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.
-
Universal Model Context Protocol (MCP) gateway for autonomous AI coding agents. Delegate pair-programming, refactoring, and code analysis to Claude Code, Antigravity, Codex, and Cursor with connection-scoped memory and zero tool bloat.
MIT -
MCP tool server for AI coding agents -- encoding-aware file tools, binary analysis, DAP debugger, SSH/SFTP, process memory, and more
MIT ★ 26 -
GitHub CLI tools for AI coding agents, served over MCP. A read server and an opt-in write server for PRs, issues, CI runs, jobs, commits, search, labels, projects, releases, and repo files, plus hooks that redirect raw gh bash calls to the tools. Packaged for Claude Code, Codex, and pi.
MIT ★ 1 -
Token-efficient MCP file, shell, SSH and ops tools for coding agents — bounded reads, dedup, spill recovery and span edits.
GPL-3.0 ★ 3 -
AI-powered development tools. 18 agents, 19 commands, 29 skills, 4 hooks, 1 MCP server for code review, research, design, and workflow automation.
MIT ★ 36 -
A paused, local-first code intelligence project that gives AI coding agents structured graph context, memory, and MCP tools.
MIT ★ 1 -
Roslyn for your coding agent — 88 MCP tools, 10–30× fewer tokens. Stops reading whole C# files: semantic navigation, compile-gated edits, safe renames, type-checked XAML. One dotnet tool install.
MIT ★ 3 -
Code intelligence CLI — function-level dependency graph across 34 languages, 34-tool MCP server for AI agents, complexity metrics, architecture boundary enforcement, CI quality gates, git diff impact with co-change analysis, hybrid semantic search. Fully local, zero API keys required.
npm Apache-2.0 ★ 100 -
The whole tools-for-agents kit in one install: nine zero-dependency MCP tools for coding agents — coordinate, read code, run safely, hold secrets, remember, read the web, read data, recall, see — and ghost, a self that persists across sessions.
npm MIT -
Persistent local memory for AI coding agents — Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. LongMemEval R@5 95.1%, LoCoMo 0.607, BEAM 1M 0.448. 74 MCP tools, 9 IDEs, 100% local.
MIT ★ 77 -
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys.
Apache-2.0 ★ 516 -
🔧 MCP tools for coding agents: include 40+ tools (file editing, search files and async shell,...) - with a SQLite audit trail.
npm AGPL-3.0 -
Shared FalkorDB context graph for coding agents: a ~200-token map before the first tool call, memory across sessions, edit claims between agents. 144 Claude Code runs: −25% tokens, −29% tool calls. No LLM calls, no Docker.
MIT -
Local-first developer tools for macOS that you share with your coding agent: code search, MCP servers, hooks and skills for Claude Code and Codex.
BSD-3-Clause ★ 2 -
Shared memory for Claude Code sessions. The plugin, hooks, MCP tools and CLI that connect your agents to Bellek.
Apache-2.0 -
Local Sovereign Multi-Agent Swarm OS & Cockpit for Autonomous AI Coding Agents. 28 Personas, 45 Core MCP Tools, Sub-10ms Trigram Search, Zero-Console Background Swarm. Official: https://uikode.com/acs
★ 21 -
Local, provider-agnostic MCP server for coding agents: 122 policy-governed tools for files, code intelligence, terminal, browser, and screen automation.
-
Clipboard tools for AI coding agents: a Bash MCP server with clipboard_copy and clipboard_copy_file, native backends with an OSC 52 fallback over SSH, and hooks that point agents to the tools instead of pbcopy. Plugin for Claude Code and Codex, package for Pi.
MIT -
claude-agent-org-toolsgithub.com/suguruooki/claude-agent-org-toolsupdated this year
Organization-theory based tools for Claude Code Agent Teams — 8 tools: Andon, Topology, RACI, OrgMemory, Workflow, QualityGate, Trace, Knowledge
npm MIT -
Better code search for coding agents: Claude Code, Codex, Cursor, OpenCode and Pi spend fewer tokens, tool calls and time.
MIT ★ 14 -
Coding power tools for AI agents. 18 deterministic MCP tools: code-graph search, SAST, blast radius, wire-level PII redaction, signed audit chain. Works with Claude Code, Codex, Gemini, Cursor.
★ 1 -
Human-approved engineering decisions for AI coding agents. Local-first MCP tools for Codex and Claude Code with evidence-based Git diff reviews.
Apache-2.0 ★ 11 -
midosgithub.com/MidOSresearch/midosupdated this year
Agentic OS that runs on any Linux — curated knowledge API for AI agents: MCP tools, skill packs, semantic search. Works with Claude Code, Cursor, Cline, Windsurf.
MIT ★ 8 -
Fast local code search, source reads, and smart block-clamped context for AI coding agents. VS Code Native Language Model Tools & MCP server backed by a shared Rust trigram cache (Linux, Windows, WSL).
MIT -
Your project remembers across coding agents. Compact, cited project memory for Codex, Claude Code, Cursor, and compatible tools.
npm Apache-2.0 ★ 3 -
intel-overdrivegithub.com/looney-tic/intel-overdriveupdated this year
Breaking changes, new tools, and security alerts for AI coding agents. 1100+ sources, one command to install.
npm SEE LICENSE IN LICENSE -
AI code governance for autonomous agents. Enforce architecture and business rules with AST intelligence, 54 MCP tools, and cryptographic audit trails.
npm Apache-2.0 ★ 4 -
context-enginegithub.com/JaimeJunr/context-engineupdated this year
Drop-in token saver for Claude Code & MCP agents — auto-rewrite hooks + 10-tool MCP server + BM25/PageRank repo maps + call graphs in 7 languages + local RAG. Single Rust binary, 100% local, zero APIs.
Apache-2.0 ★ 2 -
Rust-native context compression for Claude Code, Codex & MCP agents: filters & compresses noisy tool output (tests, diffs, logs, JSON, provider traffic) before it reaches the LLM — fewer wasted tokens, full evidence recoverable. Local-first, Apache-2.0. Pairs with Code Explorer.
Apache-2.0 ★ 4 -
Per-node design-implementation ledger: a Figma plugin, API, and agent tooling that tell coding agents exactly which design changes aren't built yet.
Apache-2.0 ★ 2 -
MCP server providing semantic Java code analysis for AI agents. Built on Eclipse JDT with tools for navigation, refactoring, search, and metrics.
npm MIT ★ 48 -
Machine-local, agent-writable knowledge base: an MCP server where coding-agent sessions record hard-won facts about tools and workflows, with git provenance
MIT -
Standalone code knowledge-graph MCP server + KG-only coding agents. Indexes TS/JS into SQLite; agents navigate and edit through graph tools alone.
MIT -
Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.
Apache-2.0 ★ 9 -
intel-overdrive-mcpupdated this year
Real-time intelligence for Claude Code — new MCP servers, tools, skills, and SDK updates from 1,000+ monitored sources. Paste the install command into Claude Code and your agent stays current automatically.
npm SEE LICENSE IN LICENSE -
Token-efficient code intelligence for AI agents — 66 MCP tools via tree-sitter AST, BM25F search, semantic search, and LSP bridge
npm NOASSERTION ★ 4 -
Terminal-first, local-first context engine for Codex and Claude Code. AST indexing, dependency graphs, MCP tools, Agent Skill, and an optional VS Code HUD.
MIT ★ 3 -
Multi-Agent Workspace Knowledge Graph — a cross-repo, contract-verified code-understanding MCP server (10 tools, 9 extractor forms, no fabricated edges)
MIT -
keshro-mcpgithub.com/jlewitt1/keshro-mcpupdated this year
MCP server for Keshro. Exposes plans, tasks, and project state as MCP tools for any MCP-compatible coding agent.
MIT -
Teach any coding agent the real s&box API: 17 source-verified reference files plus an 18-tool editor MCP toolset. Stops agents writing Unity code into Source 2 projects.
NOASSERTION ★ 4 -
Your coding agents forget between sessions. oboete remembers, on your machine: one Rust binary for Claude Code, Codex and Grok Build, with search, MCP tools and a local web page.
Apache-2.0 ★ 2 -
Reflect helps engineering teams see whether AI coding agents are actually improving delivery or just burning tokens, failing tools, and creating hidden debt
Apache-2.0 ★ 20 -
Cross-language-safe code-intelligence MCP for AI agents: 13 languages, family-gated call graph, blast radius, health grading, 8 facade tools, JSON envelopes, 100% local. Run miswire-audit on your repo.
MIT ★ 61 -
Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.
npm Apache-2.0 ★ 677 -
@mcpware/cross-code-organizergithub.com/mcpware/cross-code-organizerupdated this year
Cross-Code Organizer (CCO, formerly Claude Code Organizer) — manage AI coding tool configs across Claude Code, Codex CLI, and more. Memories, skills, MCP servers, commands, agents, rules, and hooks across global and project scopes
npm MIT -
5D Living Code Graph, 1-Call Subagent Context (chronos_explore), 4-Angle Review Audit, Surface Tracer, Universal Multi-Agent Synthesizer (Codex/Antigravity/Claude/OpenCode/Cursor) & Super-Mutant Gate (12 MCP Tools)
MIT ★ 2 -
Token-efficient context engine for AI coding agents. v2.23.0: token-killer pack — deep-forget (unlearning propagation), dangling-reference guard, MCP schemas-on-demand. 2462 tests, 43 MCP tools, Elastic-2.0.
NOASSERTION ★ 3 -
Static tools read dead binaries. DEA debugs live processes for coding agents—in ≤191 tokens per step (MCP + Antigravity Skill).
★ 2 -
Kern , The local, deterministic code-intelligence engine for AI agents. Fast AST indexing, precise dependency graphs, sandboxed execution, and MCP tools with zero network calls and zero telemetry.
MIT ★ 1 -
Modular Python coding and agent platform — LLM agents, graph RAG, static analysis, git ops, cloud and container deployment, all exposed as Model Context Protocol tools. uv-managed, with a zero-mock test suite.
MIT ★ 10 -
Remembra Relay: one agent stops, the next one already knows. Session handoffs built from git facts, for the next coding agent in any MCP tool, on any machine. MCP server + CLI. MIT.
MIT ★ 16 -
Roslyn-based MCP server giving AI agents deep semantic understanding of .NET/C# codebases — 67 tools for navigation, call graphs, diagnostics & code fixes, safe refactoring, code-quality auditing, test intelligence, DI graphs, and IL/external-assembly inspection.
npm MIT ★ 74 -
Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection.
npm MIT ★ 48,652 -
Veto MCP — gives every major AI CLI (Claude Code, Codex, Gemini, Cursor, Windsurf) a council of 49 specialist agents + 93 tools. Deterministic-first, self-learning, no API keys.
npm MIT ★ 4 -
xstitchgithub.com/raghavvbiyani/xstitchupdated this year
Cross-tool memory for AI agents. Stitch context across Cursor, Claude Code, Codex, Gemini CLI, Windsurf, Copilot, and 9+ AI tools. Preserves decisions, failed experiments & warnings across sessions. Zero dependencies, MCP + instruction files, BM25 relevance search. Never re-explain your work.
MIT ★ 3 -
Swift source, Apple guides and MCP tools for AI coding agents. Review iOS code, scaffold apps, and build/run/preview with Xcode Simulator.
npm MIT ★ 41 -
Supervise an AI coding agent (Claude Code / Codex / ACP) overnight and keep control: block forbidden tool calls before they run, gate 'done' on real tests, checkpoint work to git, cap spend, and get a morning report where every line is sourced. Local-first, no telemetry. Rust daemon + Tauri app + Claude Code plugin.
MIT ★ 1 -
cruxgithub.com/crux-cli/cruxupdated this year
Agentic Tool Manager for Claude Code
MIT -
Open-source, local-first long-term memory for AI coding agents: one MCP tool (recall) over a private local SQLite vault — zero cloud, zero vectors, zero background LLM calls, ~30 ms lookups. Apache-2.0.
Apache-2.0 ★ 1 -
ymcpgithub.com/xlsft/ymcpactive
YouTrack MCP server and coding-agent pipelines. Every built-in YouTrack MCP tool plus deletes, sprints, attachments, history and reports, signed in with your login and password. Pipelines hand YouTrack issues to Claude Code, Kimi or any ACP agent and open the pull requests. One-command install into Claude, Cursor, VS Code, Zed, Codex and more.
MIT ★ 2