Skip to main content
Glama
singlestore-mcp-server

singlestore-mcp-server

by jonasliesas

notebook_run

Destructive

Execute a SQL, Python, or SAS notebook cell in its kernel, returning a run ID to poll; SQL results become DataFrames and data-changing statements may require confirmation.

Instructions

Run one notebook cell in its kernel; returns a run id to poll with notebook_poll.

cell_type "sql": a SingleStore statement whose result becomes a DataFrame
(``df``, and ``name`` if given). Statements that change data or schema
come back with ``needs_confirmation`` unless ``confirmed``.
cell_type "python": Python code, run as-is.
cell_type "sas": SAS code through saspy in the kernel's own SAS session (kept for older callers; the app runs
SAS cells with notebook_sas_cell in the Workspace's SAS session).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "notebook_id": "<notebook_id>",
      "cell_type": "<cell_type>",
      "source": "<source>"
    },
    "name": "notebook_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
sourceYes
databaseNo
cell_typeYes
confirmedNo
notebook_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.8.1

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag destructiveHint=true and readOnlyHint=false; the description adds real context beyond them by explaining that data- or schema-changing statements come back with needs_confirmation unless confirmed, i.e. a confirmation gate precedes the destructive effect. It does not cover kernel session side effects (persisted variables, session state changes) or what happens when no kernel is active.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the one-sentence purpose and return value, then structured per cell_type, so scanning is easy. The SAS parenthetical is slightly verbose for a legacy path but still earns its place by redirecting callers.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, six-parameter mutation tool with no output schema, it supplies the key missing pieces: the run-id/poll contract and the confirmation behavior for mutating SQL. The gaps are the undocumented notebook_id/database parameters and the unstated kernel prerequisite, which an agent would need to infer from siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description carries the full explanatory burden. It does well on cell_type by enumerating sql/python/sas semantics, implies source is the statement or code, hints that name labels the resulting DataFrame, and explains confirmed; however notebook_id and database are never mentioned, leaving two of six parameters undocumented anywhere.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource — run one notebook cell in its kernel — and adds the outcome (a run id to poll with notebook_poll). It also differentiates itself from the sibling notebook_sas_cell by scoping the 'sas' cell_type to older callers, so an agent can pick between them without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit follow-up routing (poll with notebook_poll) and an explicit alternative for SAS work (notebook_sas_cell in the Workspace's SAS session). It stops short of stating prerequisites, such as whether a kernel must already be running via notebook_kernel_start, or when to prefer a plain SQL path like sql_editor_execute.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools