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.
-
AI code review agent MCP server. Reviews code like a kernel maintainer: blunt, technical, no sugarcoating. Detects bugs + OWASP Top 10 security vulnerabilities. 4 harshness levels. Anti-RLHF.
MIT ★ 5 -
Universal Model Context Protocol (MCP) gateway for autonomous AI coding agents: Anthropic Claude Code, Google Antigravity, OpenAI Codex, and Cursor Agent.
npm MIT -
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 -
@ambih/coding-agent-memoryactive
Memory for AI coding agents: the plans, tasks, decisions, rules and bugs your agents work through, recorded automatically, shared with your team, readable by every agent through MCP, with a dashboard.
npm Apache-2.0 -
Semantic code map and code graph MCP server for AI coding agents, powered by SCIP and Tree-sitter.
Apache-2.0 ★ 4 -
Stop vibe-coding bloat & token waste. Unified AI Coding-Agent & Spec-Driven Development (SDD) framework with AST semantic code reuse, progressive project memory (.ai/), and native MCP server for Claude Code, Cursor, Windsurf, Roo Code, Copilot, Zed, and A
npm MIT -
MCP server for AI coding agents — verifier gates, stop limits, and Verified Handoffs.
npm Apache-2.0 -
codebase-intelgithub.com/mutharasu/codebase-intelupdated this year
Your AI agent writes code — but does it know WHY your code exists? Decision provenance, quality contracts, and AI anti-pattern detection for coding agents.
pypi MIT -
Local codebase intelligence for AI coding agents: structural repo map, change-safety gates, MCP security receipts, and tamper-evident ChangeEvidence packets. Local analysis, zero API keys, no source-code egress.
pypi Apache-2.0 -
Open-source command center for governed AI coding agents with built-in onboarding, hard gates, MCP, and shareable run receipts.
npm Apache-2.0 -
Fast Rust MCP server for AST-aware code navigation: tree-sitter symbol indexing and token-budget pruning for AI coding agents
Apache-2.0 -
agent-rackgithub.com/lakpriya1s/agent-rackupdated this year
MCP server that runs CLI AI coding agents (Claude Code, Codex, opencode, Antigravity) as sub-agents from any MCP client — background sessions, terminal dashboard, structured code review
MIT ★ 3 -
Run, watch, and meter Claude Code, Codex CLI, Gemini CLI, OpenCode, and Kiro from one CLI. Normalized events, cache-aware token usage, cost accounting verified against each agent's own records, budget caps, OpenTelemetry gen_ai spans, Langfuse traces, and a live web dashboard + MCP server.
npm MIT ★ 2 -
Undo and verify what your AI coding agent did: rollback, test-proof gate and token trimming for Claude Code, Codex and OpenCode (CLI + MCP server)
Apache-2.0 ★ 4 -
Remote code intelligence and build server for AI coding agents via MCP: semantic navigation, safe refactoring, builds and tests on remote nodes.
Apache-2.0 ★ 7 -
Persistent memory, architectural decision enforcement, pre-execution safety hooks, and session handoff for Claude Code. MCP server plugin for AI coding agents.
MIT ★ 14 -
Open-source AI coding workbench in Rust: desktop app (GUI) + terminal TUI. Multi-session agents, plan and goal modes, built-in terminal and browser, diff review and Git commits, MCP client and server, skills, knowledge base and long-term memory. Works with OpenAI, Anthropic, Gemini, DeepSeek and more.
MIT ★ 21 -
Best AI Coding Agent Observability Tool 2026 - Self-Bench & Semantic Search
-
🧠 Python MCP Server for AST Codebase Intelligence, Symbol Extraction, Cyclomatic Complexity & Refactoring Analysis — compatible with Cursor, Claude Code, Windsurf & AI Agents.
MIT ★ 1 -
Code search that lets AI coding agents find the right files in fewer steps. Use the hosted endpoint or self-host, works with Claude Code, Copilot and Cursor via MCP.
MIT ★ 12 -
code-nexus-cortexgithub.com/ezain345/code-nexus-cortexupdated this year
Code Graph Nexus: AI-Powered Code Intelligence for Autonomous Agents 2026
-
Open-source, local code intelligence and dependency graph for cross-repository impact analysis. Map APIs, events, schemas, packages, databases, and ownership for AI coding agents via MCP.
NOASSERTION ★ 4 -
Coding agent memory — local-first memory and judgment for AI coding agents. One MCP server for every project; warns before repeating failed fixes.
pypi MIT -
AST-based code navigation for AI agents: static analysis and call graphs instead of vector search. Includes an MCP server (cdd-mcp).
MIT -
Token and context optimization for AI coding agents with smart compression, retrieval, recovery, routing, and MCP integrations.
MIT ★ 1 -
Secure Node.js execution sandbox for AI. Allows coding agents & LLMs to dynamically run JavaScript, install NPM packages, and retrieve results, facilitating code generation, testing, and interactive assistance. MCP-compatible.
★ 4 -
Local code intelligence MCP server and CLI for AI coding agents
Apache-2.0 ★ 760 -
Claude Code plugin for Fax for Agents: the hosted MCP server plus the fax-for-agents skill. Fax for Agents is a fax API, a hosted MCP server and SDKs built so AI agents can send and receive faxes. It is made by JSB Holdings LLC.
MIT -
Quorus AI: multi-agent rooms for Claude Code, Codex and opencode. Agents fix in their own git worktrees, review each other and push to your repo. MCP + CLI, MIT.
pypi MIT ★ 6 -
Open-source, local-first control plane for multi-model AI coding agents in VS Code and MCP: task DAGs, source intelligence, durable context and evidence-based review.
MIT ★ 12 -
coding-ethosgithub.com/paudley/coding-ethosupdated this year
Policy-as-code enforcement for AI agents with MCP, CEL, Git hooks, SARIF, and static-analysis guardrails.
pypi AGPL-3.0-only -
Project rules for AI coding agents. An MCP server gives Claude Code, Codex CLI and Antigravity the rules for the files they are about to edit; AST checks run in a git pre-commit hook and in CI (aegis check). Zero dependencies, Python 3.9+, Apache-2.0.
Apache-2.0 ★ 4 -
MCP server to orchestrate parallel AI coding agents (omp, Claude Code, any model) in Tern terminal tabs and git worktrees, from Claude Desktop or Claude Code.
MIT ★ 4 -
Review your AI agent's edits like tracked changes: marked in VS Code and the Markdown preview until you accept them.
MIT -
Claude Code Sub-agents Orchestrator - A powerful MCP server for orchestrating multiple AI sub-agents for complex task execution in Claude Code
npm MIT -
Hand-offs for AI coding agents (Claude Code, Codex, Cursor, any MCP client): a hand-off is refused while a question to that agent is still open. Plain files in git, no server.
MIT ★ 4 -
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 -
Verify AI-generated code with execution evidence — deterministic, local-first verification for coding-agent changes via a macOS app, CLI, and MCP server.
MIT ★ 1 -
One-command agentic workflow kit for AI coding agents: Workflow v3, a 25-agent squad, persistent memory, 70 Agent Skills and an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Oh My Pi and DeepSeek Harness. npx, Claude Code plugin or MCP Registry. Zero dependencies.
npm MIT ★ 3 -
Your AI agent writes code — but does it know WHY your code exists? Decision provenance, quality contracts, and AI anti-pattern detection for coding agents. 19 languages. MCP compatible.
MIT ★ 5 -
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.
npm NOASSERTION ★ 515 -
When several people code with their own AI agents, Teamping shows the team lead who is working on what, and stops an edit when a teammate's agent already holds that file. Plugin for Claude Code, Cursor, Antigravity and Grok.
MIT -
Project rules for AI coding agents (Claude Code, Codex CLI, Antigravity): MCP server, AGENTS.md bootstrap, AST checks, pre-commit hook and CI gate
pypi 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 -
Your AI agent's codebase map. Local-first, hybrid-search code graph for 51+ languages & formats. MCP server. 100% private.
MIT ★ 2 -
A precise local codebase map for AI coding agents: find, trace, and predict with file-line evidence.
pypi MIT -
Local code search and token-budgeted repository context for AI coding agents. Rust CLI and read-only MCP server for PR review, debugging, and agent handoffs.
MIT ★ 1 -
@aictx/memorygithub.com/aictx/memoryupdated this year
Local-first product graph for AI coding agents.
npm MIT -
A high-performance code intelligence graph for LLMs and AI agents. Sub-second structural queries, impact analysis, and cross-repo API contracts for autonomous coding workflows.
MIT ★ 10 -
knotgithub.com/dreygur/knotactive
Archived experiment: local code graph search and team learnings for AI coding agents (Claude Code, Codex, Cursor) as a Rust MCP server and CLI. Tree-sitter, BM25F and call graph ranking, benchmarked on Agent Retrieval Bench against Trail, CodeGraph, Serena and more. Abandoned: agents never used it.
MIT -
Multi_Agent_Python_Code_Auditorgithub.com/spranavk-03/Multi_Agent_Python_Code_Auditorupdated this year
Multi-Agent AI Code Auditor is a Python-based code review system that uses AST parsing, Bandit, Radon, and LLM-based agents to analyze code for security, quality, and complexity. The findings are summarized into a final report, saved as JSON, and benchmarked across multiple Python programs.
★ 1 -
Token-efficient code reading for AI coding agents: budgeted, symbol-aware, diff-aware reads over MCP.
MIT ★ 1 -
Policy-as-code enforcement for AI agents: MCP server, CEL policies, git hooks, SARIF, and static analysis guardrails.
AGPL-3.0 -
AI coding agent orchestrator — resolve GitHub issues end-to-end with isolated git worktrees, quality gates, and an MCP server. Works with Claude Code or Aider.
npm MIT ★ 1 -
Local decision ledger for AI coding agents — keeps why a choice was made and which paths are dead ends, and re-injects it after context compaction. Plain Markdown, zero dependencies, works across Claude Code / Codex / Cursor / Copilot / Gemini.
MIT -
Local-only Go static analysis engine with a built-in MCP server. Gives AI coding agents deterministic structural awareness: call graphs, impact analysis, symbol search, and more.
MIT ★ 231 -
Dependency graph, blast-radius analysis, and pre-commit safety gates for AI coding agents. MCP server.
npm MIT ★ 1 -
Using SDD? But Who checks that Specs out of the date? CatSpec Cares. Living specs linked to your code, with checks for TypeScript and C# and an MCP server for AI agents.
npm Apache-2.0 ★ 2 -
Shared project rules and memory for AI coding agents. Decisions, rules and failed approaches in one JEVMEM.md in your repo, read by Claude Code, Cursor and Codex, with a guard that checks Claude's commands before they run.
npm MIT ★ 150 -
agent-mux-mcpgithub.com/wowoyong/agent-muxupdated this year
MCP server for agent-mux — routes tasks between Claude Code and Codex CLI based on complexity, optimizing AI coding subscription costs
npm MIT