Skip to main content
Glama

create_api_key

Create a new PricklyMails API key under the caller's account and return its raw value once (field raw_key); store it right away, it is never shown again. Use it to give an integration or script its own credential; the tools in this server do not need one. environment picks live (default, real billing and real SMTP) or test (a deterministic sandbox: no SMTP, no wallet debit). scopes default to the project defaults and enabled_checks to every check the plan allows when omitted, and the new key may hold only scopes the caller's session holds itself, the defaults included. Use list_api_keys to see existing keys and revoke_api_key to disable one. Requires the api_keys:create scope.

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": {
      "name": "<name>"
    },
    "name": "create_api_key"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesDisplay name for the new key, shown in the PricklyMails dashboard.
scopesNoOptional scope wire strings (e.g. email:verify:single, results:read), each one the caller's session holds; when absent the project default scopes are applied.
expires_atNoOptional RFC 3339 time at which the key stops working, in the future and at most 364 days ahead; when absent the key never expires.
environmentNoOptional environment, live or test (defaults to live). A test key (pm_test_*) runs a deterministic sandbox: the worker never dials SMTP or resolves DNS, and nothing is reserved or billed from the wallet, so it is safe for integration testing.
enabled_checksNoOptional check wire strings (syntax, mx, smtp, disposable, role, free, catchall); when absent the key runs every check the caller's plan allows, each billed per verification (see get_pricing).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / expires_at
      Added value: +{
      +  "description": "Optional RFC 3339 time at which the key stops working, in the future and at most 364 days ahead; when absent the key never expires.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / enabled_checks / description
      Previous value: -"Optional check wire strings (syntax, mx, smtp, disposable, role, free, catchall); when absent the default check set is applied."New value: +"Optional check wire strings (syntax, mx, smtp, disposable, role, free, catchall); when absent the key runs every check the caller's plan allows, each billed per verification (see get_pricing)."
    • changedInput schema / properties / scopes / description
      Previous value: -"Optional scope wire strings (e.g. email:verify:single, results:read); when absent the project default scopes are applied."New value: +"Optional scope wire strings (e.g. email:verify:single, results:read), each one the caller's session holds; when absent the project default scopes are applied."
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

No annotations are supplied, so the description carries the full burden, and it delivers: the raw key is shown exactly once and never again, test keys (pm_test_*) never dial SMTP or debit the wallet, live keys incur real billing and real SMTP, and default scopes/enabled_checks are applied when omitted. It also discloses the authorization requirement (api_keys:create scope) and the privilege constraint that the new key cannot exceed the caller's session scopes.

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?

The most decision-critical facts (one-time raw_key return, scope requirement) are front-loaded, and every sentence carries content rather than filler. It is a dense single paragraph, though, and the scopes/enabled_checks sentence packs two defaults and a privilege constraint together, which slightly hurts scanability.

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 credential-issuing mutation tool with no annotations and no output schema, the description covers the return shape (raw_key, one-time), the security constraint on scopes, environment semantics and their billing/SMTP consequences, defaults for both optional arrays, and the required authorization scope. An agent has enough to call this safely and correctly in one shot.

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 description coverage is 100%, so the baseline applies and the description largely restates what the schema already documents (environment defaults to live, enabled_checks defaults to all plan-allowed and bills per verification, scopes default to project defaults and must be held by the caller). The only marginal addition is that the default scopes themselves are subject to the caller's session-scope ceiling, which is not clearly spelled out in the schema.

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 ('Create a new PricklyMails API key under the caller's account'), plus the notable side effect that the raw value is returned once in field raw_key. It also names its siblings (list_api_keys, revoke_api_key), so an agent can separate creating from listing or revoking without inspecting schemas.

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 says when to use it ('give an integration or script its own credential') and when not to ('the tools in this server do not need one'), and points to list_api_keys for visibility and revoke_api_key for disabling. The live-vs-test choice is framed as a use-case decision for integration testing versus real billing.

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