verifiable data layer for AI agents across domains (biology + literature). Same query → byte-identical records, complete-or-fail-loudly, re-runnable provenance manifest + verify().
go Apache-2.0 ★ 4 -
osf-data-marketplacegithub.com/onefreeman1337/osf-data-marketplaceupdated this year
Remote MCP server + x402 USDC API: 8.1M+ provenance stamped US government and scientific records across 80 official sources, sold per call to AI agents on Base. 21 tools, 15 free. npx osf-data-marketplace
npm MIT -
MCP server exposing Dell EMC PPDM, NetWorker & Data Domain as Claude Code tools — 32 tools (20 PPDM + 6 NetWorker + 6 Data Domain). On npm with signed provenance.
npm MIT -
Local-first MCP server for personal health data (Apple Health, WHOOP, Health Connect) with privacy, statistical evidence, and provenance.
pypi MIT ★ 8 -
@worldscore/mcpgithub.com/mik2503/worldscoreupdated this year
MCP server for WorldScore — read-only, provenance-carrying access to sourced 0–100 country scores for AI agents and MCP clients. Thin client over the public API; ships no data.
npm MIT -
senmcpgithub.com/AlKountiyou/senmcpupdated this year
An open-source Senegal civic MCP stack: MCP servers for public data and citizen services, with a LangChain/LangGraph agent, provenance, and safety-by-design.
MIT -
MCP server making India's public company data agent-legible — 3.74M-company MCA mirror, offline CIN/GSTIN tools, provenance on every field
pypi MIT ★ 1 -
An MCP server over Canada's public tender and award data (CanadaBuys). Scoped auth, provenance on every result, and a write that takes two calls.
MIT ★ 1 -
mcp-injection-guardgithub.com/Hosein-Abdollahi/mcp-injection-guardupdated this year
MCP server that blocks indirect prompt injection by tracking data provenance, not text patterns.
MIT ★ 1 -
alchemylake-apexgithub.com/zorost/alchemylake-apexupdated this year
Truth, made visible. AlchemyLake turns governed lakehouse data (Databricks Unity Catalog, Genie, or your own uploads) into verified, provenance-sealed deliverables: PDF reports, PowerPoint decks, infographics, video briefings, podcasts, sonified scores, deep research. MCP server (13 tools), REST API, CLI. 200 free credits.
Apache-2.0 ★ 1 -
Text-to-SQL agent over public Hedera mainnet data. Ask in English, get the SQL back as the citation — with an eval harness whose cases are proven to reject careless queries. Also an MCP server.
MIT ★ 1 -
A governed MCP server: canonical, provenance-stamped answers for business metrics over role-based access, with a lexer-guarded ad-hoc path and a full audit trail. Architecture, decision records and a working reference implementation on synthetic data.
CC-BY-4.0 -
Agent-native ecological data workbench and MCP server for NEON, EMSO, ICOS, Euro-Argo, local scientific files, multimodal Rerun visualization, selections, and provenance
mcpb MIT -
The sky, queryable. A local, open-source MCP server that hands your AI assistant real astronomy data (ephemerides, catalogs, literature) with citable provenance.
MIT ★ 1 -
koreaapigithub.com/kwangdol-star/koreaapiupdated this year
The verifiable data layer for Korean culture — callable by any AI agent (MCP), citable by any answer engine. Cross-verified, with provenance + Skill Score on every record.
pypi MIT -
Local-first, fully offline AI assistant for an NGO's case data. A local Ollama model answers only through MCP tools, with full provenance in the UI. Nothing leaves the machine.
MIT ★ 3 -
CS239 multi-agent app: three Claude-powered Rakazo bots (Financial Advisor, Payment Manager, Bank Agent) decide if and when you can afford a purchase, and pay bills with your confirmation. Each agent has its own MCP tool server and private data, with 16 policies on access, information flow, provenance and lifecycle. Fictional data.
★ 1 -
AgentGuard MCP server: local spend caps, kill-switch style blocking, and Ed25519-signed provenance receipts for AI agent actions. Zero data plane: prompts never pass through this server.
npm SEE LICENSE IN LICENSE -
Open-source engine for AI-native sales systems — ontology-driven data, one permission kernel, change-set provenance, and native MCP (2026-07-28). Business logic is loaded from pluggable, signed knowledge packs.
Apache-2.0 -
Fledly for AI agents: iOS App Store market data (young apps that earn, proven app ideas, top charts, keyword research, rank tracking) via the hosted Fledly MCP server. Claude Code, Cursor, Hermes, OpenCode and npx skills.
MIT -
HITRAN spectroscopy toolkit for AI agents & researchers: MCP server (12 tools) + HitranLink desktop GUI. 61 line-by-line molecules & 600+ cross-section species. Absorption, cross-section, line strength S(296K), transmittance (Voigt/HT/SDVoigt). One-click XSC download, auto-cache, full provenance. Live data from HITRANonline via HAPI.
GPL-3.0 ★ 5 -
Eclipse Muster MCP — the Customer Graph core of the Eclipse customer adapter family: canonical Person/Company/Deal/Ticket/Conversation/Activity records with per-field provenance and Data Rights Ledgers, propose-only identity merges, field-level egress masking, records-only reply drafts, and a hash-chained, content-free receipt ledger. No platform is contacted and no credential exists in this build.
pypi MIT -
pptx-mcpgithub.com/swak/pptx-mcpupdated this year
AI-powered PowerPoint (.pptx) generation, editing, and review via MCP — 42 tools, 53 slide types, 12 chart types, 8 diagrams, 12 branded presets, 34 archetypes, 8 variant groups, image treatments (mask/duotone/overlay), proportional type-scale, dark-mode palettes, responsive aspect ratios (16:9/4:3/16:10), gradient presets, icon pack, financial primitives, and a 33-rule review engine with WCAG a11y, MECE/parallelism, data-provenance, auto-fix
pypi MIT -
the-metis-fca-handbook-ai-harness-mcpno update data
# Metis FCA Handbook AI Harness — MCP Server An MCP (Model Context Protocol) server that integrates the Metis FCA Handbook AI Harness into Claude Desktop and other MCP-compatible agents. **Tool name:** `evaluate_fca_handbook_applicability` Use this tool to analyze FCA Handbook applicability for a product, service, or firm. Returns structured compliance reasoning with verbatim handbook citations. ## Why choose The Metis FCA Handbook AI Harness? - **Efficiency** Multiplies effectiveness of compliance advice. Saves £80+ in token fees per Harness run. - **Deals with "Hard Problem"**, in which LLMs' token incentives prioritise training data so results are unreliable. - **Verbatim citations** Quotes verbatim entries from the FCA Handbook. Other AI systems struggle to do this. - **Matches real-world need** You do not have to start off knowing which sections you are looking for. Carries out structured searches across all 10,000+ FCA Handbook entries. - **Secure Design** Harness compartmentalisation, one-shot structure, and statelessness fits natively with emerging AI agent security standards such as OWASP Top 10 for Agentic Applications 2026. - **AI Accessible** Integrates easily with AI workflows and agents. Your LLM can use it as a tool. ## Design Principles The Harness is built on proven principles: - **Stateless** — Each request is independent; no session coupling - **One-shot** — Complete analysis in a single call; no multi-turn state - **Clear contract** — Explicit input/output schemas for easy integration - **Hosted** — Single canonical source; no version drift or stale data ## Use Cases ### Compliance AI Platforms Embed FCA reasoning as a service within your compliance platform. Users ask natural-language questions; your platform calls the Harness and presents structured reasoning. ### AI Agent Workflows Agents building compliance workflows can include FCA Handbook reasoning as a composed tool—no external API calls, just MCP configuration. ### Compliance Review Automation Integrate into document review or due-diligence pipelines. Automatically screen new rules against FCA applicability. ## For Regulatory Screening FS firms screening MCP servers will find: - **Simple model:** Stateless, no hidden state, no background jobs - **Clear contract:** Explicit input schema, output schema, error modes - **Transparent updates:** Version pinning; no automatic upgrades - **Single point of failure:** If the Harness is down, it is obvious; no cascading config issues - **Audit-friendly:** All calls logged centrally, not distributed
smithery -
Web scraper & crawler → clean Markdown with byte-level SHA-256 provenance + WARC archival for LLM/RAG knowledge bases
pypi MIT ★ 2 -
academic-data-huntergithub.com/Wack520/academic-data-hunterupdated this year
面向研究、竞赛与论文场景的可追溯数据采集与交付工具
MIT ★ 3 -
mcp-operations-context-demogithub.com/Nexarion-Technologies/mcp-operations-context-demoupdated this year
Read-only MCP context demo with bounded retrieval, source provenance, and conservative publication controls.
MIT -
Governed single-operator data fabric for agents and dashboards
Apache-2.0 -
MCP server for the Rijksmuseum collections with extended metadata, semantic and full-text search, provenance analysis, similarity comparisons and spatial queries.
MIT ★ 19 -
Governed expense-operations platform with deterministic policy execution, durable workflows, provenance, evaluations, observability, and MCP interfaces.
MIT -
Repertorium - legal knowledge infrastructure for AI: Polish and EU law corpus with citation graph, locators and provenance. Public interface docs (MCP, REST).
NOASSERTION -
lab_archives_mcpgithub.com/SamuelBrudner/lab_archives_mcpupdated this year
Chat with your electronic lab notebooks
MIT ★ 6 -
Strata is a notebook your coding agent can drive, and everything it computes stays.
pypi Apache-2.0 ★ 5 -
Explore sleep, training, mood and nutrition together using local records, traceable calculations and optional MCP tools for your preferred AI client.
AGPL-3.0 ★ 67 -
Open, MCP-native training-data foundry: turn permitted documents into traceable, quality-gated SFT and preference datasets.
Apache-2.0 ★ 1 -
Homebrew tap for permissionless financial-evidence CLI and MCP infrastructure
-
SwarmLabs: 30-domain scientific knowledge engine with 300K+ structured entities. MCP server + REST API + independent partner gateway (slb_ keys).
NOASSERTION ★ 1 -
mcp4rs-media-gallerygithub.com/MCP4RemoteSensing/mcp4rs-media-galleryupdated this year
Reproducible media-gallery pipeline for MCP4RS: query open remote-sensing sources, record provenance, and render auditable PNG/GIF examples for GitHub, Colab, and Hugging Face.
MIT -
Answers from authoritative public sources, with a citation for every number.
Apache-2.0 -
A fact store for agents, on Postgres: registered attributes and values, every write a transaction with its actor and evidence.
pypi MIT