- Telys — on-device memory @thyn-ai/telysPrivate on-device memory & retrieval for AI assistants — offline vector + lexical search.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Databases (read-only, switchable) @shibbirweb/mcp-db-read-onlyRead-only SQL, MongoDB, Redis and Elasticsearch access, switchable mid-conversation.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- OwnPG @devops-infinity/ownpgPostgreSQL DBA tools over MCP, scoped to one database and one schema.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.
- Devart MCP Server for Dynamics 365 (ADO.NET) @devart/mcp-dynamics365Schema-aware read/write access to Dynamics 365 through Devart dotConnect ADO.NET data provider.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.
- Devart MCP Server for MySQL (ADO.NET) @devart/mcp-mysqlSchema-aware read/write access to MySQL through Devart dotConnect ADO.NET data provider.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.
- DBHawk @datasparc/dbhawkSecure access to DBHawk datasources: browse schemas, run governed queries, HawkAI text-to-SQL.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MySQL (read-only, switchable) @shibbirweb/mcp-mysql-read-onlyRead-only MySQL access, with the database and server switchable mid-conversation.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- sqlglass @s-curvelabs/sqlglassSQL Server / Azure SQL for agents: real schema, lint, read-only runs, plans, write previews.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- SQL Safe MCP @proprock/sql-safe-mcpMinimal, read-only, PII-safe MCP server for SQL databases.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- health4ai @jefflitt1/health4aiQuery your Apple Health data from your own Supabase/Postgres via local MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- MySQL Legacy MCP @rufflet/mysql-legacy-mcpInspect and query MySQL 5.0–5.6; opt-in INSERT/UPDATE/DELETE/DDL. Live-verified 5.0–8.0.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- WHOOP MCP @cunicopia-dev/whoop-postgres-mcpSync WHOOP recovery, sleep, strain, and workouts into Postgres and query them from any MCP client.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- SQL Server @hlgurgel/sqlserverServidor MCP para SQL Server com controle de permissões e modo somente-leitura5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- BigQuery Data Platform @debilla/data-platform-mcpRead-only BigQuery tools for plain-language data questions, with a cost gate on every query3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- RCLL @rcll/fleet-memorySelf-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Loreweave @lets-order-some-fries/loreweaveDurable agent memory over a markdown vault: bitemporal facts, timelines, hybrid graph search.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- metabrain @ariaxhan/metabrainMCP server giving AI agents persistent SQLite memory that proves which lessons hold.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- pgops @arzharch/pgops-mcpSafe, audited PostgreSQL operations for AI agents: queries, migrations, EXPLAIN, containers3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- BanditDB @banditdb/mcpPersistent decision memory for agents — learns which action works in which context3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Websupport @tydung26/websupport-mcpManage a Websupport account: DNS, FTP, hosting, databases, mailboxes, VPS and invoices.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Docker MCP Server @hypnosis/docker-mcp-serverDocker for AI agents — containers, compose stacks, logs and databases, locally or over SSH.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- SafeSelect MCP @antonillos/safeselectFail-closed, read-only PostgreSQL and MongoDB access for AI agents over MCP.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- MySQL MCP @gistrec/mcp-mysql-clientMCP server for one MySQL database: schema, read-only queries and guarded writes.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Copilot Datagate @afurlane/copilot-datagatePolicy-driven, read-only MCP server for safe database access from AI tools.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
