Helps developers tackle legacy codebases by giving AI coding assistants context through Qdrant vector store and Agentic RAG with Ollama or DeepSeek.
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
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`
process.env. You'll be asked to provide them before it can run.AGENT_ABSOLUTE_MAX_STEPS— : Absolute maximum number of steps the agent can take, even if it requests more. Default: 15AGENT_DEFAULT_MAX_STEPS— : Default maximum number of steps (tool calls or LLM responses) the agent will take. Default: 10AGENT_MAX_CONTEXT_ITEMSAGENT_QUERY_TIMEOUT— : Timeout in milliseconds for agent's LLM reasoning steps. Default: 180000 (3 minutes)CLAUDE_API_KEY— : Your API key for Anthropic Claude.CODECOMPASS_FORCE_SRC_PATHS_FOR_TESTINGCODECOMPASS_INTEGRATION_TEST_MOCK_LLMCODECOMPASS_INTEGRATION_TEST_MOCK_QDRANTCOLLECTION_NAME— : Name of the Qdrant collection for this repository.COMMIT_HISTORY_MAX_COUNT_FOR_INDEXINGDEEPSEEK_API_KEY— export ="your_deepseek_api_key_here"DEEPSEEK_API_URL— : Custom API URL for DeepSeek if not using the default.DEEPSEEK_MODELDEEPSEEK_RPM_LIMIT— : Requests per minute limit for DeepSeek. Default: 20DIFF_CHUNK_OVERLAP_CHARSDIFF_CHUNK_SIZE_CHARSDIFF_LINES_OF_CONTEXTEMBEDDING_DIMENSIONEMBEDDING_MODEL— : The specific model to use for embeddings via Ollama.EMBEDDING_PROVIDER— : Specifies the provider for generating embeddings.FILE_INDEXING_CHUNK_OVERLAP_CHARS— : Overlap between chunks when indexing large files (in characters). Default: 200FILE_INDEXING_CHUNK_SIZE_CHARS— : Target size for chunks when indexing large files (in characters). Default: 1000FORCE_PROVIDER_AVAILABLEFORCE_PROVIDER_UNAVAILABLEGEMINI_API_KEY— : Your API key for Google Gemini.HTTP_PORT— port <number> (optional): Specify the HTTP port for the server. This overrides the environment variable and the default port (3001).LLM_PROVIDER— export ="deepseek"LOG_LEVEL— : Logging level (e.g., error, warn, info, verbose, debug, silly). Default: infoMAX_DIFF_LENGTH_FOR_CONTEXT_TOOL— : Maximum length of a git diff to include in context without summarization.MAX_DIR_LISTING_ENTRIES_FOR_CAPABILITYMAX_FILES_FOR_SUGGESTION_CONTEXT_NO_SUMMARY— : Maximum number of files to list directly in the generate_suggestion tool's contextMAX_FILE_CONTENT_LENGTH_FOR_CAPABILITYMAX_REFINEMENT_ITERATIONS— : Maximum number of iterations for query refinement. Default: 3MAX_SNIPPET_LENGTH_FOR_CONTEXT_NO_SUMMARY— : Maximum length of a code snippet to include in context without summarization.OLLAMA_HOST— : URL for the Ollama server.OPENAI_API_KEY— : Your API key for OpenAI.QDRANT_BATCH_UPSERT_SIZEQDRANT_HOST— : URL for the Qdrant vector store server.QDRANT_SEARCH_LIMIT_DEFAULT— : Default number of results to fetch from Qdrant during standard searches. Default: 10REFINEMENT_MODEL— : LLM model to use for LLM-powered query refinement.REQUEST_ADDITIONAL_CONTEXT_MAX_SEARCH_RESULTS— : Number of search results to fetch when agent uses 'request_additional_context' with type 'MORE_SEARCH_RESULTS'. Default: 20SIMULATE_EADDRINUSE_FOR_PROXY_SUITE_LISTENSIMULATE_EADDRINUSE_FOR_TESTSKIP_QDRANT_INITSUGGESTION_MODEL— : The specific model to use for suggestions.SUGGESTION_PROVIDERSUMMARIZATION_MODEL— : LLM model to use for summarization tasks (e.g., long diffs, long snippets).TEST_PROVIDER_UNAVAILABLEUSE_MIXED_PROVIDERSVITESTVITEST_TESTING_FAIL_HANDLERVITEST_WORKER_ID[](https://m8ven.ai/mcp/alvinveroy-codecompass-xviesm)