Enterprise-grade (40m+ lines) codebase intelligence in a zero-setup, private and local MCP: managed indexing, hybrid semantic search, polyglot code dependency graphs, and DB/API/infra knowledge. Benchmark: 61% less tokens, 84% fewer calls, 37x faster than standard AI grep.
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
glob CLI: Command injection via -c/--cmd executes matches with shell:true
process.env. You'll be asked to provide them before it can run.EMBEDDING_BATCH_SIZEEMBEDDING_CONTEXT_LENGTHEMBEDDING_DIMENSIONS— Defaults: EMBEDDING_MODEL=text-embedding-3-small, =1536. For higher quality, use text-embedding-3-large with EMBEDDING_DIMENSIONS=3072.EMBEDDING_MODEL— Defaults: =text-embedding-3-small, EMBEDDING_DIMENSIONS=1536. For higher quality, use text-embedding-3-large with EMBEDDING_DIMENSIONS=3072.EMBEDDING_PROVIDER— "": "openai",EXTRA_EXTENSIONS— Custom file extensions — Projects with non-standard extensions (e.g. .tpl, .blade) can be included via env var or extraExtensions tool parameter. Works for both indexing and code graph.GOOGLE_API_KEY— "": "AIza..."INCLUDE_DOT_FILESLITELLM_API_KEY— "": "sk-...",LITELLM_SEND_DIMENSIONS— suffix; =true to forward the OpenAI dimensions parameterLITELLM_URL— Optional: (default http://localhost:4000/v1) — must include the /v1LMSTUDIO_API_KEY— if you've enabled API key auth in LM Studio.LMSTUDIO_URL— Optional: (default http://localhost:1234/v1) for non-default ports;MAX_FILE_SIZE_MB— 5 Maximum file size in MB. Files larger than this are skipped during indexing. Increase for repos with large generated or data files you want indexed.OLLAMA_API_KEY— (none) Optional API key for authenticated Ollama proxiesOLLAMA_HOSTOLLAMA_MODE— If you have [Ollama](https://ollama.com) installed natively, set =external and point to your instance:OLLAMA_PORT— 11435 Ollama container port (Docker mode). Ignored when OLLAMA_URL is set explicitly.OLLAMA_URL— "": "http://localhost:11434"OPENAI_API_KEY— "": "sk-..."QDRANT_API_KEYQDRANT_COLLECTION_PREFIXQDRANT_GRPC_PORT— 16334 Qdrant gRPC port (managed mode only)QDRANT_HOST— localhost Qdrant hostname (alternative to QDRANT_URL for non-HTTPS external instances)QDRANT_MODE— The Qdrant container is managed automatically. If you set =external and point QDRANT_URL at a remote or cloud Qdrant instance, Docker is only needed for Ollama (embeddings) in that case.QDRANT_PORT— 16333 Qdrant REST API port (managed mode, or external without QDRANT_URL)QDRANT_URL— The Qdrant container is managed automatically. If you set QDRANT_MODE=external and point at a remote or cloud Qdrant instance, Docker is only needed for Ollama (embeddings) in that case.RESPECT_GITIGNORE— 2. .gitignore — All .gitignore files in the project (root and nested subdirectories). Set =false to skip .gitignore processing entirely.SCALE_LARGESEARCH_DEFAULT_LIMITSEARCH_MIN_SCORESOCRATICODE_AUTO_RESUME— and SOCRATICODE_AUTO_RESUME_PROJECTS environment variablesSOCRATICODE_AUTO_RESUME_PROJECTS— SOCRATICODE_AUTO_RESUME and environment variablesSOCRATICODE_BRANCH_AWARESOCRATICODE_GLOBAL_CONFIG_DIRSOCRATICODE_LINKED_PROJECTS— Or set the environment variable (comma-separated paths):SOCRATICODE_LOG_FILESOCRATICODE_LOG_LEVEL— Structured logging — All operations are logged with structured context for observability. Log level configurable via .SOCRATICODE_PROJECT_ID— Set to share a single index across all directories of the same project.[](https://m8ven.ai/mcp/giancarloerra-socraticode-hugbmd)