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.
-
Your AI agents know the code. They don't know the company. Free, local CLI and MCP server that imports your team's decisions from Jira, Confluence, Linear, Notion, Slack, Teams, Zoom, GitHub, GitLab, git history and repo docs, and checks your coding agent's change against them before it edits.
npm MIT ★ 18 -
Structured AI memory layer. A single source of truth for what your agent knows across conversations. :)
pypi MIT ★ 10 -
agent_recordergithub.com/EdytaKucharska/agent_recorderupdated this year
Know what your AI agent actually did. Agent Recorder logs every tool call across your MCP servers — locally, to SQLite, without capturing prompts or reasoning. Debug failures, audit runs, and stop guessing.
MIT ★ 9 -
Know your agent stopped working before your customer does. Alerts on missing activity, failure streaks and undelivered messages from a JSONL event log. CLI, library, and MCP server. Zero dependencies.
npm MIT -
A senior developer for your AI agent: read-only MCP servers that know your legacy .NET code and your SQL Server database, with a citation for every answer.
NOASSERTION -
Give every agent your team's brain on day one. The memory layer for AI agents. Everything your team knows. Cited, and always up to date.
NOASSERTION ★ 103 -
Your vault is what your agents should know about you, shared by every agent you connect. End-to-end encrypted. Local MCP bridge to Decoy.
npm MIT -
Point at your running Vite app, write what should change, let your coding agent do it. Knows the exact .vue file and line. MCP + Vite DevTools, built on devframe.
npm MIT ★ 1 -
Know what your AI agents cost, per project, without your prompts leaving the machine. CLI, MCP server and CI gate. Zero dependencies, offline.
npm MIT ★ 1 -
4DA knows every dependency on your machine and tells you — and your coding agent — what changed and exactly what to run. Privately, locally.
NOASSERTION ★ 2 -
Find GitHub projects that fit you, using what your coding agents already know about you.
pypi MIT ★ 7 -
codebase-intelgithub.com/mutharasu/codebase-intelupdated this year
Your AI agent writes code — but does it know WHY your code exists? Decision provenance, quality contracts, and AI anti-pattern detection for coding agents.
pypi MIT -
Click any element in Chrome. Your coding agent knows exactly what you mean, and which file to edit. MCP, Claude Code, Codex.
MIT ★ 1 -
What your agents know about your system: a 114-language code graph, memory and knowledge, in a local CLI and MCP server (33 MCP tools, 3 domains). Holds your data sources' structure, never their rows.
cargo MIT ★ 2 -
Know your agent works before your customers find out it doesn't. Stateful fake Zendesk, Slack, Linear and HTTP backends (HTTP + MCP) for AI agent evals that block bad releases.
npm Apache-2.0 -
Give your agent a body: Embodify lets it control robots directly and become your embodied agent. Your best embodied agent is your favorite agent — with its memory, its tools and everything it knows about you. Works with Codex, Claude Code and any other agent that supports MCP and skills.
pypi Apache-2.0 ★ 5 -
The brain for AI agents. One place to write what your agents know — served over MCP, readable and correctable by you.
MIT ★ 1 -
Your AI agent writes code — but does it know WHY your code exists? Decision provenance, quality contracts, and AI anti-pattern detection for coding agents. 19 languages. MCP compatible.
MIT ★ 5 -
probe-codegithub.com/matiasxth/probeupdated this year
Codebase intelligence for AI agents. Index your code at function-level, query what matters, know what breaks.
npm MIT -
kyp-memgithub.com/kdbalagency/kyp-memupdated this year
Know Your Project — Persistent knowledge base for AI agents. MCP-powered with wikilinks, backlinks, auto-learning, and neon web UI.
pypi MIT -
MCP-first infrastructure & agentic-AI cartography — install once, every AI agent knows your system landscape. Read-only discovery exposed over the Model Context Protocol.
npm MIT -
groundprobegithub.com/aureliocpr-ctrl/groundprobeupdated this year
Runtime epistemic profiler for AI agents. Tag every claim as grounded, inferred, speculative or meta — measure how much your agent actually knows.
MIT -
Agent memory that knows when it's wrong. Catches facts that have gone stale, retires them, and never leaves your laptop. Local-first, MCP-native.
MIT -
Collective intelligence for agents. Stop your agents from guessing how to use the web. Let them know what to do. Think; hive mind. Let's make the open agent internet.
go MIT ★ 1 -
sourcebookgithub.com/maroondlabs/sourcebookupdated this year
Generate AI context files from your codebase's actual conventions. Not what agents already know — what they keep missing.
NOASSERTION ★ 3 -
squints-mcpactive
Point at an element in the browser with Squints, and your coding agent knows exactly which one you mean
npm MIT -
Trade GIFs with your coding agent, like with a teammate - and let it get to know you. MCP server + Claude Code plugin + VS Code panel.
npm MIT -
kyp-memgithub.com/adhithya-karthikeyan/kyp-memupdated this year
Know Your Project — Persistent & Session level knowledge base for AI agents. MCP-powered with wikilinks, backlinks, auto-learning, and neon web UI.
npm MIT -
Grill's record of what you know, for any AI agent: weak spots, misconceptions, questions to ask, and a place to record your answers.
npm MIT -
deploypilot-mcpgithub.com/marilynceo/deploypilot-mcpupdated this year
Inspect, manage, and roll back deployments across GitHub Actions, Vercel, Netlify, and Railway u2014 directly from your AI agent. One tool to know what shipped, when, and whether it's healthy.
-
valentinegithub.com/80x-djh/valentineupdated this year
Know before you walk in — a read-only AI agent that checks if anyone at your fund has talked to a founder before. CLI + MCP. Attio/Affinity.
MIT -
One memory for every AI agent on your machine: tell one, and the rest know. A gate, not a store — it decides what gets in, and writes down why.
npm MIT -
Deterministic, local impact analysis for coding agents. Know what your code change will break before you make it. Code graphs for Python, TypeScript, Go, Rust and Java across many repositories; confidence-graded answers, MCP + CLI.
Apache-2.0 ★ 1 -
Your local AI agents talk to each other. You should know what they're saying. A terminal-first guardian that mediates every MCP call, scores it for risk, and asks before anything dangerous happens.
MIT ★ 11 -
Cross-repo infrastructure memory for coding agents — knows who else depends on an artifact before you change it, and watches your pins for CVEs.
pypi MIT ★ 4 -
Give your AI agent ears that know who's talking: a local, hands-free voice front-end that names speakers. Works with OpenAI, OpenClaw, Hermes Agent, Ollama and any MCP client.
Apache-2.0 -
Grow on Laravel. Run it with AI. A CMS with an admin editors already know — Filament or Nova, WooCommerce, ACF, MCP for AI agents — and a way in for your WordPress site. Questions, ideas and bug reports.
-
Long-term memory for agentic tasks. It tells you when it doesn't know. An MCP server for Claude Desktop and Claude Code: hybrid retrieval over your own markdown memories, with an explicit absence verdict instead of a least-bad match.
npm MIT -
Curltale AI is a hippocampus for AI agents: it grounds them in an ontology and a verified knowledge base, so they know what your data means and what's true. Docs and a public docs MCP at kb.curltale.com.
MIT -
Your agent should already know what you're looking at. A local context harness for the browser: it reads the page and how you got there, and hands it to Claude Code, Cursor or any MCP agent.
MIT ★ 1 -
privacypage-mcpno update data
Give your AI agent the power to generate privacy policies, terms of service, EULAs, cookie policies, and disclaimers — while it builds your app. Every app shipped from Cursor, Lovable, Bolt, or v0 eventually needs legal documents — the App Store and Play Store require a privacy policy, GDPR requires cookie disclosures, and users expect terms of service. This MCP server lets the agent that's building your app generate those documents in the same conversation, filled in from what the agent already knows about your app: its name, platform, the data it collects, and the SDKs it uses.
smithery -
Yinli AI (引力AI) for DeepSeek Harness — the SI (Social Intelligence)-native human connection and instant-messaging network. Put people first; let your Agent apply social intelligence to discover and connect you with people you do not know through MCP.
npm MIT -
Learn what you don't know yet from the code your AI agent writes. Free and secure by design, for Claude Code, Claude Desktop, Gemini CLI & Codex — one lesson at a time.
npm AGPL-3.0 ★ 5 -
Squish gives AI agents calibrated recall confidence (ECE 0.055) and honest abstention — the only memory runtime that tells your agent how much to trust each recollection, and says I don't know when nothing clears the bar. Local-first, MIT, npm install in 30s.
MIT ★ 12 -
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 -
Stops your coding agent from deleting, leaking or dropping things. Records everything else.
npm MIT -
Writ MCP server — give an MCP-capable runtime (Claude Code, etc.) a verifiable agent passport. Tools to check status and present signed X-Passport assertions for real economic actions.
npm MIT -
@clearagent/mcpgithub.com/clearag3nt/mcpupdated this year
Model Context Protocol (MCP) server for ClearAgent API — exposes OFAC/BSA compliance screening and agent credentials management as tools for Claude Desktop, Cursor, and other MCP clients
npm MIT -
MCP security trust layer. Scan packages, inspect repo MCP dependencies, generate Policy Gate setup, install the workflow directly, check exposure, and query abuse data.
npm MIT -
The reverse CAPTCHA: a test only AI can pass. Agents prove they're AI and who sent them; websites let the right ones in. CLI, MCP server, widget, verifiers (Node/Python/Go), protocol spec and an AI-vs-human benchmark.
npm MIT ★ 2 -
KYA Brasil as a local MCP server (stdio): verify that an AI agent acts for a Brazilian company (e-CNPJ) or person (e-CPF), check an action against its mandate, verify credentials and sub-agent delegation chains offline. No key needed for the free and offl
npm MIT -
booklibgithub.com/booklib-ai/booklibupdated this year
Detects what your AI doesn't know about your project and fixes it. Post-training gap detection, runtime context injection via MCP.
npm MIT ★ 40 -
Vitrus-Archivegithub.com/ahmetvural79/Vitrus-Archiveupdated this year
your glass-box company brain — tells you what it doesn't know (deterministic gap analysis). MIT core · MCP · PGLite→Postgres.
Apache-2.0 ★ 13 -
Persistent AI memory with crossover — your AI at home shares the same memory as your AI at work. What one LLM learns, all your AIs know. Memory + PKM for Claude, GPT, Gemini & local models. MCP-native. (Engine stays private.)
npm MIT -
Know what breaks before you change Salesforce. Ask your AI about your org: where a field is used, what runs on save, which Apex is dead, who can see what. Offline, read-only, cited. Open source (MIT).
npm MIT ★ 3 -
Tell one AI, they all know: one memory on your Mac, shared by Claude Code, Codex and Cursor over MCP.
npm MIT ★ 2 -
Know what changed inside your Electron release: diff two builds for IPC, preload, windows, fuses and hosts, with file:line. CLI, CI gate, MCP server.
npm MIT ★ 10 -
Free up space on your Mac without fear. Disk cleaner that knows what recreates itself: folder catalog, MCP server docs and release notes.
mcpb NOASSERTION ★ 1 -
The code graph that knows which tasks and tests implement your code — MCP server, CLI, and HTTP tool surface over a local SQLite or Neo4j graph. 9 languages, 135 LLM-callable tools, read-only by default.
MIT -
Give your AI a body, hands and eyes in a Minecraft world, and the know-how to build like a pro. An MCP server with 39 tools + a building skill; works with Claude, Gemini, Codex and local models (Ollama).
MIT ★ 1