Skip to main content
Glama
Oxylabs Web API MCP Server

Oxylabs Web API MCP Server

Official

Collect queued requests

check_requests
Read-only

Retrieve results of queued scrape or crawler requests in one call. Waits up to 30 seconds for completion, returning finished results and summaries without polling.

Instructions

Collect requests the API is running in the background.

Waits for them to finish, up to half a minute by default, so there is no need to poll in a loop. Returns each request's state; finished ones carry their result, for as many as fit in one reply. The rest come as summaries marked summarized, holding as much of each page as there was room for: read on with read_result. A parser note comes once, in parser_notes, and each result names its own. Only the first few screenshots come back as images. If some are still pending, call again with only their request ids.

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": {
      "request_ids": "<request_ids>"
    },
    "name": "check_requests"
  }
}

Input Schema

NameRequiredDescriptionDefault
request_idsYesThe `request_id`s of queued requests, from `scrape` or `run_scraper` replies or an earlier call to this tool. A single id is fine.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.2

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only cover read-only/open-world safety; the description adds substantive unannotated behavior: blocking timeout, per-request state, truncation into `summarized` summaries, one-time `parser_notes`, and image-only screenshots for the first few. These are exactly the traits an agent cannot infer from structured fields.

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?

Dense but front-loaded: the core action and the no-polling benefit come first, follow-up behavior after. Slightly awkward phrasing ('up to half a minute by default', 'for as many as fit in one reply') costs a little clarity, and 'by default' hints at an option the schema does not expose.

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?

There is no output schema, so the description carries the full return-value burden and does it: states, results, summarized truncation, parser_notes, and screenshot limits are all explained. Combined with the retry instruction, an agent can call this correctly without further information.

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, and the description goes further by stating where ids come from (`scrape`, `run_scraper`, or a prior call), that a single id is acceptable, and that a retry should pass only the pending ids. It does not discuss the 50-item cap or ordering, so it sits just above baseline.

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?

Specific verb plus resource: collect background-running requests and wait for their completion. It distinguishes itself from siblings by describing the collect-and-wait semantics, and explicitly routes deep reading of truncated results to `read_result`.

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?

Gives explicit behavioral guidance: no need to poll in a loop because it blocks up to ~30s, and 'If some are still pending, call again with only their request ids' defines the retry pattern. It also names `read_result` as the follow-up path for summarized results, so the agent knows the alternative.

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