# zilliztech/claude-context

Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

Repository: https://github.com/zilliztech/claude-context
Canonical: https://ross.abutalabs.com/products/claude-context
Homepage: https://github.com/zilliztech/claude-context/tree/master/docs
Language: TypeScript
License: MIT
License Family: permissive
Topics: agent, agentic-rag, ai-coding, code-search, cursor, embedding, mcp, nodejs, openai, rag, semantic-search, typescript, vector-database, vibe-coding, voyage-ai, vscode-extension, merkle-tree, code-generation, claude-code, gemini-cli
Last push: 2026-07-14T12:00:38+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 35, longevity 32
- inputs: {"age_days": 454, "days_push": 50, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 12447, forks 914 (observed 2026-08-28T04:10:52.733621+00:00)

## What it is
Claude Context is an MCP plugin that adds semantic code search to Claude Code and other AI coding agents, indexing an entire codebase into a vector database so agents retrieve only relevant code as context. It ships as an MCP server, a core npm package, and a VS Code extension, with support for embedding providers like OpenAI and Voyage AI.

## Use cases
- give claude code semantic search over my whole codebase
- index a large repository so my AI coding agent finds relevant code
- reduce token costs when working with big codebases in claude
- add codebase context to cursor or gemini cli via mcp
- search millions of lines of code semantically instead of grep
- set up an mcp server for code retrieval with a vector database

## When to choose
- you use Claude Code, Cursor, or another MCP-compatible agent and want whole-repo context
- your codebase is too large to load into context and you want cost-efficient retrieval
- you want semantic code search backed by Milvus/Zilliz Cloud with incremental Merkle-tree indexing

## When to avoid
- you need fully offline search with no external embedding or vector database service
- your project is small enough that built-in grep/file tools suffice
- you are not using any MCP-compatible coding agent

## Facets
- artifact type: plugin
- maturity: active
- function: mcp, search-engine, rag, vector-database, developer-tools
- domain: developer-tools, artificial-intelligence, large-language-models
- platform: editor-plugin, cli, cloud
- tags: semantic-code-search, claude-code, mcp-server, code-indexing, vscode-extension, merkle-tree, agentic-coding, zilliz, milvus, embedding, ai-agents, search, nodejs, typescript, docker

## Member repositories
- zilliztech/claude-context (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:52.733621+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:14:04.033865+00:00, confidence not recorded.
  - readme: https://github.com/zilliztech/claude-context (fetched 2026-08-28T04:10:52.733621+00:00, sha cd5f292f2af4)
  - homepage: https://github.com/zilliztech/claude-context/tree/master/docs (fetched 2026-08-29T08:11:11.569138+00:00, sha 6c2136aa79fa)
- Data as of 2026-08-30T08:39:29.467469+00:00.