Frontier Now
Search

← Back toMCP

Databases

Published entries filed under “Databases” in MCP, newest first by publication date on this site.

6 entries

  1. Confluent MCP: Kafka topics and consumer lag for agents

    Confluent's open-source Kafka MCP server: agents manage topics, produce and consume, check consumer lag and run Flink SQL. Local Kafka needs no cloud account.

    Databases

  2. DuckDB / MotherDuck MCP: SQL analytics on local data

    MotherDuck's official DuckDB MCP server: agents run analytical SQL on local DuckDB files, S3 or MotherDuck, read-only by default, with no server to deploy.

    Databases

  3. Qdrant MCP: a vector database as semantic agent memory

    Qdrant's official MCP server: two tools, store and find, with text embedded by FastEmbed. Works with a local file or a Qdrant server, for memory or snippets.

    Databases

  4. MCP Toolbox for Databases: one server for 20+ databases

    Google's open-source database MCP server: one flag connects Postgres, MySQL, BigQuery and more, and a YAML file defines safe tools that run only fixed SQL.

    Databases

  5. MongoDB MCP Server: query collections and manage Atlas

    MongoDB's official MCP server: agents query, aggregate and read plans, and with Atlas credentials manage clusters and users. Examples default to read-only.

    Databases

  6. Postgres MCP Pro: slow-query hunting and index advice

    More than a SQL pipe to Postgres: agents run health checks, read EXPLAIN plans, simulate hypothetical indexes and get index advice, with a read-only mode.

    Databases