An MCP server that enables searching arXiv, importing papers, enriching with citation data, generating summaries and research ideas, and querying a local library using local LLMs and 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.
process.env. You'll be asked to provide them before it can run.APP_ENVDATA_DIR— ./data SQLite database + ChromaDB location.MODELS_DIR— ./models GGUF model file location.LOG_LEVELHOSTPORTEMBEDDING_MODELRERANKER_MODELLLM_REPO_IDLLM_MODEL_FILELLM_N_CTX— 4096 LLM context window size.LLM_N_THREADS— 4 CPU threads for LLM inference.LLM_N_GPU_LAYERS— 0 GPU layers to offload (0 = pure CPU).MCP_TRANSPORT— Communicates over stdio by default. Set =sse in .env forHF_TOKEN— Edit .env and add your . This is used only for downloading[](https://m8ven.ai/mcp/eddisonpham-arxivum-16tq36)