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.
-
thuban-mcpupdated this year
MCP Server for Thuban AI Code Verification — let AI agents scan, fix, and verify code quality, with Thuban Shield gating every write and command execution
npm MIT -
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 -
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 -
@appcellent/supaseogithub.com/appcellent/supaseoupdated this year
MCP Server for SEO content creation with keyword research, content writing, image prompts, and quality checking
npm MIT -
Read-only substation and utility telemetry through IEC 60870-5-104, DNP3 and IEC 61850 MMS. Governed MCP tools for point values, quality and shared Industrial-AIOps diagnostics; no control-direction writes. Native dependencies and verified device coverage vary by platform.
pypi MIT ★ 3 -
lorem-mcpactive
MCP server for Lorem, the design-first AI slide deck editor: read and write decks as code, run the full AI pipeline (outline → build → quality loop → agentic edit), generate imagery, and export native PPTX/PDF — connects to the hosted Lorem service.
npm SEE LICENSE IN LICENSE.md -
تمهيد — ground work for execution: turn a project description into a validated, execution-ready planning & handoff package for Claude Code. Relational package store (SQLite ⇄ canonical JSONL), MCP-only writes, schema-enforced quality gates, HTML review surface. Successor of Keystone.
MIT -
music-creation-enginegithub.com/mage0535/music-creation-engineupdated this year
AI-Powered Full-Pipeline Music Composition Engine — Multi-Agent Lyric Writing → Sheet Music (PDF/MIDI/MusicXML) → Demo Audio (MP3) → Quality Eval → Publish. Zero GPU required. AI coding agent native. / AI 驱动全链路音乐创作引擎 — 多Agent作词→乐谱→Demo→评估→发布。零GPU。AI智能体原生。
★ 3 -
Claude Code plugin: the Opus supervisor plans, specifies and reviews; cheap workers (DeepSeek & co. via 9Router) write the code in isolated git worktrees. Server-side verification, a review gate, and merge-back as one squash commit. Fewer tokens, same quality.
AGPL-3.0 -
Make your model serve faster on your GPU, and prove it. Skills for Claude Code, Codex and OpenCode, plus a CLI and MCP server: your agent picks and tunes inference engines, can write GPU kernels, and backs every number with client-timed benchmarks, anti-cheat gates and quality checks.
pypi Apache-2.0 -
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Cut agent token costs by finding code without reading the repo, then keep large codebases off the complexity wall: blast radius, tests to run, quality deltas as you write. Every guess labelled, every loss published. Paddle out with a map.
go Apache-2.0 ★ 2,544 -
bitogithub.com/claylo/bitoactive
Quality gate tooling for building-in-the-open artifacts
npm MIT -
MCP server for nonfiction writers - AI-powered manuscript assistant for research, structure, and quality control
npm MIT -
LLM 输出质量检查器:24 条规则、0-100 评分、CLI 与零依赖 MCP server
MIT -
Prose in, plain-language prose out: scores text against the FAA standard and rewrites it to the bar. HTTP + MCP, any OpenAI-compatible engine, one hardened container.
MIT -
66 agent skills, 13 role agents and 8 MCP servers for AI assistants that build software, review code, write, research, analyse data and do quant work. Open Agent Skills format, with tested standard-library checkers.
MIT -
Your agent writes bad Rust. This catches it.
npm Apache-2.0 ★ 23 -
An MCP guardrail that enforces architecture conventions while AI writes code.
MIT -
raysensegithub.com/RayforceDB/raysenseupdated this year
A structural X-ray for the codebases AI agents are writing.
cargo MIT ★ 14 -
AI design system scanner + mcp server. Scores repos 0-100, writes fix prompts. 30K+ npm downloads.
npm MIT ★ 65 -
MCP server and CLI that measures how your team actually writes tickets, then holds new ones to that. GitLab, Jira, GitHub. No model needed to measure.
pypi MIT -
draftmason-editor-mcpgithub.com/crawde/draftmason-editor-mcpupdated this year
MCP server for developmental book editing — character consistency analysis, plot structure evaluation, pacing metrics, dialogue quality scoring, and show-don't-tell detection
npm MIT -
Stops your AI coding agent from writing calls to functions that don't exist, before the edit lands. Deterministic, no LLM, no API keys.
go MIT ★ 2 -
Style and quality linter for Norwegian and English text - MCP server for agents, with TypeSafe's Jev as the judgment layer. Reports findings, never authorship verdicts.
MIT -
CodeLensgithub.com/Wolfvin/CodeLensupdated this year
AI-native static code intelligence CLI + MCP server — prevents collision, dead code, and security bugs before AI agents write code. 13 languages, SQLite graph model, zero LLM calls.
MIT ★ 1 -
AgentsMeristemgithub.com/Vector897/AgentsMeristemupdated this year
Lineage-native root-cause for any AI agent. When data breaks, AgentsMeristem walks the DataHub lineage graph to the real upstream cause, probes the actual data, and writes the finding back as a DataHub incident — running local as a 7B any agent can call over MCP.
Apache-2.0 -
Zero-dependency linter and gate that blocks AI-generated comment slop: multi-line narrative comments, changelog markers, step-numbered filler. Write-time plugin for OpenCode, Claude Code hooks, pre-commit, GitHub Action, GitLab CI, MCP server. RU+EN+DE+FR+ES detection.
npm MIT ★ 7 -
Your AI writes the code; Karajan governs how it happens: TDD-first method, cross-AI review on every commit and git gates that make a false green impossible. Works with Claude, Codex, Gemini, OpenCode and Aider, on the subscriptions you already pay for. MCP server included.
npm AGPL-3.0 ★ 42