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.
-
Drop-in HTTP proxy for Ollama with priority queuing, per-client auth, and model-aware failover
MIT ★ 3 -
context-guardian-mcpupdated this year
MCP server + proxy that cuts cloud LLM costs 36-42% by indexing context locally with Ollama and giving agents precision retrieval tools instead of raw dumps.
npm MIT -
hybrid-model-switcher-mcp-for-Claude-Desktopgithub.com/berry1200/hybrid-model-switcher-mcp-for-Claude-Desktopupdated this year
MCP routing proxy for Claude Desktop — local Ollama model switching via LiteLLM
MIT ★ 3 -
One interface for every coding agent: Claude Code, Codex, OpenCode, Antigravity, pi and Ollama. MCP bridge, rate-limit fallback, OpenAI/Anthropic-compatible proxy, live dashboard.
npm MIT ★ 3 -
modelroutegithub.com/cognis-digital/modelrouteupdated this year
Local model router / proxy across Ollama, vLLM, and cloud with fallback
NOASSERTION -
A token-optimization and memory layer between agent and model: dedups tool output, distills old turns, prunes to a token budget. Proxy, MCP server, CLI, or library
Apache-2.0 ★ 1 -
Hong Kong Labour Department Job Listing Scraper & AI Agent
MIT -
Self-hosted AI workspace that compresses prompts before they leave your machine — 79% fewer tokens, measured. Drop-in gateway for Claude Code, Cursor, Aider and any OpenAI/Anthropic client, plus an MCP server. Free, MIT, zero telemetry.
MIT ★ 3 -
openballastgithub.com/openballast/ballastupdated this year
Ballast: pull a quantized knowledge corpus (or build your own) and ground any local model — OpenAI proxy, MCP server, model profiling, and a three-arm grounding benchmark.
pypi Apache-2.0 -
skill-forgegithub.com/gtm-k/skill-forgeupdated this year
Local-first skill runtime + visual manager for local/open LLMs — source agentskills.io skills and inject the right one at runtime into LM Studio, MCP hosts, and any OpenAI-compatible proxy.
Apache-2.0 -
veugithub.com/guhttps/veuactive
Esconde dados pessoais e segredos (nomes, e-mails, telefones, CPF, CNPJ, documentos de mais 21 países, cartões, chaves de API, senhas) antes de o texto chegar à IA e devolve os dados reais na resposta. Página web, painel, extensão, Python, JavaScript, proxy e MCP.
MIT -
token-scoutgithub.com/jackccrawford/token-scoutupdated this year
For OpenClaw, Hermes and more. Find free and low-cost inference (LLM models). Use them directly. Provides both a CLI and MCP server that knows which free-tier LLM APIs exist, which ones you have keys for, and which one fits your task. Returns endpoints so can you call models directly. No proxy, no middleware, no latency tax.
MIT ★ 9