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 descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
SQLite-backed MCP server with FTS5 full-text search for truly infinite agent context. Session tracking, event logging, and paged retrieval for long-horizon tasks.
npm MIT -
Midasgithub.com/vornicx/Midasupdated this year
Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest. Python SDK + MCP server with source-traceable recall, belief revision, selective forgetting, and reproducible benchmarks.
pypi MIT ★ 14 -
Stateful task tracking CLI & Model Context Protocol (MCP) server for long-horizon agents
Apache-2.0 -
Four-layer memory substrate for long-horizon agents: write-gate admission, signed approvals, hash-chained ledger, revocable and portable.
MIT ★ 4 -
MCP Server implementation of AgentFold - Long-Horizon Web Agents with Proactive Context Management. v2.0 adds analytics, validation, quality evaluation, and performance benchmarking.
npm MIT -
Zero-error LLM execution via SPRT voting. Rust library and MCP server implementing the MAKER algorithm for mathematically-grounded error correction in long-horizon AI agent tasks. Research experiment based on arXiv:2511.09030
MIT ★ 5 -
🔬 Local SQLite-based AI research agent swarm with GOAP planning, multi-perspective analysis, long-horizon recursive framework, AgentDB self-learning, anti-hallucination controls, and MCP server. Goal-oriented with parallel execution. No cloud dependencie
npm ISC -
lemonade-benchgithub.com/mxmarchal/lemonade-benchupdated this year
Zero-vision, long-horizon AI benchmark for Lemonade Tycoon Deluxe 1.1.9. Includes a Wine-compatible DLL bridge, semantic Player MCP, OpenAI/OpenRouter agent runner, crash-safe tracing, compaction, and economic scoring. Bring your own legal game copy.
MIT -
Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eager AI Agents goodbye! Effective for: Coding, Ambiguous Tasks, High-Risk tasks
npm MIT ★ 506 -
Make your AI agents look pretty
pypi MIT ★ 3 -
Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.
Apache-2.0 ★ 403 -
dsh bundle for TSM / DLR: MCP semantic gateway to tsm-core-dlr, the scenario-independent paradigm skill, the TSM status overlay, and the agent rules (AGENTS.md). Assembly face = preset-dlr.
npm MIT -
An AI agent plays Baldur's Gate 3 on Linux through a Lua mod and an MCP server, seeing only what a player sees. Includes a model benchmark and a playthrough app.
MIT ★ 34