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.
-
Local agency/runtime harness for ChatGPT Web: repositories, tasks, commands, validation, Git, skills/memory, observability, and opt-in computer control.
Apache-2.0 ★ 27 -
MCP files for the Metis FCA Handbook AI Harness. Evaluate applicability of FCA Handbook entries to any specified situation. Integrate with your AI Agents using MCP.
pypi MIT -
Claude Code plugin and MCP server that makes AI coding agents prove their work (tests, review, acceptance criteria) before they can commit or open a PR.
MIT -
Testers.ai CARBON Test Harness Litegithub.com/jarbon/carbon-lite/blob/main/mcp/README.mdno update data
Local, MIT-licensed AI test harness with 10 MCP tools and 11 prompts for risk-based test planning, focused testing, accessibility checks, evidence capture, screenshot maps and interactive HTML quality reports. Runs over stdio in one explicitly selected project. Your coding agent supplies AI and browser execution; CARBON records observed evidence and generates reports. No hosted backend, model API key or telemetry required.
smithery -
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 -
AIM — AI Maestro for the Harness platform. Your personal Harness Architect, powered by the Harness Adoption MCP server.
npm Apache-2.0 -
@godot-harness/mcp-servergithub.com/skillcap-studio/godot-harnessupdated this year
MCP server exposing Godot Harness tools for AI agent consumption
npm MIT -
Local, read-only MCP Server for analyzing HAR (HTTP Archive) files with AI agents
-
MCP server for invoice-harness: operate your self-hosted invoicing tool from Claude and other AI assistants.
npm MIT -
Harness-agnostic inter-agent proxy and Model Context Protocol (MCP) server for AI coding agents
MIT ★ 2 -
Give AI agents full access to the Harness.io platform — manage pipelines, deployments, cloud costs, chaos engineering, feature flags, SEI, and 125+ resource types through 11 MCP tools
npm Apache-2.0 -
Open source AI agent harness & agentic AI runtime in TypeScript. 6-phase state machine, 24 tools, human-in-the-loop permissions, MCP server, and composable agent APIs. Zero dependencies.
npm MIT ★ 2 -
Local AI development harness for FastAPI projects: version-aware manual sync, SQLite/FTS5 search, a FastAPI Claude Code Skill, and an MCP server.
npm MIT -
@andygo.dev/cakephp-harnessupdated this year
Local AI development harness for CakePHP projects: version-aware manual sync, SQLite/FTS5 search, a CakePHP Claude Code Skill, and an MCP server.
npm MIT -
Local AI development harness for NestJS projects: version-aware manual sync, SQLite/FTS5 search, a NestJS Claude Code Skill, and an MCP server.
npm MIT -
harness-engineering-mcpgithub.com/movebrickschi/harness-engineering-mcpupdated this year
Engineering Harness as MCP server + CLI: ship a complete software engineering governance kit (spec, skills, rules, templates, checks) to any AI IDE (Cursor, Claude Code, Codex) with one config line.
npm MIT -
Local AI development harness for Next.js projects: version-aware manual sync, SQLite/FTS5 search, a Next.js Claude Code Skill, and an MCP server.
npm MIT -
🧪 CSOAI GSPC: 22-axis AI governance measurement with Ed25519-signed receipts, corrections ledger, and Inspect AI integration. npm: csoai-gspc-mcp | pip: gspc-harness
Apache-2.0 -
Local AI development harness for a project's own documentation: SQLite/FTS5 (optionally hybrid) search over your docs, served to coding agents through an MCP server.
npm MIT -
Plugins for DeepSeek Harness (dsh). joint-memory: 4-layer, file-first long-term memory for any AI agent — zero deps, markdown as source of truth, MCP stdio, deny floors, backup + sha256 verify.
MIT ★ 1 -
Model-agnostic AI agent harness with durable structured memory (MongoDB Atlas Vector Search), an MCP server and a CLI. Published as the npm package aitl-mcp. B.Sc. thesis project, UMSNH.
MIT -
Production-grade multi-agent harness for SDD-BDD-TDD software development. RAG memory (BM25), Obsidian vault, MCP server, agent auto-generation. Compatible with Claude, Codex, OpenCode, Kimi, Qwen, DeepSeek, and any AI tool.
npm MIT -
Shared context for AI agents — structured harnesses from conversations, feedback, and decisions, queryable via MCP
npm MIT -
msxai-harnessgithub.com/vdom-1/msxai-harnessupdated this year
AI-driven MSX development and operations harness, featuring documentation organized via the Open Knowledge Format (OKF), automated build workflows, and direct agent-to-emulator communication via MCP to execute complex tasks.
MIT ★ 1 -
dev-harness-cligithub.com/bakr-bagaber/dev-harnessupdated this year
Agent-agnostic development harness for AI coding agents — gated phase pipeline with a next-step trajectory engine, built-in MCP server, craft skills library, and deterministic gate validation. Works inside Claude Code, Codex, Cursor, VS Code, and any MCP-
npm MIT -
Evidence-bound reverse-engineering harness for AI agents, served over MCP. Ghidra or IDA static analysis, a claim verifier that rejects claims without quoted evidence, Windows Sandbox runs for behaviour claims. Core edition, Apache-2.0.
Apache-2.0 -
The agent that built it never leaves. A source-aware harness for every AI-built app — source-mapped build plugins, an MCP daemon, and a runtime client that let the agent keep watching, listening, and fixing the app long after it ships.
npm MIT ★ 2 -
MCP Toolkit for Flutter AI Agent Driven Development (MCP/CLI + custom client side tools) - via closed feedback loop (visual & semantic snapshot) and high client side customization adaptable for any Flutter app. Nowadays it is often called as agentic harness.
npm MIT ★ 399 -
dsh-plugin-chatcutgithub.com/nigedazhima/dsh-plugin-chatcutupdated this year
Edit videos with AI inside DeepSeek Harness — 50 ChatCut MCP tools, one-time OAuth, auto token refresh
GPL-3.0 ★ 3 -
GatherThread 共序:本地 AI 编程 Agent 多人联机协作、实时共享上下文。Self-hostable collaboration for local AI coding agents, Codex Desktop connector & DeepSeek Harness plugin.
npm Apache-2.0 ★ 28 -
DeepSeek Harness ↔ WeChat bridge for the wechat-ai MCP server
GPL-3.0 ★ 1 -
DSH(DeepSeek Harness)自用小工具合集:Agnes AI 生图本地网关(多账号池 + 管理台 + MCP)、GitHub REST MCP 连接器
MIT -
@gatolim/tessera-cligithub.com/gatolim/tesseraupdated this year
Tessera CLI & MCP Server - State management harness for autonomous AI development
npm MIT -
AI coding harness: rules, skills, agents, workflows, hooks and MCP server for Kotlin, Android, Compose and KMP.
★ 1 -
Fork: where AI agents share improvements to their setups. Remote MCP server + Root's harnesses. Maintained by Root, an AI agent.
-
AI-powered healthcare front-desk agent built with FastAPI, Groq, and MCP, featuring deterministic safety guardrails, patient-message triage, and an evaluation harness for messages.
-
Harness security for AI agents, for SQL databases: a Lock of the Lock Family. PII-masked queries; connections and writes approved in lox run (CLI + MCP).
Apache-2.0 ★ 2 -
Harness security for AI agents, for RabbitMQ: a Lock of the Lock Family. Masked queue inspection; message reads and actions approved in lox run (CLI + MCP).
Apache-2.0 -
@zxz9988/dsh-wechat-bridgegithub.com/zxz9988/dsh-wechat-bridgeupdated this year
DSH 插件:把手机微信(腾讯 iLink/ClawBot 官方协议)桥接到 DeepSeek Harness AI 助手 | DeepSeek Harness WeChat bridge plugin: connect WeChat to DSH AI via Tencent iLink/ClawBot — streaming replies, QR login, cron jobs, web fetch (MCP)
npm MIT -
天正建筑 AI 插件 · T20/T30 天正建筑 MCP connector for DeepSeek Harness — 让 AI 直接生成真天正对象:墙体、门窗、轴网、柱、楼梯、阳台、天正文字
NOASSERTION -
DSH 插件:把手机微信(腾讯 iLink/ClawBot 官方协议)桥接到 DeepSeek Harness AI 助手 | DeepSeek Harness WeChat bridge plugin: connect WeChat to DSH AI via Tencent iLink/ClawBot — streaming replies, QR login, cron jobs, web fetch (MCP)
npm MIT -
The persistent memory and coordination graph for AI agents (MCP, DeepSeek Harness, Claude Code, Cursor)
AGPL-3.0 ★ 1 -
DSH 插件:把本机 DeepSeek Harness 暴露成 JSON-RPC / MCP 接口,让本地其它 AI agent 像子智能体一样调用它 —— 选工作区、指定模型与推理等级、下发权限预设,并可在设置页查看实时状态。
MIT -
Hub for EVE Map Assistant integrations — connect EVE Static Map Planner to Codex, DeepSeek Harness, and other AI agents through MCP.
★ 1 -
DSH 插件:一键接入 mcp-unity,让 AI Agent 直接操控 Unity 编辑器(34 个工具) · One-shot mcp-unity integration for DeepSeek Harness
MIT ★ 21 -
Open-source IDE context harness and persistent memory engine for AI coding agents
npm MIT -
The adaptive AI harness for React Native — project-aware SDLC intelligence for any agent
npm BSL-1.1 -
A TypeScript-based Model Context Protocol (MCP) server for inter-session terminal orchestration, polyglot harness multiplexing, and AI agent control planes.
GPL-3.0 -
Roomcomm for DeepSeek Harness: your dsh agent talks to other AI agents in shared rooms (MCP tools + skill, zero setup)
MIT -
dsh-browser-controlgithub.com/kyo615/dsh-browser-controlupdated this year
Let an AI control a real visible Chrome browser via Playwright MCP, with a live view of every action inside the DeepSeek Harness GUI.
MIT ★ 8 -
DeepSeek Harness plugin: bridge the boss-agent-cli MCP server (BOSS直聘 AI Agent CLI) into DSH as native mcp__boss__* tools.
npm MIT -
dsh-code-checkeractive
DeepSeek Harness 代码全面检查插件:三步流水线(编译运行检查 → 功能完整性核对 → 真实用户模拟测试),自动把问题反馈给 AI 修复,可选用 GUI,并附带适用于 Trae/Qoder 等平台的独立 CLI 与 MCP 服务
npm MIT -
DeepSeek Harness (dsh) bundle that routes the harness through the OpenLLM gateway: an openllm provider on the in-box pi-ai adapter (via the local daemon gateway) plus the OpenLLM MCP server. Pure config; install OpenLLM and sign in first (see README).
npm MIT -
Machine-wide shared memory for AI agents (MCP) — WorkBuddy/Codex/Claude Code/Kilo/OpenCode/DeepSeek Harness
MIT ★ 1 -
Local MCP server for controlling and monitoring DeepSeek Harness sessions from Codex and other AI agents
MIT -
Your AI. Your Memory. — persistent memory engine for AI agents: typed memories with provenance, hybrid retrieval, reversible lifecycle, MCP/DeepSeek Harness plugin, SDK/CLI/REST.
MIT -
AiFP 记忆感知系统|MCP 服务,一套记忆全 AI 共享。面向中文的 Agent 感知记忆,支持叙事链、语义纠错、感知链图扩散。兼容 DeepSeek‑Harness、Claude Code、Cursor、Codex等全部 MCP 客户端,数据完全本地存储。
npm NOASSERTION ★ 3 -
edgesentinel-visionopsgithub.com/zja0011/edgesentinel-visionopsupdated this year
Jetson Nano edge AI vision Agent Harness: real-time video analytics, MCP tools, event evidence, DeepSeek online/offline, secure recovery
Apache-2.0 ★ 21 -
DSH 数据库 MCP 插件:把 DBHub 接入 DeepSeek Harness,让 AI 在对话里直接查询 MySQL / PostgreSQL / MariaDB / SQLite / SQL Server。
npm MIT ★ 2 -
DeepSeek Harness (DSH) 适配 EditaPlot: 通过本地 Origin/OriginPro 2021–2026b,让 AI 引导生成可编辑的科学图表。本包是 hang-jin/editaplot 的 Apache-2.0 派生作品。
npm Apache-2.0