Provides semantic code search and retrieval capabilities for AI agents, enabling them to query codebases using natural language with automatic learning, hybrid search, and intelligent chunking of functions and classes.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.API_BASE_URLCOHERE_API_KEY— Cohere 🟡 ~$0.05/1000 functions 🔴 None Set + npm install cohere-aiCORS_ORIGINDATABASE_URLHOSTLOG_LEVELMONITORING_ENABLEDOPENAI_API_KEY— OpenAI 🔴 ~$0.10/1000 functions 🔴 None SetPAMPA_BENCH_BM25— off npm run bench – disable BM25 candidate generationPAMPA_BENCH_HYBRIDPAMPA_BENCH_MODES— base,hybrid npm run bench – limit to specific modesPAMPA_BENCH_RERANKERPAMPA_ENCRYPTION_KEY— export ="$(openssl rand -base64 32)"PAMPA_MOCK_RERANKER_TESTS— Benchmark runs never download external models when =1 (enabled by default inside the harness).PAMPA_RERANKER_MAXPAMPA_RERANKER_MODELPORTSSL_CA_PATHSSL_CERT_PATHSSL_ENABLEDSSL_KEY_PATH[](https://m8ven.ai/mcp/tecnomanu-pampa-1s1m3x)