Claude Context — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Claude Context (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Actively maintained fork of zilliztech/claude-context — hardened for self-hosted Milvus deployments.
The upstream @zilliz/claude-context-mcp targets Zilliz Cloud. When used with self-hosted Milvus it has several issues:
DEADLINE_EXCEEDED.dockerignore, .npmignore etc. loaded alongside .gitignore, causing patterns like *.md to bleed across repos indexed in the same sessionThis fork strips it down to core + MCP server, patches all known issues, and publishes to @lbruton/ on npm.
DEADLINE_EXCEEDED and connection errors retry automatically before failing.gitignore and .contextignore are loaded; .dockerignore, .npmignore, and other tool-specific files are excluded. Prevents patterns like *.md from a Docker ignore file bleeding into unrelated repos indexed in the same session.!-prefixed lines in .gitignore are stripped rather than passed as positive rules to the glob engine, preventing false exclusions.[DEBUG] lines that dumped environment variable names (including API key presence) to stderr on every startup have been removed from config.ts.evaluation/ benchmark suite eliminated along with their vulnerable dependency trees.codacy.yml configured, false positives suppressed@lbruton/claude-context-core + @lbruton/claude-context-mcppackages/core and packages/mcp remain in the workspaceIn ~/.claude/.mcp.json:
{
"mcpServers": {
"claude-context": {
"command": "npx",
"args": ["-y", "@lbruton/claude-context-mcp@latest"],
"env": {
"OPENAI_API_KEY": "sk-...",
"EMBEDDING_PROVIDER": "OpenAI",
"EMBEDDING_MODEL": "text-embedding-3-small",
"MILVUS_ADDRESS": "192.168.1.81:19530"
},
"startupTimeoutMs": 30000
}
}
}| Variable | Required | Description |
|---|---|---|
MILVUS_ADDRESS | Yes | Milvus gRPC endpoint — bare host:port (e.g., 192.168.1.81:19530) |
OPENAI_API_KEY | Yes\* | API key for OpenAI embeddings |
EMBEDDING_PROVIDER | No | OpenAI (default), VoyageAI, Gemini, Ollama |
EMBEDDING_MODEL | No | Model name (default: text-embedding-3-small) |
MILVUS_TOKEN | No | Authentication token for Milvus (if auth enabled) |
VOYAGEAI_API_KEY | No | Required when EMBEDDING_PROVIDER=VoyageAI |
GEMINI_API_KEY | No | Required when EMBEDDING_PROVIDER=Gemini |
OLLAMA_HOST | No | Ollama server host (default: http://127.0.0.1:11434) |
OLLAMA_MODEL | No | Ollama model name (alternative to EMBEDDING_MODEL for Ollama) |
\*Required when using OpenAI embeddings (default).
By default only .gitignore and .contextignore are loaded. To exclude files or directories from indexing without modifying your .gitignore, add a .contextignore file at the root of the codebase:
# .contextignore
dist/
*.generated.ts
secrets/This fork is designed for local Milvus Standalone. Run Milvus via Docker:
docker compose -f docker-compose-milvus.yml up -dOr point MILVUS_ADDRESS at an existing Milvus instance on your network.
pnpm install
pnpm build:core
pnpm build:mcppnpm release:core
pnpm release:mcpMIT — same as upstream.
Original project by Zilliz: zilliztech/claude-context. This fork diverges in scope (MCP-only, self-hosted Milvus) but the core indexing engine and MCP protocol implementation remain theirs.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.