MaterialsCodeGraph

mcg_clusters

Read-only

Connected clusters: id, name, preset (hive or auto), status (pending until the agent's first sync; connected; stale: the agent stopped syncing; revoked; scheduler_down: the agent syncs but cannot reach the scheduler, nothing is offered; agent_outdated: an auto cluster's agent sends no inventory; snapshot_rejected: its last snapshot was over the size cap; snapshot_stale: no fresh capacity snapshot, nothing is offered; nodes_unavailable: none of an auto cluster's nodes accept jobs (drained, down, in maintenance or not responding), nothing is offered), status_detail (why, when not connected), classes (resource classes offered per partition, with per-job GPU, CPU and memory maxima, the GRES type, and in_use: false when no engine runs on the class), unclassified_gpus (GPU types present but not offered: type, count, reason), untyped_gpus, last sync time. Pass target {cluster_id} to mcg_quote to run there at zero hardware cost; only a connected cluster quotes. Clusters are created with POST /api/clusters (on the machine host with a spend-scoped key).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "mcg_clusters"
  }
}

Input Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 8, 2026

TDQS

A4.6/5.0

Behavior5/5

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

The description adds substantial behavioral context beyond readOnlyHint=true: it explains each status value, when status_detail is populated, what it means for nothing to be offered, and the zero-hardware-cost quoting constraint. It also discloses the creation path and spend-scoped key requirement.

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 description is front-loaded with the resource and returned fields, and every status definition earns its place for interpreting output. It is dense and parenthesis-heavy, but the information is relevant rather than redundant.

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?

With no output schema, no parameters, and only a readOnly annotation, the description carries the burden of explaining the return shape and status meanings. It does so thoroughly, including classes, unclassified GPUs, sync timing, and status enum semantics.

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?

This tool has zero input parameters, so parameter semantics are not applicable and the baseline is 4. The description mentions target {cluster_id} only for mcg_quote, not as an input to this tool, so there is no additional parameter detail to add.

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?

The description identifies the resource precisely as connected clusters and enumerates the returned fields, including status semantics, classes, and GPU information. It also distinguishes the tool from mcg_quote by explaining that cluster_id values are passed to mcg_quote for quoting.

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?

It gives clear usage context: pass a cluster_id to mcg_quote to run there, and only a connected cluster can quote. It also notes that clusters are created via POST /api/clusters rather than through this tool. However, it does not explicitly compare this tool against other siblings such as mcg_catalog or mcg_rates.

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

All MaterialsCodeGraph tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?