Skip to main content
Glama
meshive-mcp

meshive-mcp

Official
by meshive

List Pods

pods
Read-onlyIdempotent

List workspace GPU/CPU containers or inspect a specific one by name, with live metrics, status, endpoints, and login details.

Instructions

List the pods (GPU/CPU containers) in a workspace, or show one pod by its pod_name (its display name also works). workspace takes the id from the workspaces tool (a label also works); pass "all" to list pods across every workspace, or omit it if the user has only one. Set include_metrics for live CPU/RAM/GPU usage of a single pod (ram_size, ephemeral_storage_* and GPU vram_size are MiB); use status to filter the list. System-managed downloader pods are hidden unless include_system is true; they are free and cannot be stopped or deleted. To open a pod, use its endpoints (URLs; readiness ready/preparing/interrupted) and connect_credentials (logins the console shows on Connect, e.g. ComfyUI's ACCESS_PASSWORD). Secret values are null; set show_secrets with a single pod only when the user asks for the login (a read-only API key gets "***"). Each endpoint's access says who can reach it: internal (only from inside the workspace), locked (only workspace members signed in to the console and requests that carry one of the port's access keys) or unlocked (anyone who knows the URL). A locked port answers a request without a key with 401 and sends a browser to the console to sign in. That is the lock working, not a fault: don't restart, edit or delete the pod for it. To call the app for your own work, use run_command inside the pod against http://localhost:; for a program outside the pod, ask the user whether to create an access key (create_access_key). set_port_lock locks or unlocks a port. A lock choice takes a few seconds to take effect: an endpoint's lock_state is locking or unlocking until then (else locked or unlocked, null when the server doesn't say), and a locking port can still be reached without a key. locked is the choice itself. allow_preflight true means CORS preflight requests (OPTIONS) reach the app without a key while the port is locked (set_port_preflight). A stopped pod's stop_reason_code (other than "user") says the system stopped it, and same_node_unavailable_reason why it cannot start on its machine now. restart_count and last_exit (one pod: recent_exits, current_run marks this run) say whether its main container keeps ending and why; status can stay running meanwhile.

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": "pods"
  }
}

Input Schema

NameRequiredDescriptionDefault
podNo
limitNo
cursorNo
statusNo
workspaceNo
show_secretsNo
include_systemNo
include_metricsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/idempotent/non-destructive, yet the description still adds substantial behavior: system downloader pods are hidden and cannot be stopped or deleted, secret values return null or "***", a 401 on a locked port is expected and must not trigger a restart/edit/delete, and lock changes take a few seconds. The only shortfall is that pagination behavior (limit/cursor) is never described.

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?

Purpose is front-loaded and nearly every sentence carries real information, but the body is a dense multi-topic block mixing listing, metrics, secrets, endpoint access semantics, lock timing, and crash diagnostics. It would scan far better as short labeled sections; as written an agent must parse a wall of prose to find the parameter it needs.

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 an 8-parameter read tool with an output schema, the description covers everything an agent needs to call it correctly and to interpret the response fields it will actually act on (endpoints, access, lock_state, stop_reason_code, restart_count). Return-value explanation is arguably redundant given the output schema, but it adds interpretation rather than repeating field names.

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?

Schema coverage is 0%, so the description carries the full burden and mostly succeeds: it explains workspace (id or label, or "all"), status as a filter, include_metrics (single pod only, MiB units), include_system, and show_secrets (single pod only, read-only keys get "***"). It leaves limit and cursor completely unexplained, and refers to the pod parameter as `pod_name` while the schema key is `pod`, a small naming mismatch.

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?

Opens with a specific verb and resource ('List the pods (GPU/CPU containers) in a workspace') and immediately distinguishes the two modes: list, or show one pod by name. An agent can tell this apart from create_pod/delete_pod/estimate_pod 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?

Explicit routing guidance throughout: pass workspace="all" to span workspaces, omit it when the user has only one, use status to filter, use run_command against localhost for the agent's own calls, ask the user before create_access_key, and use set_port_lock/set_port_preflight for lock changes. It also names the sibling tools by name, so alternatives are concrete rather than inferred.

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