Skip to main content
Glama

Mint an API key — no account, session or browser needed

keys_create

The one endpoint that needs no key. Send {} for a dv_sk_test_ sandbox key (real data, small daily quota, never billed, no /research). Send {"email":"…"} for a dv_sk_live_ key on a new prepaid account; the first key for an email carries 1 starter credit ($1.00). Send it with an existing key as the bearer to mint a sibling key on the same account (rotation). The raw key is returned once. The email is a contact label, not a credential. Limited to 10 keys per address per day. The raw key is in the result once: keep it and send it as Authorization: Bearer on REST calls (or have the host re-add this server with that header). With a key already configured, mints a sibling on the same account. (POST https://app.deepvalues.ai/api/v1/keys — no charge; needs no credentials)

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": "keys_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
emailNoContact address for a dv_sk_live_ key (1 starter credit the first time). Omit for a never-billed dv_sk_test_ sandbox key.
labelNoOptional name for the key.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Adds substantial context beyond the annotations: 10 keys per address per day, raw key shown only once, email is a contact label not a credential, sandbox is never billed and excludes /research, first live key carries 1 starter credit. Annotations only cover readOnly/openWorld/idempotent/destructive flags; this fills in rate limits and secret-handling. A near-5, held back only because the return shape of the mint result beyond the raw key is left implicit.

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?

Front-loads the key facts well, but repeats itself: 'The raw key is returned once' and 'The raw key is in the result once' say the same thing, and 'With a key already configured, mints a sibling on the same account' restates the earlier rotation sentence. Roughly a fifth of the text is 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?

For a zero-required-param minting tool with no output schema, it covers everything an agent needs: endpoint and method, auth requirements, quota, billing behavior, secret-once handling, and how to use the returned key on subsequent calls.

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, but the description goes further by explaining the consequence of each parameter: omitting email yields a never-billed test key, including it creates a live prepaid account with a starter credit, and the address is a label rather than an auth factor.

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+resource (mint an API key) and immediately scopes it: 'The one endpoint that needs no key.' The three modes (sandbox, live, rotation) are enumerated, so an agent can tell exactly what it is versus siblings like keys_me.

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?

Explicit conditions are given per mode: send {} for a sandbox key, send {"email":"…"} for a live key on a new prepaid account, send with an existing bearer key to rotate. What's absent is any mention of when to prefer a sibling such as keys_me for inspection rather than minting.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources