Skip to main content
Glama
Sign In

Runcrate

by io.github.aeonmindai
OverviewDiscussionsAdmin

List model calls

list_requests
Read-onlyIdempotent

List calls to Runcrate's models (chat, embeddings, images, speech, /v1/messages, /v1/responses) from this environment, newest first, kept 30 days: model, status, outcome, took_ms, ttft_ms, tokens, tokens_per_second, finish_reason, tool_calls, cost, end_user, session and tags. Prompts and answers are never stored. outcome: "error" finds failures: each failed call carries error.message (what happened) and error.next_step (what to do about it), and get_request with an id has its timing. Filter by session to read one agent run's calls (newest first), end_user for one of your users, tag for "key=value" pairs sent in X-Runcrate-Tags. Without from it covers the last 24 hours. When next_cursor is not null, pass it as cursor for the next page. Docs: https://www.runcrate.ai/docs/api-reference/model-calls/list-model-calls

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": "list_requests"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoEnd time, ISO 8601 (default now)
keyNoOnly calls made with this API key id
tagNoOnly calls with this tag, as key=value, e.g. "feature=search"; a list needs every one
fromNoStart time, ISO 8601 (default 24 hours ago; at most 30 days back)
limitNoHow many calls (default 50, max 100)
modelNoOnly calls to this model id
cursorNonext_cursor from the previous page
outcomeNoOnly calls that succeeded (ok) or failed (error)
sessionNoOnly calls sent with this X-Runcrate-Session
end_userNoOnly calls sent with this end user (OpenAI `user`, Anthropic `metadata.user_id`)
endpointNoOnly calls to this endpoint
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

A4.8/5.0
Behavior5/5

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

Annotations already establish a safe read-only, idempotent, non-destructive operation, and the description adds real behavioral context beyond them: 30-day retention, 30-day max lookback, prompt/answer non-storage, newest-first ordering, error.message/error.next_step on failed calls, and cursor-based paging.

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 scoping, then filters, then pagination, then docs link — a sensible order. The mid-sentence enumeration of returned fields (model, status, outcome, took_ms, ttft_ms, ...) is long, though defensible given the absence of an output schema.

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 13 optional parameters, no output schema, and a large sibling set, the description covers ordering, retention, defaults, pagination, filter semantics, error inspection, and escalation to get_request and the docs URL. Nothing essential for a correct invocation is missing.

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 100%, so the baseline is 3; the description still earns above-baseline credit by explaining tag syntax ("key=value" pairs sent in X-Runcrate-Tags), session as "one agent run", the 24-hour default for from, and how next_cursor maps to cursor. It does not spell out workspace/environment/key semantics, which remain schema-only.

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+resource ("List calls to Runcrate's models") and immediately scopes it (endpoints enumerated, "from this environment", "newest first", "kept 30 days"). It distinguishes itself from the sibling get_request by noting get_request with an id returns one call's timing.

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 concrete routing rules: use outcome="error" to find failures, session to read one agent run, end_user for a specific user, tag for X-Runcrate-Tags pairs, and get_request for a single call. Also states the default window (last 24 hours without from) and the pagination contract when next_cursor is non-null.

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