Tinybird MCP server

What the model can do

Tinybird analytics: read data sources, pipes, recent jobs, rows from a pipe endpoint and a bounded read-only SQL query (both on the customer's compute), and run, pause or resume a copy pipe, run a sink pipe, cancel a job, append events and delete rows matching explicit values.

Reads

• tinybird_list_datasourcesTinybird data sources (tables) the token can read: name, engine and sorting key, row count, size in bytes, columns with types, which pipes use it…
• tinybird_list_pipesTinybird pipes the token can read: name, description, whether it is published as an API endpoint, its node names, last updated.
• tinybird_query_pipeRows from a published Tinybird pipe endpoint, with the pipe's own parameters.
• tinybird_sqlA read-only SQL query (ClickHouse dialect) over this workspace's data sources and pipes.
• tinybird_list_jobsRecent Tinybird jobs (the last 100 in 48 hours): copies, imports, populates, deletes and sinks with their status.

Acts, when you ask

These change something in Tinybird. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

• tinybird_run_copy_pipeRuns a Tinybird copy pipe now, writing its result into its target data source (appended by default; mode "replace" overwrites the target's contents).
• tinybird_pause_copy_schedulePauses a Tinybird copy pipe's schedule: no further scheduled copies run until resumed.
• tinybird_resume_copy_scheduleResumes a paused Tinybird copy pipe's schedule, so scheduled copies run again (on the customer's compute).
• tinybird_cancel_jobCancels a waiting Tinybird job (or a running populate).
• tinybird_append_eventsAppends up to 20 events (JSON rows) to a Tinybird data source through the Events API, waiting for each write to be acknowledged.
• tinybird_delete_rowsPermanently deletes the rows of a Tinybird data source whose column equals one of up to 100 given values (e.g. user_id in a list).
• tinybird_run_sink_pipeRuns a Tinybird sink pipe now, exporting its result to the bucket or Kafka topic configured on it (outside Tinybird).

Connect it

First connect Tinybird on Dashboard → Connections, then add Memtro to your client once. The Tinybird tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Tinybird connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

• › How many events per day did we get last week?
• › Which Tinybird data sources are the largest by size?
• › What columns does the page_views data source have?
• › Run the top_pages endpoint for yesterday.
• › Run the daily_rollup copy pipe now

Questions

Is this an official Tinybird MCP server?

No. It is Memtro's MCP server with Memtro's Tinybird connector behind it: the connector reads Tinybird through its API with the credentials you connect on Dashboard → Connections, and Tinybird publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

What does it cost?

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in Tinybird?

Only when you ask, and only what it has been granted: run a copy pipe now, appending to (or, if asked, replacing) its target data source; pause or resume a copy pipe's schedule; cancel a waiting or running job; append up to 20 events to a data source; delete the rows of a data source whose column matches up to 100 given values; run a sink pipe, exporting its result to the configured bucket or topic. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.

Which clients work?

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

Other MCP servers · Databases and warehouses

• Postgres MCP server
• MySQL and MariaDB MCP server
• SQL Server MCP server
• BigQuery MCP server
• Snowflake MCP server
• AWS Athena MCP server