Skip to main content
Glama
Sign In
Colab MCP

Colab MCP

by ALiwoto
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

runtime_action

Destructive

Manage a Colab notebook runtime by connecting, disconnecting, restarting, interrupting, deleting, or configuring CPU/GPU/TPU settings. Check runtime_status for completion or errors.

Instructions

Manage this notebook's runtime using the optional Chrome companion. Returns immediately; check runtime_status for completion or errors. Connect uses the notebook's selected runtime. Disconnect detaches the tab; delete releases its runtime and loses its files and memory. Restart clears kernel memory. Configure changes runtime settings and may replace a running runtime. GPU/TPU and high-memory availability depend on the user's account. The user handles any Colab permission or confirmation dialogs.

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": {
      "action": "<action>"
    },
    "name": "runtime_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
acceleratorNoConfigure only. Required when changing runtime settings.
high_memoryNoConfigure only; omitted preserves the setting.
accelerator_modelNoConfigure only. Colab's model identifier, e.g. T4; empty uses its default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.2/5.0
Behavior5/5

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

With annotations only declaring openWorldHint and destructiveHint, the description adds substantial context: the call is asynchronous and returns immediately, delete loses files and memory, restart clears kernel memory, configure may replace a running runtime, and outcomes depend on the user's account and confirmation dialogs. That is exactly the kind of consequence and side-effect disclosure an agent cannot get from the annotations alone.

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?

The async-return fact is front-loaded, then each action gets a short clause with no filler. Sentences are dense but every one carries a distinct behavioral fact; minor cost is that the per-action clauses are packed into a single paragraph rather than listed.

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, open-world dispatcher with no output schema, the description covers async semantics, destruction scope, permission handling, and resource-availability caveats. The main gap is the undocumented 'interrupt' action, plus no note on what happens when a connect is issued while already connected.

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

Parameters4/5

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

The schema covers 75% of parameters but leaves the action enum undocumented; the description compensates by explaining connect, disconnect, delete, restart, and configure. However 'interrupt' appears in the enum and is never described anywhere, leaving one action's semantics undefined.

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

Purpose4/5

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

States the resource precisely ('this notebook's runtime') and enumerates what each action does (connect attaches to the selected runtime, disconnect detaches the tab, delete releases the runtime, restart clears kernel memory, configure changes settings). The generic verb 'manage' is offset by the per-action breakdown, so an agent can tell it apart from runtime_status and connect_colab_tab, though the dispatcher framing makes the single purpose slightly diffuse.

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?

Explicitly routes post-action polling to runtime_status ('Returns immediately; check runtime_status for completion or errors'), which is the key alternative an agent needs. It also flags prerequisites (GPU/TPU availability tied to the account, user handles Colab permission dialogs). It stops short of saying when not to use this versus connect_colab_tab or list_colab_tabs.

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