MCP server for semantic search using local Qdrant vector database and OpenAI embeddings
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
Picomatch has a ReDoS vulnerability via extglob quantifiers
Picomatch: Method Injection in POSIX Character Classes causes incorrect Glob Matching
process.env. You'll be asked to provide them before it can run.CODE_BATCH_SIZE— Number of chunks to embed in one batch 100CODE_CHUNK_OVERLAP— Overlap between chunks in characters 300CODE_CHUNK_SIZE— Maximum chunk size in characters 2500CODE_ENABLE_AST— Enable AST-aware chunking (tree-sitter) trueCODE_ENABLE_HYBRIDCODE_SEARCH_LIMITCOHERE_API_KEY— Cohere API key -EMBEDDING_BASE_URL— Custom API URL Provider-specificEMBEDDING_DIMENSIONSEMBEDDING_MAX_REQUESTS_PER_MINUTE— Rate limit Provider-specificEMBEDDING_MODEL— Model name Provider-specificEMBEDDING_PROVIDER— "": "openai", // or "cohere", "voyage"EMBEDDING_RETRY_ATTEMPTS— Retry count 3EMBEDDING_RETRY_DELAY— Initial retry delay (ms) 1000GIT_BATCH_RETRY_ATTEMPTS— Retry attempts for failed batches 3GIT_BATCH_SIZE— Number of chunks to embed in one batch 100GIT_ENABLE_HYBRID— Enable hybrid search with sparse vectors trueGIT_INCLUDE_DIFF— Include truncated diff in chunks trueGIT_INCLUDE_FILES— Include changed file list in chunks trueGIT_MAX_CHUNK_SIZE— Maximum characters per chunk 3000GIT_MAX_COMMITS— Maximum commits to index per run 5000GIT_MAX_DIFF_SIZE— Maximum diff size in bytes per commit 5000GIT_SEARCH_LIMIT— Default search result limit 10GIT_TIMEOUT— Timeout for git commands (ms) 300000HTTP_PORT— TRANSPORT_MODE=http =3000 node build/index.jsHTTP_REQUEST_TIMEOUT_MS— Request timeout for HTTP transport (ms) 300000LOG_LEVEL— Logging level (fatal/error/warn/info/debug/trace/silent) infoOPENAI_API_KEY— "": "sk-...", // provider-specific API keyPROMPTS_CONFIG_FILE— Note: By default, the server looks for prompts.json in the project root directory. If the file exists, prompts are automatically loaded. You can specify a custom path using the environment variable.QDRANT_API_KEY— For Qdrant Cloud or secured instances, add --env =your-key or set in env config.QDRANT_URL— "": "http://localhost:6333"TRANSPORT_MODE— http HTTP_PORT=3000 node build/index.jsVOYAGE_API_KEY— Voyage AI API key -[](https://m8ven.ai/mcp/mhalder-qdrant-mcp-server-1l5g3w)