claude-context-mcp@0.1.3-relyt-0
VERIFIED· startup onlyPublisher claims: "Model Context Protocol integration for Claude Context" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Startup only; authenticated tool behavior not tested.- Tested
- server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
- Not tested
- the tool list (the server exited before answering) · what the tools do when called with real credentials
- Needs
- GEMINI_API_KEY, OPENAI_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
- no credential variables read in the code; at startup it asked for GEMINI_API_KEY, OPENAI_API_KEY
- Where it talks to
- no vendor host named in the code
- What we saw when it ran
- no credential files read · no network
- What we could not test
- the tool list (the server exited before answering) · what the tools do when called with real credentials
Connect it under the guard. Startup only; authenticated tool behavior not tested. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-20 and scored it 80/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed (it asks for GEMINI_API_KEY, OPENAI_API_KEY); the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 62 s · 2 scenarios · 0 deviationsStatic findings
Usage: npx @zilliz/claude-context-mcp@latest [options]Fix: Pin versions and sources; vendor anything fetched at install time.OPENAI_API_KEY=sk-xxx MILVUS_ADDRESS=localhost:19530 npx @zilliz/claude-context-mcp@latestFix: Pin versions and sources; vendor anything fetched at install time.this.codebaseFileCount = new Map(); // No file count info in v1 formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.OPENAI_API_KEY=sk-xxx VECTOR_DATABASE_PROVIDER=postgres POSTGRES_CONNECTION_STRING=postgresql://user:pass@localhost:5432/db npx @zilliz/claude-context-mcp@latestFix: Pin versions and sources; vendor anything fetched at install time.<summary><strong>2. VoyageAI Configuration</strong></summary> VoyageAI offers specialized code embeddings optimized for programming languages. ```bash # RequireFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><strong>1. OpenAI Configuration (Default)</strong></summary> OpenAI provides high-quality embeddings with excellent performance for code understanding.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><strong>3. Gemini Configuration</strong></summary> Google's Gemini provides competitive embeddings with good multilingual support. ```bash # Required: Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.OPENAI_API_KEY=sk-xxx EMBEDDING_MODEL=text-embedding-3-large MILVUS_TOKEN=your-token npx @zilliz/claude-context-mcp@latestFix: Pin versions and sources; vendor anything fetched at install time.<summary><strong>4. Ollama Configuration (Local/Self-hosted)</strong></summary> Ollama allows you to run embeddings locally without sending data to external serFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…alhost POSTGRES_DATABASE=vectordb POSTGRES_USERNAME=user POSTGRES_PASSWORD=pass npx @zilliz/claude-context-mcp@latest # Start MCP server with Gemini and specific model EMBEDDING_PROVIDER=Gem…Fix: Pin versions and sources; vendor anything fetched at install time.console.log(`[VECTOR_DB] Initializing PostgreSQL vector database...`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(`[MCP] PostgreSQL Connection: ${config.postgresConnectionString ? '✅ Connection string configured' :Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(`[DEBUG] POSTGRES_CONNECTION_STRING: ${envManager.get('POSTGRES_CONNECTION_STRING') ? 'SET' : 'NOT SET'}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
1 advisory for @relyt/claude-context-mcp@0.1.3-relyt-0 in OSV, worst unknown, checked 28 min ago. A vulnerability is not misbehavior: the honeypot score above is unchanged, but an exploitable server next to your credentials widens its blast radius.