Skip to main content
Glama
Sign In
BlockRun MCP

BlockRun MCP

Official
by BlockRunAI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

blockrun_modal

Destructive

Runs isolated code in disposable Modal sandboxes with optional GPU access, providing a clean ephemeral environment for untrusted or resource-intensive workloads.

Instructions

Run isolated code in a BlockRun-hosted Modal sandbox — disposable remote container, optional GPU.

Use when you need: a clean ephemeral environment, GPU access (T4/L4/A10G/A100/H100 — those five only), or a safer place for untrusted code. Prefer local tools for normal repo work.

⚠️ timeout IS THE BILLED LIFETIME — charged upfront in full, NEVER refunded. It is not an idle timeout: you pay for the time you ASK for, not the time you use, and terminating early refunds nothing. Ask for what you need, not a safe-looking ceiling.

  • timeout ≤ 300s, cpu ≤ 1 and memory ≤ 1024 → flat: $0.0120 CPU · $0.0520 T4 · $0.0820 L4 · $0.1020 A10G · $0.2020 A100 · $0.4020 H100

  • anything longer or larger → PER-HOUR × the full requested lifetime, never below flat: $0.25/h CPU · $4.00 T4 · $4.50 L4 · $5.00 A10G · $7.00 A100 · $9.00/h H100 e.g. { timeout: 600, gpu: "A100" } = $1.1687 · { timeout: 300, gpu: "T4", cpu: 8 } = $0.3353 · { timeout: 86400, gpu: "H100" } = $216.00

Common paths (all POST):

  • sandbox/create — body: { image?, timeout?, cpu?, memory?, gpu?, setup_commands? } (see above — $0.0120 to $216.00)

  • sandbox/exec — body: { sandbox_id, command: ["python","-c","..."], timeout? } ($0.0030)

  • sandbox/status — body: { sandbox_id } ($0.0030)

  • sandbox/terminate — body: { sandbox_id } ($0.0030)

Full pricing tables + GPU details in the modal skill.

Input Schema

NameRequiredDescriptionDefault
bodyNoJSON body. Sent as POST.
pathYesEndpoint under /v1/modal/, e.g. 'sandbox/create', 'sandbox/exec'
agent_idNoAgent identifier for budget tracking and enforcement.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.45.1
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  2. First observedv0.16.2

TDQS

A4.6/5.0
Behavior4/5

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

Annotations declare destructive=true and openWorld=true, but the description adds the critical undisclosed behavior: timeout is billed lifetime, charged upfront, never refunded, with concrete price tiers and worked examples. It omits return-value shape and whether create returns a sandbox_id, which is a minor gap given no output schema.

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 purpose and the billing warning, then structured endpoint and pricing blocks. The pricing table is dense but every figure earns its place for a paid resource; the sentence about timeout is emphatic but justified because misuse has real cost.

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?

A complex, costly, multi-endpoint tool with no output schema and a free-form body, and the description covers endpoints, GPU options, pricing, and billing semantics. The only material gap is what a successful create/exec returns.

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

Parameters5/5

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

Schema coverage is 100% but the body property is a bare object with no fields, and the description compensates by enumerating each endpoint's body shape (image, timeout, cpu, memory, gpu, setup_commands) and the exec/status/terminate bodies. This adds meaning the schema alone does not carry.

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 specific verb+resource ("Run isolated code in a BlockRun-hosted Modal sandbox") and adds qualifiers (disposable remote container, optional GPU) that separate it from all sibling tools, none of which execute code.

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

Usage Guidelines5/5

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

Gives explicit selection criteria ("Use when you need: a clean ephemeral environment, GPU access... or a safer place for untrusted code") and an explicit when-not ("Prefer local tools for normal repo work"), plus a per-endpoint breakdown for choosing path values.

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