Skip to main content
Glama

Firecrawl MCP Server

firecrawl_scrape

Scrape one URL and return its content: markdown by default, or HTML, links, screenshots, branding data, a targeted answer, or JSON matching a supplied schema. Use it when the request identifies a page and needs its content or defined fields. Use firecrawl_search when additional web sources are needed; on an authenticated session, firecrawl_map lists a site's URLs and firecrawl_crawl collects a set of pages.

Firecrawl may serve recently indexed content; set maxAge: 0 for a live fetch or a smaller maxAge to bound staleness. A successful response does not by itself confirm the page is still current. Browser actions can change the live page when interactive actions are enabled. Authenticated responses can include a metadata.scrapeId for optional scrape feedback.

On an authenticated session with Alexandria access, firecrawl_search with sources unset and firecrawl_find_tools can discover providers for the same fields across several pages; a matching provider returns typed records in one call. Keyless sessions have no provider matches.

Alexandria mode, on an authenticated session with Alexandria access: alexandria selects catalogued capability execution and is mutually exclusive with url.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNo
proxyNo
maxAgeNo
mobileNo
formatsNo
parsersNo
profileNo
timeoutNoExecution timeout in milliseconds.
waitForNo
locationNo
lockdownNo
redactPIINo
requestIdNoIdempotency key bound to one Alexandria execution payload. Generated when omitted and returned with the result.
alexandriaNoCatalogued Alexandria capability invocation, mutually exclusive with url. One {provider, capability, options} object or an array of 1-10, with contracts available through firecrawl_search or firecrawl_find_tools. Each call may include version to pin a published workflow; omitting it uses latest. Only requestId and timeout are supported alongside alexandria. The selected contract marks required inputs and any requiresOneOf groups (at least one member per group); it may include example.request/example.response and response.key (which may differ from records). Where pagination is declared, its fields govern paging with the same filters; catalogue next is separate from provider pagination. Returns per-capability results in data.alexandria with data, records, or an error with a code; individual capabilities can fail even when the outer response succeeds. Requires an API key on a team with Alexandria enabled. Some providers require accepted terms; blocked requests return the applicable requirements.
pdfOptionsNo
toolDetailNoURL mode only: domain discovery detail, summary by default; compact returns provider/capability/description, full includes contracts. Ignored with alexandria.
domainToolsNoURL mode only: include domain-matched Alexandria tools for the page in tools on the returned document. Ignored with alexandria.
excludeTagsNo
includeTagsNo
jsonOptionsNo
queryOptionsNo
storeInCacheNo
onlyMainContentNo
screenshotOptionsNo
zeroDataRetentionNo
removeBase64ImagesNo
skipTlsVerificationNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNoAlexandria mode: per-capability results in `data.alexandria`, each with `data`, `records`, or an `error`.
htmlNoProcessed HTML of the page.
jsonNoStructured data matching the requested JSON schema or prompt.
menuNoMenu data extracted from the page.
audioNoAudio extracted from the page.
errorNoError message or error object when the call did not succeed.
linksNoLinks found on the page.
pagesNoPhysical PDF pages, when `parsers[].pages` is set.
toolsNoDomain-matched Alexandria tools for the page, when `domainTools` is set.
videoNoVideo extracted from the page.
answerNoTargeted answer to the question that was asked of the page.
blocksNoTyped PDF layout blocks, when `parsers[].blocks` is set.
imagesNoImages found on the page.
actionsNoResults of the browser actions that ran during the scrape.
messageNoGuidance that accompanies the result.
productNoProduct data extracted from the page.
rawHtmlNoUnprocessed HTML of the page.
receiptNoBilling receipt for the execution.
successNoWhether the API call succeeded.
summaryNoSummary of the page content.
warningNoNon-fatal warning about the result.
brandingNoBranding data extracted from the page.
deliveryNo`retained` when the full result stayed server-side instead of being inlined.
markdownNoPage content as markdown.
metadataNoPage metadata; authenticated responses can include `metadata.scrapeId` for scrape feedback.
nextToolNoA follow-up tool call (`{name, arguments}`) that continues or inspects this result.
requestIdNoIdentifier of this Alexandria execution.
scrape_idNoIdentifier of the underlying scrape.
attributesNoValues collected by the requested attribute selectors.
highlightsNoHighlighted passages from the page.
screenshotNoScreenshot of the page.
agent_hintsNoOptional response guidance from the Firecrawl API.
creditsCostNoCredits this call consumed.
workspaceIdNoWorkspace holding a retained result, for inspection through virtual Bash.
feedbackToolNoPointer to the feedback tool for reporting how this result served the task.
responseBytesNoSize of the full result in bytes.
changeTrackingNoChange-tracking comparison against the previous scrape.
idleTtlSecondsNoSeconds a retained workspace stays available while idle.
estimatedTokensNoEstimated token cost of the full result.
inlineTokenBudgetNoToken budget above which a result is retained rather than inlined.
tokenEstimateMethodNoHow `estimatedTokens` was derived.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, but the description adds genuinely non-obvious behavior: cached/recently-indexed content and the maxAge=0 escape hatch, the caveat that a successful response does not confirm freshness, that browser actions can mutate the live page, scrapeId feedback, and keyless-session limitations. It stops short of describing pagination or partial-failure behavior for URL mode, so it is not a 5.

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

Conciseness3/5

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

The first paragraph is well front-loaded and earns its place, but the second and third paragraphs are dense run-on sentences with heavy qualifiers ('On an authenticated session with Alexandria access, firecrawl_search with sources unset and firecrawl_find_tools can discover providers...'). The content is relevant but the structure makes it hard to scan.

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

Completeness4/5

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

Given a 27-parameter tool with nested objects and an output schema, the description covers the important mode distinctions, freshness semantics, auth requirements, and the alexandria-exclusive mode. Return values are covered by the output schema. The main gap is the undocumented parameter surface, which is partly excusable given the volume.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 19% across 27 parameters, so the description carries a heavy burden. It glosses the format options and explains maxAge and the alexandria/url mutual exclusion, but leaves the majority of parameters (proxy, location, parsers, profile, screenshotOptions, jsonOptions, redactPII, lockdown, and more) undocumented in both places.

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?

Opens with a specific verb+resource ('Scrape one URL') and enumerates the concrete output formats the caller can request. It explicitly separates itself from firecrawl_search, firecrawl_map, and firecrawl_crawl by naming the condition that selects each.

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?

States the selection condition ('when the request identifies a page and needs its content or defined fields') and names the alternatives with their own triggers. The Alexandria paragraph adds a clear mutually-exclusive usage path with its own precondition (authenticated session with Alexandria access).

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.