Codeweave
This server gives your AI agent structured code understanding instead of dumping entire files into context. It runs locally, parses your codebase with tree-sitter across seven languages, and exposes three tools: semantic_search for hybrid vector and keyword queries with density-based reranking, reindex for manual updates, and get_index_status for health checks. The search pipeline combines Qwen3 embeddings via Ollama with BM25 full-text search, then reranks results using call graph centrality, visibility, and structural complexity signals to surface important code over boilerplate. Setup runs through npx with an interactive wizard that handles Ollama installation and project indexing. Reach for this when you want cheaper, more relevant context for coding tasks without blowing through tokens on file dumps.
- GitHub stars
- 3
- tools
- 3
- transport
- STDIO
- last updated
- Apr 3, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
semantic_searchSearch by meaning — finds functions even when you don't know exact names. Hybrid vector + keyword search with density-based reranking.
Search by meaning — finds functions even when you don't know exact names. Hybrid vector + keyword search with density-based reranking.
No parameter schema in public metadata yet.
reindexManually trigger index update. Usually unnecessary — file watcher auto-reindexes on changes.
Manually trigger index update. Usually unnecessary — file watcher auto-reindexes on changes.
No parameter schema in public metadata yet.
get_index_statusIndex health dashboard: file/function counts, embedding status, call graph stats, language breakdown.
Index health dashboard: file/function counts, embedding status, call graph stats, language breakdown.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
@codeweave/mcp
Give your AI agent structured code understanding — not just file dumps.
CodeWeave is an MCP server that gives AI agents cheap, precise code intelligence. Instead of dumping entire files into context, your agent queries local indexes — AST, call graph, type graph, hybrid semantic search — and gets back only what it needs.
Less tokens. More relevant context. Better decisions.
Details
- Repository
- github.com/semihkayan/codeweave-mcp
- Category
- AI & LLM Tools
- Package
@codeweave/mcp- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
GenGEO Agent Registrywarwickwood-cell/gengeo-agent-registryMerchant verification for AI shopping agents.3stars
Leakferretleakferrethq/leakferretContext-aware secret scanner: lets an AI agent scan, verify, and rewrite secrets before committing.3stars
Remembluizedupp/remembPersistent memory for AI agents — local JSON, zero config, no server required.3stars
Memori Mcpmemorilabs/memori-mcpMemori MCP server — persistent AI memory with recall and augmentation tools3stars
Mnemon Mcpnikitacometa/mnemon-mcpPersistent layered memory for AI agents. SQLite FTS5, fact versioning, zero-cloud.3stars
agentmemoxgeneral/agentmemLightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.3stars