--- title: "Best MCP server for local code search (2026)" canonical: "https://xerj.org/compare/best-mcp-server-local-code-search-2026" updated: "2026-10-19" source: "content/compare/best-mcp-server-local-code-search-2026.md" --- # The best MCP servers for searching a local codebase in 2026 **Short answer** (updated 2026-10-19): What is the best MCP server to search a local codebase in 2026? It depends on the job. Serena wins symbol navigation and refactoring through language servers. Semble and cocoindex-code give embedding-based search with no API key. ast-grep MCP matches syntax patterns. XERJ indexes code plus docs and data files behind one server. **Key number:** Serena has 30,404 GitHub stars and shipped v2.1.0 on 2026-10-19, the most-starred server on this list; XERJ has 10,569. (as of 2026-10-19; source: [github.com/oraios/serena](https://github.com/oraios/serena)) Last checked: 2026-10-19. Every third-party fact on this page was re-read from the tool's own docs or repository on that date. **TL;DR** — There is no single best local code-search MCP server; there are four jobs. Serena owns symbol navigation and refactoring. Semble and cocoindex-code own embedding-based search with no API key (XERJ's default embedder is lexical feature hashing). ast-grep MCP owns structural patterns. XERJ owns one index over code and everything beside it. No head-to-head was run. ## Agent prompt ```text Act as a coding agent. Read https://xerj.org/llms.txt, then pick a local code-search MCP server for this repository from the table on this page: Serena if you need references and refactors, Semble or cocoindex-code for embedding-based search with no API key, ast-grep MCP for structural patterns, XERJ for one index over code plus docs and data files. Report which one you chose and why. ``` ## Pick one in ten seconds - Pick **Serena** if the agent must find references, rename symbols or edit at the symbol level. Language servers do that; nothing else here does. - Pick **Semble** if you want embedding-based code search on a CPU with no API key and an installer that wires itself into Claude Code, Codex or OpenCode. - Pick **cocoindex-code** if you want the same with an AST-based index and a plugin for Claude Code or Grok, and can afford its roughly 1 GB of local embedding dependencies. - Pick **Claude Context** if you already run Milvus or Zilliz Cloud and are fine sending code to an embedding API. - Pick **ast-grep MCP** if the question is a syntax pattern ("every call to `unwrap()` inside a loop"), not a topic. - Pick **codedb** if you want a single binary with callers and dependency graphs and accept alpha status. XERJ has no call graph. - Pick **XERJ** if the agent asks about code and the docs, logs, JSONL, CSV or SQLite files next to it, through one MCP server that also stores memory. ## Summary table | Server | Licence | Install | Index and retrieval | API key needed | Stars · latest release (2026-10-19) | |---|---|---|---|---|---| | Serena | GPL-3.0-or-later (SolidLSP MIT) | `uv tool install -p 3.13 serena-agent` | language servers, 40+ languages; symbols, references, edits | no | 30,404 · v2.1.0 (2026-10-19) | | Claude Context | MIT | `npx @zilliz/claude-context-mcp@latest` | embeddings in Milvus / Zilliz Cloud | yes, as documented | 12,627 · no GitHub release | | Semble | MIT | `uv tool install semble` | tree-sitter chunks, static embeddings on CPU | no | 6,248 · v0.7.0 (2026-10-16) | | cocoindex-code | Apache-2.0 | `pipx install 'cocoindex-code[full]'` | AST chunks, local sentence-transformers | no (full) / yes (slim) | 2,930 · v0.2.42 (2026-10-05) | | codedb | BSD-3-Clause | install script or `npx -y codedeebee mcp` | parsers for 12 language families; hybrid | default uses hosted embeddings | 1,395 · v0.2.5860 (2026-09-27) | | ast-grep MCP | MIT | `uvx --from git+https://github.com/ast-grep/ast-grep-mcp ast-grep-server` | no index; AST pattern match per call | no | 482 · no GitHub release | | XERJ | Apache-2.0 | `curl -fsSL https://xerj.org/get \| sh` | BM25 index + tree-sitter definitions, 36 languages; code, docs and data files | no | 10,569 · v1.0.0-rc.97 (2026-10-19) | ## Serena: the one with an IDE behind it Serena wraps language servers and exposes symbol-level retrieval, editing and refactoring as MCP tools. Its README claims support for over 40 languages through that backend, and a JetBrains plugin backend for more. That is a capability XERJ does not have. XERJ records where a symbol is defined, has no call graph, and does not edit. If the agent's next step is a rename across files, Serena is the right tool. ## Semble and cocoindex-code: embedding-based search, no key Semble chunks files with tree-sitter and scores chunks with a static embedding model that runs on a CPU. It needs no API key, GPU or external service; the model downloads from Hugging Face on first use. Its README claims about 99 % fewer tokens than grep plus read, measured by the vendor on about 1,250 queries over 63 repositories. We did not reproduce that. cocoindex-code builds an AST-based index. Its full install pulls in sentence-transformers so local embeddings work with no key; the slim install requires a cloud embedding provider. Both beat XERJ's default path on synonym-style questions, because XERJ's default embedder is lexical feature hashing. XERJ needs `--embed-mode neural` for that. ## Claude Context and codedb: hosted embeddings by default Claude Context's documented setup asks for a vector database (Milvus or Zilliz Cloud) and an OpenAI API key for embeddings. It is a good fit if that infrastructure already exists; it is not an offline tool. codedb is a single binary that registers itself in many MCP clients. Its README marks it alpha and says the default hybrid retrieval uses hosted embeddings, with `semantic=local` for local-only retrieval. ## ast-grep MCP: patterns, not topics The ast-grep MCP server is experimental and exposes four tools, including one that dumps a syntax tree so the agent can write a working pattern. It builds no index, so it never goes stale, and it needs ast-grep and uv installed. Use it beside an index, not instead of one. Choose ast-grep when the question is a pattern rather than a topic. The [XERJ vs ast-grep](/compare/xerj-vs-ast-grep) page splits those jobs in detail. ## XERJ: one index over the whole folder XERJ is a search engine first. `xerj autoindex` reads a repository plus the docs, logs, JSONL, CSV, PDFs and SQLite files around it, writes a `defs` field and a `symbols` array for 36 tree-sitter languages, and `xerj mcp` serves 17 tools over that node, memory included. What it gives up: no references, no edits, a lexical default embedder, single-node only, and heavy memory while indexing. Our own [JSONL benchmark](/compare/best-local-full-text-search-jsonl-csv-2026) measured the node peaking at about 9.1 GiB resident while indexing a 9.7 MB file. For code-only questions, compare it with ripgrep first: on 30 disclosed tasks ripgrep won 5 outright ([XERJ vs ripgrep](/compare/xerj-vs-ripgrep-for-code-agents)). Choose ripgrep when the agent searches a tree once. ## How this page was checked Every licence, install line and capability above was read from the project's own README or docs on 2026-10-19. Stars and latest releases came from the GitHub REST API the same day. Nothing was benchmarked head to head, and every vendor performance number is labelled as the vendor's. ## FAQ ### Which MCP server for local code search needs no API key? Serena, Semble, cocoindex-code with its full install, ast-grep MCP and XERJ all run without an API key. Claude Context's documented setup needs a vector database and an OpenAI key for embeddings, and codedb's default hybrid retrieval uses hosted embeddings unless you choose semantic=local. ### Which one is best for finding references and renaming symbols? Serena. It drives real language servers, so it can find references and perform symbol-level edits. XERJ extracts definitions only and rewrites nothing, and the embedding-based servers return passages, not reference graphs. ### Which one searches by meaning offline? Semble and cocoindex-code ship local embedding models. XERJ's default embedder is lexical feature hashing; embedding-based retrieval needs the opt-in --embed-mode neural, which downloads a small model once. ### When does XERJ beat the code-only servers? When the agent's questions span code and the files around it: docs, JSONL, CSV, logs, PDFs and SQLite. XERJ indexes all of them into one Elasticsearch-compatible node behind one MCP server, and the same node stores agent memory. ### Were these servers benchmarked against each other? No. This page compares documented capabilities and GitHub data checked on 2026-10-19. No head-to-head retrieval benchmark was run, and vendor token-saving claims are quoted as vendor claims. ### How were stars and releases collected? From the GitHub REST API on 2026-10-19: stargazers_count from the repository endpoint and the latest release from the releases/latest endpoint. A server with no GitHub release shows none. ## Evidence - Serena provides semantic code retrieval, editing and refactoring tools through language servers, supports over 40 programming languages with its language-server backend, and installs with uv tool install -p 3.13 serena-agent. — [https://github.com/oraios/serena](https://github.com/oraios/serena) - Claude Context needs a vector database (Milvus or Zilliz Cloud) and, in its documented configuration, an OpenAI API key for the embedding model; the MCP server runs with npx @zilliz/claude-context-mcp@latest. — [https://github.com/zilliztech/claude-context](https://github.com/zilliztech/claude-context) - Semble runs on CPU with no API keys, GPU or external services, downloads its embedding model from Hugging Face on first use, chunks files with tree-sitter, and exposes a search MCP tool. — [https://github.com/MinishLab/semble](https://github.com/MinishLab/semble) - cocoindex-code's full install pulls in sentence-transformers for local embeddings with no API key; the slim install requires a cloud embedding provider and an API key. — [https://github.com/cocoindex-io/cocoindex-code](https://github.com/cocoindex-io/cocoindex-code) - codedb is alpha; structural search runs locally, and its default hybrid retrieval uses hosted embeddings unless semantic=local is chosen. — [https://github.com/justrach/codedb](https://github.com/justrach/codedb) - ast-grep MCP is an experimental server exposing four tools and requires ast-grep and uv to be installed. — [https://github.com/ast-grep/ast-grep-mcp](https://github.com/ast-grep/ast-grep-mcp) - ripgrep searches files directly with no index; on one 331-file tree it won 5 of 30 disclosed tasks outright against the XERJ index. — [https://github.com/BurntSushi/ripgrep](https://github.com/BurntSushi/ripgrep) - XERJ's tree-sitter registry covers 36 languages and extracts definitions; xerj mcp served 17 tools in a live tools/list. — `engine/crates/xerj-autoindex/src/extract/code.rs` - In the JSONL benchmark of 2026-10-19 the XERJ node peaked at 9,578,548 kB (about 9.1 GiB) resident while indexing one 9.7 MB file of 50,000 records. — `benchmarks/best-of-jsonl-search-2026/README.md` - Semble's README claims about 99 % fewer tokens than grep plus read, measured by the vendor on about 1,250 queries over 63 repositories. — [https://github.com/MinishLab/semble](https://github.com/MinishLab/semble) ## Related - [I need my agent to find a passage and cite the file, not dump the whole tree. How?](/answers/code-search-mcp-for-claude-code) - [Local code search MCP for Claude Code that uses fewer tokens than grep](/answers/local-code-search-mcp-fewer-tokens-than-grep) - [The best grep and ripgrep alternatives for AI coding agents in 2026](/compare/best-grep-alternative-for-ai-coding-agents-2026) - [Is ripgrep enough for a coding agent, or do I need a code index?](/compare/xerj-vs-ripgrep-for-code-agents) - [ast-grep vs a code index for an agent?](/compare/xerj-vs-ast-grep) - [How do I stop my agent from reading the whole repo into context?](/answers/index-monorepo-for-agent) - [How do I audit a PHP codebase with an index instead of grepping 1,400 files?](/answers/audit-php-codebase-with-an-index) (same intent: code search for agents) - [My codebase indexer says indexed but I don't see my code. How do I check it actually finished?](/answers/check-codebase-index-is-complete) (same intent: code search for agents) - [How do I set up reference coding so the agent retrieves a mechanism before writing code?](/answers/index-reference-library-for-coding-agent) (same intent: code search for agents)