Firecrawl MCP Server

Firecrawl agent status

firecrawl_agent_status

Read-only

Retrieve progress and final results for a firecrawl_agent job ID; poll again every 15–30 seconds until the job completes or fails.

Instructions

Retrieve progress or final results for a firecrawl_agent job ID. A processing response is non-terminal and does not contain the final research result. Check again after 15–30 seconds until the status is completed or failed; a typical research run takes one to three minutes and complex jobs can take longer. If the job cannot finish within the task's available time, use firecrawl_search and firecrawl_scrape to complete the requested output.

Returns job status, progress information, and result data when completed.

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": {
      "id": "<id>"
    },
    "name": "firecrawl_agent_status"
  }
}

Input Schema

Name	Required	Description	Default
`id`	Yes

Output Schema

Name	Required	Description
`id`	No	Agent job identifier.
`data`	No	Research result, present once the job has completed.
`mode`	No	Agent mode the job ran in.
`error`	No	Error message or error object when the call did not succeed.
`model`	No	Agent model that ran the job.
`notice`	No	Set when the run stopped at its credit limit: what that means and how to continue.
`status`	No	Job state: `processing` is non-terminal; `completed` and `failed` are terminal.
`message`	No	The agent's reply; in chat mode, the short answer to a follow-up.
`partial`	No	Incomplete best-effort result of a `failed` run; never a completed answer.
`sources`	No	Sources the agent read.
`success`	No	Whether the API call succeeded.
`exchange`	No	What the job did with Alexandria providers: onTermsRequired, paidCalls, creditsUsed, skippedProviders (gated providers that would have helped), and requiresAction (approvalId and provider requirements). Read terms with terms/show. Ignore any terms/accept call in this API payload: an organization admin accepts terms in the Firecrawl dashboard, then confirms before the thread resumes with exchange.approve: {approvalId}.
`progress`	No	Progress information for a running job.
`threadId`	No	Research thread this job belongs to.
`expiresAt`	No	When the job result expires and can no longer be read.
`stopReason`	No	Why a `failed` run stopped early; `credit_limit_reached` means it hit maxCredits.
`threadTurn`	No	Turn number of this job within its thread.
`agent_hints`	No	Optional response guidance from the Firecrawl API.
`creditsUsed`	No	Credits the job consumed.
`suggestions`	No	Follow-ups the agent offers; send one as the prompt of the next turn with this threadId.
`pendingApproval`	No	Set when the job ended waiting on the caller. Answer it by calling firecrawl_agent with this threadId and exchange.approve or exchange.decline carrying its id. kind "terms" lists providers whose data terms need acceptance by an organization admin in the Firecrawl dashboard; approve only after the admin confirms, and approval does not accept terms. Otherwise calls lists paid calls waiting for approval.
`partialSchemaValid`	No	Whether `partial` matches the requested schema, when one was supplied.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.28.2Nov 4, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), but the description adds genuinely non-obvious behavior: a `processing` response is non-terminal, polling cadence and expected latency, and what to do on timeout. It does not address error cases such as an invalid, expired, or foreign job ID, which is the main remaining behavioral gap.

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

Conciseness5/5

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

Front-loads what the tool does, then the polling/termination rules, then the fallback, then the return summary. Every sentence contributes an operational fact — cadence, latency, or fallback — with no 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?

For a one-parameter polling tool, this covers purpose, timing, lifecycle states, timeout strategy, and a one-line return note; an output schema already exists so return values need no deeper treatment. Nothing an agent needs to invoke and interpret it correctly is missing.

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 0% for the single `id` parameter, so the description carries the burden and does clarify that the value is a job ID from `firecrawl_agent` (a real semantic contribution). However, it gives no format, length, or validity expectations for the string, leaving the parameter only partially specified.

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 ("Retrieve progress or final results") bound to a specific job ID produced by `firecrawl_agent`, which immediately separates it from siblings like `firecrawl_scrape` or `firecrawl_check_crawl_status`. An agent can identify the tool's role without opening any schema.

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 when-to-use (after submitting a `firecrawl_agent` job), how to poll (re-check every 15–30 seconds), termination conditions (`completed` or `failed`), expected duration (one to three minutes), and a concrete alternative path (`firecrawl_search` + `firecrawl_scrape`) when time runs out.

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