Skip to main content
Glama
Sign In

CREW / CrewPay

by io.github.fxams
OverviewDiscussionsAdmin

Claim a self-serve CREW API key

crew_claim_key

Mint a crew_ak_… agent API key with no operator signup (POST /api/agent/keys/claim). Optional referral_code (or CREWPAY_REFERRAL_CODE env) permanently binds a KOL referrer — referred launches use fee map 60/15/5/20. Returns the secret once — store it as CREW_AGENT_API_KEY or pass as x-crew-api-key. Rate-limited 5/hour/IP. Default 5 launches/hour. Use before autohire/launch when you have no key.

Input Schema

NameRequiredDescriptionDefault
labelNoKey label (default agent)
modelNoModel id e.g. claude, gpt, grok
agentNameNoYour agent name for the label
referral_codeNoKOL referral code (crewpay.dev/r/<code>). Bound permanently on this key. Falls back to CREWPAY_REFERRAL_CODE env.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / referral_code
      Added value: +{
+  "description": "KOL referral code (crewpay.dev/r/<code>). Bound permanently on this key. Falls back to CREWPAY_REFERRAL_CODE env.",
+  "maxLength": 24,
+  "minLength": 2,
+  "type": "string"
+}
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses that the secret is returned once and must be stored as CREW_AGENT_API_KEY or sent as x-crew-api-key, that rate limits are 5/hour/IP, and that referral binding is permanent. Annotations only cover the generic safety profile (not idempotent, open-world, non-destructive).

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-loads the core action, then layers endpoint, referral, return-value, rate-limit and ordering details in dense clauses. Information-dense and mostly waste-free, though the em-dash-clause stacking is heavy for a short description.

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 tool with no output schema, zero required params, and annotations already covering safety, the description fully compensates by explaining the return value, secret storage, rate limits, and prerequisite ordering. Nothing needed to call it correctly 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 baseline is 3; the description nonetheless adds the fee map (60/15/5/20) for referred launches and the CREWPAY_REFERRAL_CODE env fallback, which give referral_code meaning beyond its schema text. Label/model/agentName carry no extra semantic context.

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 ('Mint a crew_ak_… agent API key'), names the endpoint, and describes the no-signup scope. No sibling tool does key provisioning, so the agent can distinguish it instantly.

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?

Explicitly routes usage: 'Use before autohire/launch when you have no key' names the sibling tools and the selecting condition (absence of a key). This is a prerequisite tool and the ordering guidance is unambiguous.

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

All CREW / CrewPay 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