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.
-
synaptic-stateupdated this year
Verifiable State Plane for Autonomous Agents
pypi MIT -
plane-mcp-servergithub.com/philipvanlewis/plane-mcp-serverupdated this year
Comprehensive MCP server for Plane CE — 51 tools for pages, assets, work items, modules, cycles, states, labels, members, and instance customization. Rich markdown editing, image uploads, client-side filtering.
MIT ★ 1 -
A semantic, transactional, replayable MCP control plane that lets autonomous AI agents operate Dwarf Fortress as a long-lived civilization. Safe-Rust phase-0B scaffold: MVCC world state, witnessed semantic plans, evidence-backed effects, deterministic replay.
go MIT ★ 27 -
Local control plane for AI agents to play Thronefall: structured state, harvest/build/upgrade, and unit posts on 127.0.0.1 — you keep the mouse.
MIT -
AI-agent oriented work order control plane for Laravel. Define typed work orders; lease, validate & approve items; enforce idempotency; track full audit trail. Ships a REST API + MCP server, strict state machine, partial submissions, and production-ready docs.
MIT -
Gravitas-Coregithub.com/ahmed-coding/Gravitas-Coreupdated this year
Gravitas-Core is a Python-native autonomous AI control plane and MCP (Model Context Protocol) server. It provides a persistent execution core for intelligent agents with task state management, memory persistence, terminal/browser engines, and recursive project intelligence—all designed for scalable AI-driven workflows.
MIT ★ 1 -
Local laboratory workbench with a source-independent spatial gateway - Newton or GPU-free Synthetic physics streams spatial state to a Three.js viewer over one declarative information plane shared by the Web app, lw CLI, and MCP.
-
aaa
npm MIT -
Comprehensive MCP Server for Plane with 76 project management tools including custom properties, sub-issues, relations, and transfer operations
npm MIT -
A deterministic control plane for agentic engineering workflows.
npm MIT