ApiClay

Call an ApiClay API (billed)

apiclay_call_api

Destructive

Call /v1/api// through the ApiClay gateway with your account. Billing is the gateway's: the vendor's trial requests first, then your plan, then pay-as-you-go credits (calls through an ApiClay proxy never use trial or plan); failed calls are refunded. Returns status, content type, X-ApiClay-* headers and the body (parsed JSON, text up to 256 KB with a truncated flag, or base64 for binary; PNG/JPEG/GIF/WebP images also come as an image block). Use apiclay_describe_api first to get the parameters. vendor apiclay with path extract is ApiClay's own URL extraction (GET with query url and, in an X-Proxy-Config header, your own proxy or an ApiClay proxy choice, or POST with body {urls, output_mode, render_mode, ..., proxy} returning NDJSON; billed per extracted URL plus the browser and proxy fees it used).

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": {
      "vendor": "<vendor>",
      "path": "<path>"
    },
    "name": "apiclay_call_api"
  }
}

Input Schema

Name	Required	Description	Default
`body`	No	JSON body for POST/PUT/PATCH/DELETE routes (the route's public body fields).
`path`	Yes	Route path after the vendor (e.g. "search" or "/search"), or the table name for table APIs. No query string.
`query`	No	Query parameters (the route's public query fields; page for tables).
`method`	No		GET
`vendor`	Yes	Vendor username, as returned by apiclay_search_apis.
`headers`	No	Headers: the route's declared public headers and the X-ApiClay-* control headers (e.g. X-ApiClay-Html: markdown). X-Proxy-Config passes only on routes that use the buyer's proxy. Credentials and cookies are always dropped.

Output Schema

Name	Required	Description
`body`	No	Parsed JSON, text, or base64 according to body_encoding.
`path`	No
`error`	No
`method`	No
`status`	No
`vendor`	No
`headers`	No
`body_note`	No
`truncated`	No
`body_bytes`	No
`request_id`	No
`content_type`	No
`body_encoding`	No
`dropped_headers`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already flag destructive, openWorld, non-idempotent and non-read-only, but the description adds substantive context: the billing waterfall (trial, then plan, then pay-as-you-go credits, with proxies bypassing trial/plan) and refunds on failed calls. It also explains header handling (X-ApiClay-* controls, X-Proxy-Config only on buyer-proxy routes, credentials/cookies dropped) and return shapes including image blocks.

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 the core action and billing model, then return format, then the special case. Dense but every sentence carries operational information; the long parenthetical clauses in the extract sentence require re-reading but are not filler.

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?

Covering a billed, destructive, open-world call with nested body/headers/query objects, the description addresses billing, failure refunds, header semantics and return payload variants. An output schema exists so return values need not be exhaustively specified, yet the description still summarizes them adequately.

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 83 percent, so the schema already documents most parameters. The description still adds meaning beyond it: path is a route suffix without query string, vendor comes from apiclay_search_apis, X-Proxy-Config passes only on proxy routes, and the extract route's GET/POST body shape with NDJSON output.

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 ('Call /v1/api/<vendor>/<path> through the ApiClay gateway') and clarifies the billing scope. It explicitly names apiclay_describe_api as the prerequisite step so the agent can distinguish this from its sibling.

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?

Gives clear sequencing guidance ('Use apiclay_describe_api first to get the parameters') and a worked special case for vendor apiclay with path extract. It does not state when not to use the tool or lay out trade-offs against apiclay_search_apis, but the intended invocation context is clear.

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

All ApiClay tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?