Firecrawl MCP Server

Firecrawl scrape

firecrawl_scrape

Read-only

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. A named browser profile loads saved session data without saving changes to it. Authenticated responses can include a metadata.scrapeId for optional scrape feedback.

On an authenticated session with Alexandria access, firecrawl_search 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

Name	Required	Description
`url`	No
`proxy`	No
`maxAge`	No
`mobile`	No
`formats`	No
`parsers`	No
`profile`	No	Loads a saved browser profile without saving changes to it.
`timeout`	No	Execution timeout in milliseconds.
`waitFor`	No
`location`	No
`lockdown`	No
`objective`	Yes	The user's underlying goal for this call, in one sentence: what they are ultimately trying to accomplish, not a restatement of the URL or query. Reuse it across related calls. Avoid sensitive information.
`redactPII`	No
`requestId`	No	Idempotency key bound to one Alexandria execution payload. Generated when omitted and returned with the result.
`alexandria`	No	Catalogued 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.
`pdfOptions`	No
`toolDetail`	No	URL mode only: domain discovery detail, summary by default; compact returns provider/capability/description, full includes contracts. Ignored with alexandria.
`domainTools`	No	URL mode only: include domain-matched Alexandria tools for the page in tools on the returned document. Ignored with alexandria.
`excludeTags`	No
`includeTags`	No
`jsonOptions`	No
`queryOptions`	No
`storeInCache`	No
`onlyMainContent`	No
`screenshotOptions`	No
`zeroDataRetention`	No
`removeBase64Images`	No
`skipTlsVerification`	No

Output Schema

TableJSON Schema

Name	Required	Description
`data`	No	Alexandria mode: per-capability results in `data.alexandria`, each with `data`, `records`, or an `error`.
`html`	No	Processed HTML of the page.
`json`	No	Structured data matching the requested JSON schema or prompt.
`menu`	No	Menu data extracted from the page.
`audio`	No	Audio extracted from the page.
`error`	No	Error message or error object when the call did not succeed.
`links`	No	Links found on the page.
`pages`	No	Physical PDF pages, when `parsers[].pages` is set.
`tools`	No	Domain-matched Alexandria tools for the page, when `domainTools` is set.
`video`	No	Video extracted from the page.
`answer`	No	Targeted answer to the question that was asked of the page.
`blocks`	No	Typed PDF layout blocks, when `parsers[].blocks` is set.
`images`	No	Images found on the page.
`actions`	No	Results of the browser actions that ran during the scrape.
`message`	No	Guidance that accompanies the result.
`product`	No	Product data extracted from the page.
`rawHtml`	No	Unprocessed HTML of the page.
`receipt`	No	Billing receipt for the execution.
`success`	No	Whether the API call succeeded.
`summary`	No	Summary of the page content.
`warning`	No	Non-fatal warning about the result.
`branding`	No	Branding data extracted from the page.
`delivery`	No	`retained` when the full result stayed server-side instead of being inlined.
`markdown`	No	Page content as markdown.
`metadata`	No	Page metadata; authenticated responses can include `metadata.scrapeId` for scrape feedback.
`nextTool`	No	A follow-up tool call (`{name, arguments}`) that continues or inspects this result.
`requestId`	No	Identifier of this Alexandria execution.
`scrape_id`	No	Identifier of the underlying scrape.
`attributes`	No	Values collected by the requested attribute selectors.
`highlights`	No	Highlighted passages from the page.
`screenshot`	No	Screenshot of the page.
`agent_hints`	No	Optional response guidance from the Firecrawl API.
`creditsCost`	No	Credits this call consumed.
`workspaceId`	No	Workspace holding a retained result, for inspection through virtual Bash.
`feedbackTool`	No	Pointer to the feedback tool for reporting how this result served the task.
`responseBytes`	No	Size of the full result in bytes.
`changeTracking`	No	Change-tracking comparison against the previous scrape.
`idleTtlSeconds`	No	Seconds a retained workspace stays available while idle.
`estimatedTokens`	No	Estimated token cost of the full result.
`inlineTokenBudget`	No	Token budget above which a result is retained rather than inlined.
`tokenEstimateMethod`	No	How `estimatedTokens` was derived.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 17, 2026
- addedInput schema / required
```
Added value: +[
+  "objective"
+]
```
Changed1 schema field changedOct 14, 2026
- removedInput schema / required
```
Removed value: -[
-  "objective"
-]
```

Changed1 schema field changedOct 13, 2026

removedOutput schema / description

Removed value: -"A scraped document, or the Alexandria execution envelope when `alexandria` was passed."

Changed1 schema field changedOct 12, 2026
- addedInput schema / required
```
Added value: +[
+  "objective"
+]
```

Changed1 schema field changedOct 12, 2026

addedInput schema / properties / objective

Added value: +{
+  "description": "The user's underlying goal for this call, in one sentence: what they are ultimately trying to accomplish, not a restatement of the URL or query. Reuse it across related calls. Avoid sensitive information.",
+  "maxLength": 1000,
+  "minLength": 1,
+  "type": "string"
+}

Changed1 schema field changedOct 9, 2026

changedInput schema / properties / formats / items / enum

Previous value: -[
-  "markdown",
-  "html",
-  "rawHtml",
-  "screenshot",
-  "links",
-  "summary",
-  "changeTracking",
-  "branding",
-  "json",
-  "query",
-  "audio"
-]New value: +[
+  "markdown",
+  "html",
+  "rawHtml",
+  "screenshot",
+  "links",
+  "images",
+  "summary",
+  "changeTracking",
+  "branding",
+  "json",
+  "query",
+  "audio"
+]

Changed2 schema fields changedOct 6, 2026
- addedInput schema / properties / profile / description
```
Added value: +"Loads a saved browser profile without saving changes to it."
```
- removedInput schema / properties / profile / properties / saveChanges
```
Removed value: -{
-  "type": "boolean"
-}
```
First observedSep 29, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations only declare readOnly/openWorld/non-destructive, so the description adds real behavioral context: recently indexed content may be served, maxAge=0 forces a live fetch, success does not prove the page is current, profiles load but never persist changes, authenticated responses carry metadata.scrapeId, and Alexandria requires an API team key with per-capability failures inside a successful envelope.

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 output options before any conditional guidance, and every paragraph does distinct work (routing, freshness, profiles, Alexandria). It runs long and the final Alexandria paragraph is dense, but no sentence is pure filler.

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?

An output schema exists, so return-shape explanation is rightly omitted, and the description is careful to note the alexandria return path and failure mode. For a 28-parameter tool with one required field, the description orients the agent to the main modes, though the long tail of tuning parameters remains undocumented.

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?

With 28 parameters at 25% schema description coverage, the description must carry weight, and it does explain maxAge, the formats family, profile persistence, URL-vs-Alexandria exclusivity, and the per-capability option/version semantics. However, most parameters (proxy, parsers, lockdown, waitFor, location, redactPII, storeInCache, zeroDataRetention, include/excludeTags, etc.) get no mention anywhere, so the compensation is partial.

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 ('Scrape one URL and return its content') and enumerates the concrete output shapes (markdown default, HTML, links, screenshots, branding, query answer, schema-bound JSON). It also distinguishes itself from named siblings (search, map, crawl) and from the Alexandria invocation mode, so an agent can pick it 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 an explicit selection rule ('Use it when the request identifies a page and needs its content or defined fields') plus conditional alternatives: search when more web sources are needed, map for URL listing, crawl for page sets, and the alexandria/url mutual exclusion. The only unaddressed sibling is firecrawl_parse, a minor omission against otherwise complete routing.

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

All Firecrawl MCP Server tools Inspect

Try in Browser

Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.