Connect and unify data across various platforms and databases with MindsDB as a single MCP server.
Self-hosted mem0 MCP server for Claude Code with Qdrant vector search, Neo4j knowledge graph, and Ollama embeddings.
$ uvx automatically downloads, installs, and runs the server in an isolated environment, no manual installation needed. Claude Code launches it on demand when the MCP connection starts.Or add it with the Claude CLI: claude mcp add elvismdev-mem0-mcp-selfhosted
Requires uvx (install via pip install uv)
add_memoryenable_graphsearch_memoriesget_memoriesget_memoryupdate_memorydelete_memorydelete_all_memorieslist_entitiesdelete_entitiessearch_graphget_entity{ "mcpServers": { "elvismdev-mem0-mcp-selfhosted": { "command": "uvx", "args": ["automatically", "downloads,", "installs,", "and", "runs", "the", "server", "in", "an", "isolated", "environment,", "no", "manual", "installation", "needed.", "Claude", "Code", "launches", "it", "on", "demand", "when", "the", "MCP", "connection", "starts."], "env": { "MEM0_PROVIDER": "<your-mem0-provider>", "MEM0_USER_ID": "<your-mem0-user-id>", "MEM0_LLM_MODEL": "<your-mem0-llm-model>", "MEM0_ANTHROPIC_TOKEN": "<your-mem0-anthropic-token>", "ANTHROPIC_API_KEY": "<your-anthropic-api-key>", "MEM0_OAT_REFRESH_THRESHOLD_SECONDS": "<your-mem0-oat-refresh-threshold-seconds>", "MEM0_LLM_MAX_TOKENS": "<your-mem0-llm-max-tokens>", "GOOGLE_API_KEY": "<your-google-api-key>", "MEM0_QDRANT_API_KEY": "<your-mem0-qdrant-api-key>", "MEM0_NEO4J_PASSWORD": "<your-mem0-neo4j-password>" } } } }
Paste under mcpServers in your config, then restart Claude Desktop. For Claude Code, reference this server in your project's CLAUDE.md.
Connect and unify data across various platforms and databases with MindsDB as a single MCP server.
Local-first system capturing screen/audio with timestamped indexing, SQL/embedding storage, semantic search, LLM-powered history analysis, and event-triggered actions - enables building context-aware…
npx screenpipe recordMemory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources
pip install cognee