Best Codebase AI Skills & MCP Servers

Persistent intelligence infrastructure for agentic development

Lint your AI agent context files, MCP server configs, and session data against your actual codebase

Code-aware browser testing agent — reads your codebase, understands functionality, tests every element, reports with screenshots. Works as MCP server for Cursor/Claude Code or standalone CLI.

Repository scanner that builds a structural map of a codebase (functions, imports, exports, dependencies) and adds file descriptions of what the file does,, so anagentic AI can just read the map and know the project context

Mneme — the memory layer for your codebase. Knows the WHY, the WHAT, the WHERE-IT-BREAKS.

Complete codebase intelligence — loads treesitter, symbol, outline, callgraph, depgraph, refs.

Vexp — Context Engine for AI Coding Agents. Pre-indexes your codebase into a dependency graph and delivers ranked context to any MCP-compatible agent. 58% lower cost per task, 90% fewer tool calls (SWE-bench Verified). Works with Claude Code, Cursor, Copi

Reduce Claude Code token usage by 70-90% with cross-session memory and four-layer optimization: semantic codebase indexing, PostToolUse tool compression, turn summarization, and session consolidation. MCP server powered by Ollama — zero API calls, runs en

Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware review, and git-pinned decisions. MIT; no API keys or code upload.

MCP server for AI coding tools and agents. Provides semantic codebase context for Cursor, Claude Code, Codex, Copilot, Antigravity, and CLI workflows without requiring full file uploads.

AI codebase indexer and MCP server for Claude Code, Cursor, and Copilot. Pre-index your project into a compact graph and measure real token savings with `larkx bench`.

MCP proxy for Pharaoh — maps codebases into queryable knowledge graphs for AI agents. Enables Claude Code in headless environments (VPS, SSH, CI) via device flow auth.

MCP Server for persistent code indexing. Gives AI assistants (Claude, Gemini, Copilot, Cursor) instant access to your codebase. 50x less context than grep.

MCP server that gives AI agents (Claude, Cursor, Copilot) deep understanding of your codebase patterns, conventions, and architecture. Query patterns, security boundaries, call graphs in real-time.

Termyte eats dangerous agent actions before they eat your codebase

AI-powered MCP server for codebase navigation and LLM prompt optimization

Bounded conventions map and local-pattern discovery for AI coding agents. Local-first MCP server with AST-backed hybrid search.

MCP server for semantic code search and codebase analysis — Treesitter parsing, AST extraction, and embedding-based indexing for any LLM that supports MCP

Local-first AI-powered codebase analysis tool for stdio or HTTP transports using environment-supplied provider credentials.

Local-first MCP server giving AI coding agents fast, structured, and semantic context over any codebase.

MCP server & CLI: codebase index + cache for Claude Code, Cursor, OpenAI Codex, Google Antigravity/Gemini. Model Context Protocol tools (codetree_read, codetree_search, …), hooks on Claude, rules on other IDEs. Token savings, SQLite index, symbol search,

GraphQL-style codebase intelligence CLI — index, query, and analyze any codebase

MCP server that gives Claude, Cursor, and Gemini long-term memory across sessions. Your AI remembers your codebase, decisions, and preferences — across tools and machines.

Your AI agent has read your codebase but still can't safely change it. unerr is a local guardrail that hands the agent the call graph and your rules at the moment it edits.