code-intelligence MCP for AI coding agents
Serena is a Python MCP server that gives AI coding agents semantic, symbol-level code retrieval and editing/refactoring/debugging tools.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Self-contained SQLite-code-graph MCP server with many tools and audit/change-safety; choose it over the Python server if you want local audit and broad MCP command coverage.
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.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Knowledge-graph agent skill that also indexes docs/configs/PDFs; choose it when your context needs cover non-source files too.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Pre-indexed, auto-syncing graph for many agent CLIs; choose it when minimizing tokens is the main goal.
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
TypeScript contextual-understanding engine for agent CLIs; choose it when you want lighter integration without a standalone Python MCP server.
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
Knowledge-graph RAG with edit support; choose it when you want LLM graph reasoning over the monorepo rather than deterministic symbol tools.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
Persistent-index MCP server in a single static C binary with very broad language coverage; choose it when deployment size/speed dominate.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
Enterprise zero-setup local code intelligence with hybrid search/dependency/call graphs; choose it when scaling to very large codebases.
Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta.
MCP for symbol-level GitHub retrieval; choose it when you need to explore remote code rather than a local clone.
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
Go multi-language graph engine with CLI/MCP/API; choose it when you need one code-intelligence backend for agents and IDEs.
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/39MFHu3J5d
MCP/CLI code research tool spanning a repo and GitHub; choose it when evidence gathering across repos is the task.
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI
Graph-powered code-intel engine exposed through MCP/CLI; choose it for agent-side querying of a repository graph.
Graph-powered code intelligence engine — indexes codebases into a knowledge graph, exposed via MCP tools for AI agents and a CLI for developers.
Local Rust MCP/CLI code intelligence server; choose it when you want a lighter/smaller runtime than Python.
Local code intelligence MCP server and CLI for AI coding agents
Rust/SurrealDB-backed graphRAG MCP; choose it if you specifically want that stack, accepting a less active project.
100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced agentic code analysis tools through MCP for efficient code agent context management
MCP graph engine that compounds agent context; choose it when you want an incremental context graph for coding assistants.
Compounding Context for AI Coding Assistants — MCP graph engine for Claude Code, Cursor, Copilot, Gemini, OpenCode
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Local code-intelligence graph aimed at code-review and large-repo context reduction; choose it for review workflows rather than editing.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Code-search MCP for full-codebase context; choose it only when search/context is enough.
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
Embedded AST code-search CLI; choose it when a lightweight search command is all you need.
A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!
Local semantic-search and call-graph tool for agents; choose it for relationship search without an edit toolset.
Semantic Search & Call Graphs for AI Agents (100% Local)
Engineering-context retrieval/indexer; choose it when broad context lookup matters more than code modification tools.
Your entire engineering context, deeply understood
Rust single-binary semantic-search/knowledge-graph MCP; choose it for lightweight structural lookup only.
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in one Rust binary. Give Claude, Cursor, and any MCP client a deep understanding of your codebase.
These projects were analysed and named serena among their alternatives. The relationship is not symmetric — how serena rates them is a separate judgement, made when serena is analysed in its own right.
calls serena “drop-in MCP with semantic retrieval plus editing tools; choose if you need an agent IDE within the server.”
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
calls serena “Choose for an MCP-based semantic retrieval and editing toolkit instead of graph visualization.”
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
calls serena “if you need an MCP toolkit that also performs code editing, not just read-only graph queries”
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
calls serena “Use when semantic retrieval plus editing tools are more useful than a tree-sitter graph.”
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
calls serena “Choose when you need semantic retrieval plus code editing via LSP, not just context.”
Your entire engineering context, deeply understood
calls serena “Choose it if you also need agent-driven semantic editing, not just read-only research.”
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI