- Knowledge Graph RDBMS @cunicopia-dev/knowledge-graph-rdbmsA label property graph on SQLite/Postgres with multi-ontology routing and a gated MCP server.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Boyce @boyce-io/boyceDeterministic SQL compiler for AI agents. Your agent stops guessing SQL.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Queryshield @bch1212/queryshieldSecure SQL proxy for AI agents — NL→SQL, AST safety, per-agent RLS, audit log.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- memex @ayushagrawal288/memexPersistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Fastmcp Sqltools @atarkowska/fastmcp-sqltoolsA MCP server provides SQL database access with support for PostgreSQL, MySQL, and SQLite.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- FastTransfer @arpe-io/fasttransfer-mcpMCP server for FastTransfer — high-performance parallel data transfer between databases5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Spark SQL @aidancorrell/spark-sql-mcp-serverQuery Spark SQL clusters via Thrift/HiveServer2. Works with Spark, EMR, Hive, Impala.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- SQL Server MCP (Windows) @tharanabope/sql-server-mcpSQL Server MCP with RAG capabilities for Windows (native ODBC support)5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- WhatsApp Chat Reader (Unofficial) @nabheetcloud/wa-chat-readerUnofficial read-only MCP server for your local WhatsApp chat history (stays on your machine).7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Ariel Memory @cipher208/ariel-memoryTwo-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Sql Builder Ai @csoai-org/sql-builder-ai-mcpSql Builder Ai MCP Server by MEOK AI Labs9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Atlas @atlasdevhq/atlasAtlas is a YAML-defined semantic layer for analytics — authored by humans, consumed by AI agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Neurohive @adelelo13/neurohiveMulti-agent memory intelligence with expertise tracking and conflict detection5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Flarelink @flarelink/mcpBuild on the Flarelink stack — Cloudflare auth, D1, and R2 — from your AI coding tools.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- RationalBloks @rationalbloks/mcpDeploy production REST and Neo4j Graph APIs from JSON schemas in seconds.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Plexus @pcas-io/plexusTyped on-prem knowledge graph for AI agents — read-only for humans, write-only for agents via MCP.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Award Flight Daily @awardflightdaily/award-flight-dailyOfficial airline award MCP. Search 12.3M+ award flights across 48 loyalty programs.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Grimoire @ttrpg/grimoireCampaign manager for D&D and TTRPG GMs: your AI reads and writes a live typed campaign database.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Memors @kkeo/memorsLocal, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.Not assessed yet.Runs on your machine, installed from MCPB.
- Shadowjoin @harsh-chandak/shadowjoinMeasure the matches your exact join is silently dropping, and get the rule that fixes each.Not assessed yet.Runs on your machine, installed from npm.
- LogCarver @caiderek/logcarver-mcpRead-only MCP server that finds deleted SQL Server rows from the transaction log (fn_dblog).8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.
- Qdrant RBAC @fidonis/qdrant-mcp-rbacRole-based access to your Qdrant vector store, via MCP. OIDC in, scoped JWTs out.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- PostgreSQL Performance (read-only) @gouranshul/pg-perf-mcpRead-only PostgreSQL performance diagnostics: slow queries, EXPLAIN, index advice, locks, functionsNot assessed yet.Runs on your machine, installed from Docker.
- Maplith Bridge @maplith/bridgeShare a folder of data files read-only over MCP, and fill it from PostgreSQL under a read-only role.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
