Skip to main content
Glama

Set run config

set_run_config
DestructiveIdempotent

Replace .mythex/run.json (the whole file: resend every service and its deploy) and start the preview; long-lived app servers belong here, never in bash. Frontend + API: services: [{ name, command, port, web: true, deploy }, { name: "api", command, port, web: false, deploy }]. Commands run at the project root: write cd server && node index.js (a service cwd is folded into its command the same way). port = the port the dev server already uses (the starter's Vite: 5173); no host/port flags needed. Every service needs its own deploy: static site { build, static, runtime: "static" }, server { dockerfile, context? } (a Dockerfile in a subfolder may COPY paths relative to its own folder; set context to be explicit). The frontend reaches the API at relative /api, proxied by the dev server, so the build carries no absolute API URL. database/storage flags here do not provision: call attach_database / enable_storage. If the preview stays unhealthy, read get_logs and fix the code rather than calling this again and again.

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": {
      "config": "<config>"
    },
    "name": "set_run_config"
  }
}

Input Schema

NameRequiredDescriptionDefault
configYesRun manifest: services[] (name, command, port, web, setup, deploy) or command / port / deploy, plus database / storage
project_idNoProject id (or use session from use_project)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds the critical detail of what is destroyed: the whole file is replaced, so every service and its deploy must be resent and omitted services are lost. It also discloses the side effect of starting the preview and the failure-mode guidance about repeated calls, which is behavior beyond the annotation set.

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 key statement (file replacement + preview start) is front-loaded and nearly every sentence carries actionable detail. It is, however, a dense wall of run-on sentences mixing schema examples, deploy variants, and cautionary advice, which makes it harder to scan than it needs to be.

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

Completeness5/5

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

For a high-complexity, nested-object config tool with no output schema, the description covers the manifest shape, command and port conventions, both deploy forms, proxy assumptions, and the provisioning boundary. An agent has enough to construct a valid call and to know when not to call it.

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?

Although schema coverage is 100%, the description adds substantial semantics the schema does not carry: the services[] shape with web true/false for frontend vs API, command execution at the project root with cwd folded into the command, port meaning the port the dev server already uses (5173 for the starter Vite), and the two deploy variants (static vs dockerfile with optional context and COPY path behavior). This is meaning beyond the structured fields.

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 and resource ('Replace .mythex/run.json ... and start the preview') and immediately delimits scope against siblings: long-lived app servers belong here, never in bash. An agent can distinguish this from bash and from the attach_database/enable_storage siblings without opening any schema.

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?

Provides explicit when/when-not routing: use this instead of bash for app servers, call attach_database / enable_storage for provisioning rather than relying on database/storage flags here, and read get_logs instead of re-calling when the preview stays unhealthy. These are concrete alternative-selection rules, not implied usage.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources