Skip to main content
Glama
Sign In

Runcrate

by io.github.aeonmindai
OverviewDiscussionsAdmin

Get cluster details

get_cluster
Read-onlyIdempotent

Get one cluster: status, stack_status and stack_detail (why the software install failed, if it did), hourly_rate (whole cluster) and hourly_rate_per_node (one machine), billing.billed_since (when every machine came up) and billing.nodes_billed, resize (workers can be added or removed), and nodes, each with rank, role (head is rank 0), instance_id, status, stage, overlay_address, gpus, ip and ssh_command (null until the cluster is up; on a machine with no public address of its own, ssh_command goes through a gateway host and port). A node's instance_id works with ssh_execute, file_upload and file_download. connection has head_ssh, the hostfile, MASTER_ADDR, MASTER_PORT, NCCL_SOCKET_IFNAME and ready-made torchrun, mpirun and deepspeed commands (plus sbatch, kubectl_tunnel or ray_tunnel for those stacks). Also shared (/shared on every node, or available false on container machines), the last 50 events, and last_test, the latest NCCL test result.

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": {
      "id": "<id>"
    },
    "name": "get_cluster"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesCluster ID
workspaceNoWorkspace ID (optional: defaults to the authenticated workspace)
environmentNoEnvironment name (optional: defaults to the environment this session acts in)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description goes well beyond that by explaining semantics an agent cannot get from annotations: ssh_command is null until the cluster is up, gateway routing for nodes without a public address, shared is unavailable on container machines, and instance_id is the handle for ssh_execute/file_upload/file_download.

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

Conciseness3/5

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

It is a single dense run-on sentence enumerating dozens of fields, which makes it hard to scan even though the most important items (status, stack_detail, rates, billing) are front-loaded. A structured or bulleted layout would communicate the same content with less parsing cost, and some nested detail (torchrun/mpirun/deepspeed, sbatch/kubectl_tunnel/ray_tunnel) could be compressed.

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?

There is no output schema, so the description carries the full burden of describing returns and does so thoroughly: node-level fields, billing, resize, connection helpers, shared storage, recent events and last NCCL test. An agent knows what it will receive and how to use node instance_ids downstream.

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 100%, so the schema already documents id, workspace and environment including their defaults. The description adds no syntax or constraint detail for the parameters themselves, which is acceptable at full coverage but means no extra value is contributed on this dimension.

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?

Opens with a specific verb+resource: "Get one cluster," which implicitly contrasts with the sibling list_clusters. The rest of the sentence enumerates the returned fields, reinforcing that this is a single-cluster detail fetch, though it never names list_clusters as the alternative.

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

Usage Guidelines3/5

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

Usage is only implied: an agent can infer this is for inspecting one known cluster because the required id parameter and the field enumeration suggest a detail view. There is no explicit when-to-use versus list_clusters, no prerequisites, and no note about which workspace/environment context applies.

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

All Runcrate toolsInspect
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