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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). 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.
-
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 -
capture-truthgithub.com/hilmimuktitama/capture-truthupdated this year
Capture already-exported operational material into provenance-preserving evidence packs.
npm MIT -
BingguPack — local-first, evidence-backed memory/context pack framework with an installable Claude Code MCP server (stdio JSON-RPC). Python stdlib only.
pypi MIT -
Local, auditable market research for AI agents with exact evidence provenance, claim verification, counterevidence, MCP, and deterministic evidence packs.
MIT ★ 1 -
The delivery-evidence layer for Agent collaboration: verifiable delivery, acceptance, revisions and offline evidence packs (CLI/MCP/Python).
MIT ★ 2 -
@unfakable/mcpgithub.com/unfakable/mcpupdated this year
Model Context Protocol server for Unfakable document verification. Lets AI agents verify document integrity before acting on a file. Five tools: verify_file, verify_url, verify_hash, lock_file, get_evidence_pack.
npm MIT -
reflection-skills-mcpgithub.com/JulienAvezou/reflection-skills-mcpupdated this year
A protocol server that provides evidence-backed reflection frameworks, exercises, and prompt packs configurable by depth and engineering context.
MIT ★ 1 -
Local knowledge hub for research agents: source snapshots, evidence-linked claims, context packs, and MCP.
-
可追溯、可修订的本地 AI Agent 记忆运行时,支持 SQLite、CLI、MCP 与 Evidence Pack。
Apache-2.0 -
A local evidence workbench for researchers and students: search PDFs and notes, build cited AI context packs, and audit quotations. CLI, browser, and MCP.
MIT ★ 20 -
grounder-mcpupdated this year
Live web search, page fetch, and a token-capped cited evidence pack as MCP tools for local and cloud LLMs.
pypi -
R&D tax-credit evidence from your git history: a tax year's commits by component and person, and the commits that look like experimentation (reverts, unmerged branches, spikes, benchmarks), each traced to its commit, in a dated pack for your accountant. Local; no account, no LLM. Not tax advice.
MIT -
Open-source Python CLI and MCP toolkit for local Microsoft 365 and Google Workspace tenant audit evidence packs.
Apache-2.0 ★ 1 -
PAW browser-use component: viewport evidence, guarded input and reusable site packs. Chrome extension, local CLI and MCP. Development preview.
MIT -
Self-hosted governance platform for AI agents: identity, SSO/RBAC, approvals, signed execution grants, tamper-evident audit and Solution Packs.
AGPL-3.0 -
grounder-mcpgithub.com/rozetyp/grounder-mcpupdated this year
Grounder MCP - live web search, fetch, deep_search evidence packs, and agentic research for local & cloud LLMs. Thin client for grounder.dev.
MIT -
MCP server wrapping RSPCA Assured farmed trout (2025.07) and salmon (2024.05) welfare standards. Gap analysis, compliance scoring, audit-ready evidence pack generation, signed welfare attestations. From MEOK AI Labs.
pypi MIT License -
Mechanically validated frontend aesthetics for AI agents: 89-palette evidence library, OKLCH generation, WCAG/APCA contrast, color-blind-safe data colors, AI-slop detection, theme packs, W3C design tokens. Skill + MCP server.
MIT -
Governance layer for AI coding agents — model routing, security scanning, tamper-evident audit trail, JIT permissions. MCP server, 142 tools, 83 skill packs, 14 agent hosts, MIT licensed.
MIT -
MoContext - the local MCP server included with Mo-Search for Windows: full-text search, grounded evidence packs, and durable session memory over your own indexed files.
NOASSERTION -
QA for any running website: an MCP server for AI hosts (Claude Code, Antigravity, Gemini CLI, Cursor) and a standalone command, with test-account logins, real-browser actions, check packs, evidence, bug reports and approved Nashmi cards
npm MIT -
Flagship aquaculture crosswalk — one evidence pack satisfies ASC + RSPCA Assured + GlobalG.A.P. IFA Aquaculture v6. For UK retail-supplying farms hit by Sainsbury's 100% ASC + Co-op 2027 ASC commitments. From MEOK AI Labs.
pypi MIT License -
kawngraphgithub.com/xd7fx/kawngraphupdated this year
KawnGraph (كون قراف) — the Agent Context Universe. One project universe, every coding agent: evidence-backed Context Packs that give agents the map, not the repo. Local-first, no telemetry.
MIT ★ 1 -
The accessibility layer for AI coding agents, WCAG 2.2: static and rendered audits (light AND dark), contrast over images, blindfold usability testing, PDF/DOCX screening, caption quality, prefers-reduced-motion audit, evidence packs a human can sign. Zero deps
npm MIT ★ 7 -
Claude plugin for Bitsight Security Ratings — a zero-dependency MCP server wrapping the Bitsight REST API as 15 read-only tools, plus 16 skills that turn ratings into board packs, vendor decisions, remediation roadmaps, audit evidence and Indian regulatory incident notifications.
MIT ★ 1 -
@vitronai/alethiagithub.com/vitron-ai/alethia-mcpupdated this year
MIT-licensed MCP bridge to the Alethia runtime — the patent-pending zero-IPC E2E test runtime for AI agents. 2-5x faster than Playwright MCP. Signed evidence packs, EA1 fail-closed safety gate, WCAG + NIST 800-53 audits built in. Local-first, zero telemet
npm MIT -
varvegithub.com/varve-sh/varveupdated this year
Decision memory for AI coding agents. A local-first Go binary and MCP server: records decisions with evidence, scope, provenance and expiry, packs the relevant ones into each agent session within a token budget, and links commits back to the decisions that were in scope when they landed.
go Apache-2.0 ★ 9 -
contextfulgithub.com/Inferensys/contextfulupdated this year
Context Management Layer for Agentic AI. Graph-based knowledge context, SQLite index, advanced FTS5 lexical/BM25 search and cross-session live memory.
npm MIT ★ 6