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.
-
Session Intelligence MCP Server - Lean meta-tool pattern with 95% context reduction
MIT -
Code intelligence for agents: find the code that matters and keep your context window and tokens lean.
Apache-2.0 ★ 163 -
Fast, lean MCP server that lets Claude Code and Codex ask your Google NotebookLM notebooks questions: cited answers, without loading your docs into context.
★ 1 -
claude-code-sshgithub.com/hunchom/claude-code-gitupdated this year
MCP server giving Claude Code 51 typed SSH tools across your server fleet. Pooled connections, per-user gated, context-lean output.
npm MIT -
claude-code-sshgithub.com/hunchom/claude-code-sshupdated this year
MCP server giving Claude Code 51 typed SSH tools across your server fleet. Pooled, gated, context-lean — stop being the middleman.
MIT ★ 2 -
Generate, preserve, and verify lean AGENTS.md, RUNBOOK.md, and machine-readable repo context for AI coding agents.
MIT ★ 5 -
Lean Ghidra MCP server for clean-room reverse engineering: indexed decompilation, small agent context, dirty/clean spec separation.
MIT ★ 1 -
Connect Claude Code to AgentsChat — AI Agent social network. Core tools stay lean while extended tool groups load on demand for lower token overhead and cleaner role-specific context.
npm Apache-2.0 -
agentchat-mcpgithub.com/swswordholy-tech/iosdevupdated this year
Connect Claude Code to AgentChat — AI Agent social network. Core tools stay lean while extended tool groups load on demand for lower token overhead and cleaner role-specific context.
npm MIT -
LeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: CLI, MCP, hooks and supported proxy paths.
pypi Apache-2.0 ★ 3,951 -
LeanKG: Stop Burning Tokens. Start Coding Lean.
Apache-2.0 ★ 222 -
linear-mcp-leangithub.com/wiklob/linear-mcp-leanupdated this year
Self-hosted MCP server wrapping Linear's GraphQL API with response-shape control — lean reads, minimal write acks, drop-in tool names.
npm MIT -
Self-hosted Linear MCP server with response-shape control — lean field-trimmed reads, minimal write acks, drop-in tool names. Built for token-frugal LLM agents.
npm MIT -
A token-lean MCP memory server: a knowledge graph your AI agent can search without reading the whole thing. Drop-in replacement for @modelcontextprotocol/server-memory.
npm MIT -
A token-lean MCP memory server for AI coding agents: a knowledge graph your agent can search without reading the whole thing. Drop-in replacement for the reference memory server.
npm MIT ★ 3 -
Index codebases into a local knowledge graph to provide accurate context for AI coding tools through a direct MCP server connection.
★ 1 -
Fast Lean 4 proof feedback for coding agents. CLI, Python library, and MCP server with warm LeanInteract sessions and cached env reuse.
MIT ★ 7 -
Deterministic strategic-planning frameworks (SWOT, 4Ps, Lean Canvas, decision matrix) as a local MCP server. No API keys, no network calls. Pro unlocks 8 more frameworks.
npm MIT -
A stand-alone Mathematica-style symbolic math system: a from-scratch Rust kernel (exact arithmetic, pattern matching, CAS) plus a Python web notebook with SVG plots, an HTTP API, and an MCP server. No external crates or pip packages.
MIT -
Token-lean MCP server for Figma: read designs as compact text, render only on demand
npm MIT -
Ultra-lean, scope-aware code search for LLMs and developers
npm Apache-2.0 ★ 1 -
Lean Gmail MCP server with auto authentication support (maintained fork of GongRzhe/Gmail-MCP-Server)
npm MIT -
Token-lean browser MCP server: test local apps freely, browse other sites only after the user allows them
npm MIT -
Fast, token-lean MCP server for Apple Mail on macOS — reads Mail's local index directly, zero idle CPU
MIT -
contextive-mcp-servergithub.com/BjornMelin/contextive-mcp-serverupdated this year
A lean, multi-provider MCP server that unifies LLM access. Token-efficient tools, composable workflows, and multi-model routing via Vercel AI SDK. Works with Claude, ChatGPT, Cursor & more.
-
Token-lean, ref-stable, privacy-first browser protocol for AI agents (core + Playwright/CDP driver + MCP server).
npm MIT -
mailpouch — lean, permission-gated MCP access to Proton Mail via Proton Bridge, with up to 86 tools, resources, and prompts.
npm MIT -
Token-lean MCP server for the Pixabay image & video API — slim results, 24h cache, free pagination, download-to-server with attribution. Stdlib-only core.
MIT ★ 1 -
Unofficial lean MCP server for Yandex Tracker: 9 tools, ~1.2k tokens of tool definitions (official: ~24.8k), compact answers, one-command setup.
MIT -
mare-browser-mcpgithub.com/emadklenka/mare_browser_mcpupdated this year
Lean, LLM-first browser automation MCP server. Gives Claude, OpenCode, or any MCP client a real browser to navigate, interact with, and debug web apps.
npm MIT -
Deterministic strategic-planning frameworks (SWOT, Porter's, PESTLE, OKRs, Lean Canvas) as a local MCP server. 12 tools, no API keys, no network calls. Works in Claude, Cursor, OpenCode.
npm MIT -
🦛 A hippocampus for your AI. Long-term memory for Claude & any MCP client, stored as Markdown in your own GitHub repo: hybrid semantic search, knowledge graph, auto-memory, compaction-proof, token-lean.
MIT ★ 1