Claude Context
CAUTIONgrade C · trust 80/100Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
agentagentic ragai codingclaude codecode generationcode searchcursorembeddingOverview
From the repository's own README, as read at the audited commit.
> 🆕 **Looking for persistent memory for Claude Code?** Check out [memsearch Claude Code plugin](https://github.com/zilliztech/memsearch#for-claude-code-users) — a markdown-first memory system that gives your AI agent long-term memory across sessions.### Your entire codebase as Claude's context[](https://opensource.org/licenses/MIT)[](https://nodejs.org/)[](docs/)[](https://marketplace.visualstudio.com/items?itemName=zilliz.semanticcodesearch)[](https://www.npmjs.com/package/@zilliz/claude-context-core)[](https://www.npmjs.com/package/@zilliz/claude-context-mcp)[](https://twitter.com/zilliz_universe)[](https://deepwiki.com/zilliztech/claude-context)<a href="https://discord.gg/mKc3R95yE5"><img height="20" src="https://img.shields.io/badge/Discord-%235865F2.svg?style=for-the-badge&logo=discord&logoColor=white" alt="discord" /></a><a href="https://trendshift.io/repositories/15064"><img src="https://trendshift.io/api/badge/repositories/15064" alt="zilliztech/claude-context | Trendshift" width="250" height="55" /></a></div>**Claude Context** is an MCP plugin that adds semantic code search to Claude Code and other AI coding agents, giving them deep conte
Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add semanticcodesearch --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env GITHUB_TOKEN=${GITHUB_TOKEN} --env MOONSHOT_API_KEY=${MOONSHOT_API_KEY} --env OPENAI_API_KEY=${OPENAI_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"semanticcodesearch": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"GITHUB_TOKEN": "${GITHUB_TOKEN}",
"MOONSHOT_API_KEY": "${MOONSHOT_API_KEY}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
}
}
}
}Exposed tools (17) 14 read · 2 write · 1 destructive
Blast radius: 1 tool can delete or overwrite. An agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
clear_index | destructive | Clear the search index. IMPORTANT: You MUST provide an absolute path. |
content | read | Document content |
content_bm25_emb | read | content bm25 function |
directory_tree | read | Generates a tree structure of a directory. |
edit | write | Edits the specified file with the given modifications. |
endLine | read | End line number of the chunk |
fileExtension | read | File extension |
get_indexing_status | read | Get the current indexing status of a codebase. Shows progress percentage for actively indexing codebases and completion status for indexed codebases. |
id | read | Document ID |
list_directory | read | Lists the contents of a directory. |
metadata | read | Additional document metadata as JSON string |
read_file | read | Reads the content of a text file at the specified path. |
relativePath | read | Relative path to the codebase |
search_text | read | Searches for a regular expression pattern within the content of files in a specified directory (or current working directory). Can filter files by a glob pattern. Returns the lines containing matches, along with their file paths and line numbers. |
sparse_vector | read | Sparse vector embedding from BM25 |
startLine | write | Start line number of the chunk |
vector | read | Embedding vector |
Details
- Source
- zilliztech/claude-context
- npm
semanticcodesearch@0.1.11- PyPI
evaluation- Transports
- stdio
- Credentials it reads
ANTHROPIC_API_KEYGITHUB_TOKENMOONSHOT_API_KEYOPENAI_API_KEY- License
- MIT
- Stars
- 12,521 · pushed 60d ago
Trust audit
Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (6 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (25)
tree-sitter-go.wasm
tree-sitter-java.wasm
tree-sitter-javascript.wasm
tree-sitter-python.wasm
host: config.host || 'http://127.0.0.1:11434',
clear_index
.eslintrc.js
AGENTS.md
const pathHash = crypto.createHash('md5').update(normalizedPath).digest('hex').substring(0, 8);const hash = crypto.createHash('md5').update(normalizedPath).digest('hex');const hash = crypto.createHash('md5').update(normalizedPath).digest('hex');const repoRoot = path.resolve(path.dirname(__filename), "../../..");
const repoRoot = path.resolve(path.dirname(__filename), "../../..");
| `OLLAMA_HOST` | Ollama server URL | `http://127.0.0.1:11434` |
"OLLAMA_HOST": "http://127.0.0.1:11434",
- `OLLAMA_HOST=http://127.0.0.1:11434` (or your Ollama server URL)
# Optional: Specify Ollama host (default: http://127.0.0.1:11434)
return atob(data.content.replace(/\n/g, ''));
tsx, typescript, @types/node, dotenv
@types/node, @typescript-eslint/eslint-plugin, @typescript-eslint/parser, assert, browserify-zlib, eslint, https-browserify, os-browserify
@types/chrome, @types/node, assert, browserify-zlib, buffer, copy-webpack-plugin, crypto-browserify, https-browserify
@google/genai, @zilliz/milvus2-sdk-node, faiss-node, fs-extra, glob, ignore, langchain, ollama
@modelcontextprotocol/sdk, zod, @types/node, tsx, typescript
assets/signup_and_create_cluster.jpeg
packages/chrome-extension/src/icons/icon128.png
Gates applied: no_behavioural_pass.
Audited 2026-09-13 · audit v0.4.0 · source sha 4a35db911c86 · full audit: observations/trust-audit/mcp-server/zilliztech__claude-context.json · Report an issue or request a re-scan
Audit history
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-13 | 4a35db911c86 | CAUTION | C | 80 | first audit |
Alternatives
Other servers in the same categories, safer ones first.
Questions
What is the Claude Context MCP server?
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
What tools does Claude Context expose?
17 in total: 14 read-only, 2 that write, and 1 that can delete or overwrite (clear_index). Every one is listed on this page with its risk.
Is Claude Context safe to connect to an agent?
With care. The audit graded it C (80/100) and found 25 things worth knowing before you trust this server, listed below with the exact line each was found on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Claude Context need?
It reads ANTHROPIC_API_KEY, GITHUB_TOKEN, MOONSHOT_API_KEY and OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Claude Context run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as semanticcodesearch at 0.1.11.
How current is this page?
The grade is for one exact copy of the source (4a35db911c86), read on 2026-09-13. The repository is watched and re-audited when it changes.
Provenance: OBSERVED · read 2026-09-13 · job trust-audit-2026-09-13