- ReasonGraph Cloud memory @primaxiom/reasongraphGraph memory for AI agents: entities, cause-effect links, cross-session recall, time travel.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.2 GitHub stars.
- dbt-plan @presentjay/dbt-planPredicts the DDL a dbt change will execute, before you run it. Reads files, not the warehouse.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- KEPTA — the memory for AI systems @damiantodorovic/keptaLocal encrypted memory for AI: hybrid search, 8 MCP tools, one file you own. Free, no cloud.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Memwyre @memwyreai/memwyreUniversal persistent memory and knowledge retrieval layer for AI agents and LLMs.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.2 GitHub stars.
- QuestDB Web Console MCP Server @questdb/mcp-server-questdbConnects coding agents to a running QuestDB Web Console: notebook cells, SQL queries, and charts.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Leteo @asanabrial/leteoPersistent memory for AI coding agents: one Rust binary, one local SQLite database.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.2 GitHub stars.
- SQL Benchmarks Lab @rctruta/sqlbenchdagQuery pre-computed SQL engine benchmarks. Runs standalone, no server setup required.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- hubmesh @demigoddsk/hubmeshDeterministic multi-hop graph retrieval for RAG. Zero LLM calls in the query path.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- rmbr @srock44/rmbrEmbedded, local-first memory and retrieval for AI agents. One SQLite file, no server, no API key.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Toolbelt @toolbeltai/toolbeltA collaborative substrate over your data: vector, knowledge graph, SQL, geospatial, streaming.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.2 GitHub stars.
- Scalix Cloud @scalix/cloudThe agent-native cloud: database, functions, AI, storage, computers. 50 tools, one API key.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- RavenDB @ravendb/ravendb-mcpRead-only MCP diagnostics server for RavenDB.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.2 GitHub stars.
- TypesenseKit @typesensekit/typesensekit95 typed Typesense operations for AI agents through an MCP server that is read-only by default.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- MySQL (security-first) @kurok1/mcp-server-mysqlSecurity-first MySQL MCP server with AST validation, table whitelist, schema resources, and audit.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.2 GitHub stars.
- Vectros Ai MCP @vectros-ai/mcp-serverTyped record store + hybrid search over MCP: deterministic lookups + semantic memory, per-customer.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Dbridge @ugurcl/dbridge-mcpQuery SQLite, PostgreSQL, and MySQL in plain language - read-only, with column masking and limits.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Mnemograph @tm42/mnemographEvent-sourced knowledge graph memory for AI coding agents with semantic search5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- DB MCP Server @stucchi/dbDatabase MCP server for MySQL, PostgreSQL, MongoDB, and SQLite with SSH tunneling support.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Kernal @pintomatic/kernal-mcpGraph-native memory for AI agents: a knowledge graph built from conversation, via MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Snowflake MCP Server @nsphung/mcp-snowflake-serverA Snowflake MCP server — SQL queries, schema exploration, and data insights for AI assistants5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Neo4j Canary @neo4j-labs/neo4j-mcp-canaryNeo4j MCP Canary — The canary goes first so the rest of us know what's coming3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Delx Memory @davidmosiah/delx-memoryLocal-first persistent memory MCP: shared SQLite key/value store, searchable, TTL-aware, secret-safe3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Database @cocaxcode/database-mcpMCP server for database connectivity. Multi-DB (PostgreSQL, MySQL, SQLite), 19 tools.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- wisdomGraph @cklam12345/wisdomgraphNeo4j-native DIKW memory for Claude Code — knowledge that compounds across sessions8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
