Skip to main content
Glama

mcp-cloudflare-api__search

Read-only

Search the Cloudflare OpenAPI spec. All $refs are pre-resolved inline. Response schemas describe the body as the API sends it, usually Cloudflare's envelope: { success, errors, messages, result }, plus result_info on paginated lists.

Products: cloudforce-one, access, workers, magic, dlp, email-security, realtime, devices, ai-gateway, data-security, email, intel, gateway, settings, stream, brand-protection, builds, ai-search, browser-rendering, security-center, dex, addressing, images, logpush, api_gateway, cws, load_balancers, firewall, rulesets, vectorize... (172 total)

Types:

interface OperationInfo { summary?: string; "x-api-token-group"?: string[]; // API token permissions the endpoint accepts (any one); OAuth scopes have the same names description?: string; tags?: string[]; parameters?: Array<{ name: string; in: string; required?: boolean; schema?: unknown; description?: string }>; requestBody?: { required?: boolean; content?: Record<string, { schema?: unknown }> }; // Each schema d… Through Royally: its server marks it read-only, so it runs straight away.

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": {
      "code": "<code>"
    },
    "name": "mcp-cloudflare-api__search"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeYesJavaScript async arrow function to search the OpenAPI spec
site_idNoSite to run this tool on: bb028350-9e3e-46c0-bea7-cd6c2dedf060 (https://mcp.cloudflare.com/mcp)
truncateNoCap the result at ~6,000 tokens. Set to false only when the result goes straight to a file or pipe, not into the conversation: without the cap, a broad query can return megabytes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. First observed

TDQS

C2.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered structurally. The description does add genuine behavioral context beyond that — $refs are pre-resolved inline and responses follow Cloudflare's { success, errors, messages, result } envelope with result_info on paginated lists — which helps interpret output. It still omits the code-execution model (what the sandbox permits, what the function must return, timeout or error behavior), which is the most consequential behavior for this tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is poorly structured: a products list of 172 named items and a pasted TypeScript interface dominate, displacing the operationally important information. The description ends mid-word with a corrupted fragment ("// Each schema d… Through Royally: its server marks it read-only, so it runs straight away."), which reads as accidental truncation and leaves the reader with a dangling, meaningless clause.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a code-execution search tool with a required free-form JavaScript parameter and no output schema, the description should explain the execution contract and the result shape in prose. It gestures at the response envelope but never states what the function receives or returns, and the truncation artifact signals an incomplete document. The included data model is helpful but does not cover what an agent must know to write correct code.

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%, including a clear note that truncate caps results at ~6,000 tokens, so the baseline of 3 applies. The description adds nothing about the `code` parameter — the only required one — such as the shape the arrow function must return or what helpers are in scope. It also adds nothing on site_id.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a real verb and resource — "Search the Cloudflare OpenAPI spec" — which is better than a tautology. However, the description never conveys the essential nature of this tool: it executes an agent-supplied JavaScript arrow function to perform the search. The long product enumeration and the truncated OperationInfo interface describe the searchable data, not the tool's action, so an agent finishes the description without a clear model of what invocation actually does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use or when-not-to-use guidance appears anywhere. A sibling named mcp-cloudflare-api__docs exists, and the description gives no rule for choosing between searching the spec versus fetching docs, nor any prerequisite or fallback advice. The trailing fragment about a server marking something read-only is unconnected to any usage decision.

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