Enables semantic search and retrieval of archived AI conversations from multiple providers via the MCP protocol, allowing thread continuation and integration with MCP-capable tools.
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.ALLOWED_HOSTS— . Full setup, persistence semantics, routing controls, runtimeCHUNK_MAX_CHARS— 2000 Max characters per embedded chunk.CHUNK_OVERLAP_CHARS— 100 Overlap between long chunks.COLLECTIONS_PATH— .collections.json Manual-collections registry file.EMBED_BATCH_SIZE— 25 Embedding batch size during ingest.GENERATION_CONFIG_PATH— .threadshelf/generation.json Non-secret Experimental Alpha generation settings.GENERATION_ERROR_LOG_PATHHOST— loopback-only even when the read/search UI is exposed with andLANCEDB_PATH— .lancedb LanceDB directory.MASTER_PROMPTS_PATH— .threadshelf/master-prompts.json Saved master (system) prompts.OPENROUTER_API_KEY— OpenRouter keys should preferably be supplied as in thePORT— 3000 Server port.THREADSHELF_TOOLS_PATH— .threadshelf/tools llama.cpp discovery/installer root.UPLOADS_DIR— .uploads Uploaded source files.[](https://m8ven.ai/mcp/chrystianschutz-threadshelf-1hrstq)