Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Scored across 3 tools
The three tools have distinct input sources: parse for local documents, scrape for a single URL, and search for web queries. However, parse and scrape both return similar content types (markdown, HTML, links, etc.), and the verbose descriptions referencing many other tools could cause minor confusion about boundaries.
All tools follow a consistent firecrawl_ prefix with a distinct verb (parse, scrape, search), yielding a predictable naming pattern throughout.
With only 3 tools, the set is too thin for the broad web scraping, crawling, and searching scope implied by the descriptions. The descriptions reference many additional tools (crawl, map, find_tools, research_*), indicating the surface is a small subset of a much larger API.
Significant gaps exist: there are no tools for crawling multiple pages, mapping site URLs, or using the research/Alexandria capabilities mentioned in the descriptions. Agents may try to call referenced but absent tools (e.g., firecrawl_crawl, firecrawl_map) and fail.
Parse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema. Supported inputs include common HTML, PDF, Word, RTF, OpenDocument, and spreadsheet files; PDF parsing can be bounded with pdfOptions.maxPages.
Local MCP reads filePath from the server filesystem. Hosted MCP uses two calls: first provide filePath to receive upload instructions, upload locally, then call again with the returned uploadRef; do not send both fields together. Remote web URLs belong in firecrawl_scrape.
Set redactPII to request redaction of personally identifiable information in the returned content. zeroDataRetention requires an eligible authenticated account; omit it for anonymous keyless use. Returns upload instructions for hosted phase one or parsed document content for the final call. Authenticated final responses can include a data.metadata.scrapeId for optional parse feedback.
| Name | Required | Description | Default |
|---|---|---|---|
| proxy | No | ||
| maxAge | No | Ignored: parse never reuses or stores indexed content. | |
| formats | No | ||
| parsers | No | ||
| filePath | No | Phase 1 only: path to the local file on the caller/harness machine. Hosted MCP will not read or stat this path; it is used only to produce upload instructions. | |
| redactPII | No | ||
| uploadRef | No | Phase 2 only: short-lived upload reference returned by phase 1 after the local PUT upload completes. | |
| pdfOptions | No | ||
| contentType | No | Phase 1 MIME type override. If omitted, the server infers it from the file extension without reading the file. | |
| excludeTags | No | ||
| includeTags | No | ||
| jsonOptions | No | ||
| queryOptions | No | ||
| storeInCache | No | ||
| onlyMainContent | No | ||
| declaredSizeBytes | No | Optional phase 1 size declaration. Hosted MCP does not stat the file; provide this only if the caller already knows it. | |
| zeroDataRetention | No | ||
| removeBase64Images | No | ||
| skipTlsVerification | No |
| Name | Required | Description |
|---|---|---|
| raw | No | Response body when it was not JSON. |
| data | No | Parsed document content; can include `data.metadata.scrapeId` for parse feedback. |
| mode | No | Which phase of the hosted flow produced this response. |
| error | No | Error message or error object when the call did not succeed. |
| notes | No | Hosted phase one: constraints on completing the upload flow. |
| upload | No | Hosted phase one: how to upload the local file. |
| message | No | Guidance for the next call. |
| success | No | Whether the API call succeeded. |
| warning | No | Non-fatal warning about the result. |
| agent_hints | No | Optional response guidance from the Firecrawl API. |
| nextToolCall | No | Hosted phase one: the second `firecrawl_parse` call to make once the upload succeeds, as `{name, arguments}`. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds substantial behavior beyond them: the two-phase upload protocol, the PII redaction option, the zeroDataRetention auth requirement, and what each phase returns. This is rich context that an agent could not infer from the annotations alone.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but well-structured: purpose and formats first, then the local/hosted flow distinction, then behavioral options, then return values. Every sentence carries information, with only the final scrapeId sentence being marginal.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given a 19-parameter tool with a nested schema and a two-phase hosted flow, the description covers the critical decision points and return behavior; an output schema exists, so return details are supplementary rather than required. Minor gaps remain around several optional tuning parameters, but nothing blocking correct invocation is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 26% across 19 parameters, so the description must compensate. It explains filePath, uploadRef, redactPII, zeroDataRetention, pdfOptions.maxPages, and formats, but leaves proxy, parsers, contentType, includeTags/excludeTags, jsonOptions, queryOptions, storeInCache, onlyMainContent, removeBase64Images, skipTlsVerification, and declaredSizeBytes largely to the schema, which only partially documents them.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (parse) and resource (one supported document) and enumerates the output formats (markdown, HTML, links, summary, query answers, schema JSON) plus supported input types. It explicitly separates itself from firecrawl_scrape by stating that remote web URLs belong there, so an agent can distinguish it from siblings without opening schemas.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives explicit routing: local MCP reads filePath directly, hosted MCP requires a two-call upload flow with filePath then uploadRef, and remote URLs go to firecrawl_scrape. It also states the do-not rule (never send both fields together) and the auth condition for zeroDataRetention, which is exactly the when/when-not guidance needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | ||
| proxy | No | ||
| maxAge | No | ||
| mobile | No | ||
| formats | No | ||
| parsers | No | ||
| profile | No | ||
| timeout | No | Execution timeout in milliseconds. | |
| waitFor | No | ||
| location | No | ||
| lockdown | No | ||
| 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 |
| 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. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the read-only annotations, the description discloses non-obvious behavior: Firecrawl may serve recently indexed content, maxAge controls staleness, a successful response does not confirm freshness, and browser actions can mutate the live page. It also notes the authenticated-only scrapeId and the Alexandria API-key/terms requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The core capability and routing guidance are front-loaded and every paragraph carries information, but the third and fourth paragraphs (Alexandria provider discovery, catalogue paging) are dense and overlap with what the alexandria schema description already states.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex open-world tool with a rich output schema and strong annotations, the description covers mode selection, auth prerequisites, and freshness caveats well. The remaining gap is the large set of undocumented behavior-tuning parameters, which an agent would have to infer from names alone.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 has to compensate and only partly does: it explains maxAge semantics, the formats enumeration, and the alexandria/url exclusivity and payload shape. Parameters like proxy, mobile, parsers, profile, waitFor, location, lockdown, redactPII, screenshotOptions, and jsonOptions/queryOptions remain unexplained anywhere.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The first sentence states a specific verb and resource ('Scrape one URL and return its content') and enumerates the output formats, so an agent knows exactly what comes back. It also explicitly distinguishes itself from firecrawl_search, firecrawl_map, and firecrawl_crawl, which is what separates it from siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states the selecting condition clearly ('Use it when the request identifies a page and needs its content or defined fields') and names alternatives with their triggering conditions ('Use firecrawl_search when additional web sources are needed'), plus the map/crawl split. Alexandria mode's mutual exclusivity with url is also spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search web, news, or image sources and return ranked results with query-relevant highlights. Each web result is a title, URL, and description; use firecrawl_scrape on a result URL when the excerpt is not enough.
Authenticated search also returns matching Alexandria data providers in data.tools (companies, people, jobs, finance and filings, public records and government spending, real estate, places and restaurants, retail and prices, package registries and developer data, news, research, and more). Prefer a provider over scraping pages when the task needs the same fields across several entities, exact figures or timestamps, provenance, or many records; use web results when they already answer the question. A search with sources: ["web"] omits semantic provider discovery; domainTools: true can still return website-matched tools. Web-only results use domainTools: false.
On an authenticated session, tool matches describe available capabilities; firecrawl_find_tools returns their contracts and firecrawl_scrape with an alexandria body executes a selected capability. Keyless sessions get no Alexandria matches in data.tools.
For a programming question, add categories: ["developer"]; its hits return in data.web with category: "developer". categories: ["research"] restricts web results to research-affiliated websites; the firecrawl_research_* tools are a separate surface over paper abstracts and full text (PubMed, bioRxiv, medRxiv, arXiv). Query operators, domain filters, categories, toolDetail and scrapeOptions are described on their parameters. Returns source-type result groups and usage metadata. Authenticated responses can include an id for optional search feedback.
| Name | Required | Description | Default |
|---|---|---|---|
| tbs | No | ||
| limit | No | ||
| query | Yes | Query for web and semantic tool discovery. Operators include quoted phrases, `-term`, `site:host`, `inurl:term`, `intitle:term`, and `related:host`; the set is non-exhaustive. Catalogue browsing is available through firecrawl_find_tools. | |
| filter | No | ||
| sources | No | Search sources; authenticated sessions default to web + alexandria, keyless sessions to web only. A search with sources: ["web"] omits semantic provider discovery; domainTools: true can still return website-matched tools. Web-only results use domainTools: false. Use ["alexandria"] alone for provider discovery without web results. | |
| location | No | ||
| objective | No | Optional broader goal for this search, if known. Avoid sensitive information. | |
| categories | No | Limit results to specific source types. `research` restricts ordinary web results to research-affiliated websites and returns page snippets, which is separate from the `firecrawl_research_*` tools that search paper abstracts and full text across biomedical (PubMed, bioRxiv, medRxiv) and arXiv literature; `pdf` searches PDF results; `developer` searches an index built for coding agents over public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. `developer` returns hits in `data.web` with `category: "developer"`; the other categories also filter `data.web`. | |
| enterprise | No | ||
| highlights | No | Return query-relevant page excerpts for web and news results when available (default). Highlights appear in web `description` and news `snippet`; otherwise, original snippets are returned. Set to false to keep the original search snippets. | |
| toolDetail | No | Compact by default. Compact returns only provider, capability and description; full includes contracts. Inspect selected compact tools with firecrawl_find_tools providers and capabilities. | |
| clientModel | No | Optional model identifier, if known. | |
| domainTools | No | Include domain-matched tools for result URLs. Defaults to true when Alexandria is combined with web, news or images; semantic-only search leaves domain matching off. | |
| scrapeOptions | No | Attach page content for web results in the same call. These fetches ignore maxAge, so use firecrawl_scrape when you need a live fetch. scrapeOptions fetches web pages, never Alexandria provider tools. | |
| excludeDomains | No | Hostnames to leave out of results. Mutually exclusive with includeDomains. | |
| includeDomains | No | Hostnames to restrict results to. Mutually exclusive with excludeDomains. |
| Name | Required | Description |
|---|---|---|
| id | No | Search identifier, for optional `firecrawl_search_feedback`. |
| data | No | Ranked results grouped by source, such as `web`, `news`, `images`, and `alexandria`. |
| error | No | Error message or error object when the call did not succeed. |
| tools | No | Domain-matched Alexandria tools for the results. |
| success | No | Whether the API call succeeded. |
| warning | No | Non-fatal warning about the result. |
| nextTool | No | A follow-up tool call that continues this search. |
| agent_hints | No | Optional response guidance from the Firecrawl API. |
| creditsUsed | No | Credits this search consumed. |
| feedbackTool | No | Pointer to the feedback tool for this search. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/openWorld/non-destructive, and the description goes well beyond them: keyless vs authenticated session behavior, defaults for sources and domainTools, when data.tools is omitted, the optional id for feedback, and the note that highlights is on by default. These are real operational traits an agent needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
It is dense and long, but front-loaded and organized: core behavior first, then provider discovery, then category guidance. Most sentences carry new information, though some routing detail is repeated across the description and the schema's own parameter descriptions.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 16-parameter, nested-schema tool with an output schema present, the description covers the decision-relevant behavior: source defaults, authentication effects, provider discovery flow, and category semantics. Return-value detail is appropriately left to the output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 69%, and the description meaningfully supplements it for sources, categories, toolDetail, domainTools, highlights, and scrapeOptions defaults and interactions. Some parameters (tbs, filter, location, objective, enterprise, clientModel) receive no explanation anywhere, so it is not fully compensating for the gap, but the added value is substantial.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The opening sentence names the specific action (search) and resources (web, news, image sources) and states the return shape (ranked results with query-relevant highlights). It also distinguishes itself from siblings by naming firecrawl_scrape and firecrawl_find_tools and explaining the Alexandria provider surface.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives explicit when-to-use routing: prefer a provider over scraping when the task needs consistent fields across entities, exact figures, provenance, or many records; use web results when they already answer the question. It also explains how sources, categories, and domainTools change what is returned, and contrasts with the separate firecrawl_research_* surface.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
firecrawl_search2 fields changedInput schema / properties / clientModelAdded value: +{
+ "description": "Optional model identifier, if known.",
+ "maxLength": 128,
+ "minLength": 1,
+ "type": "string"
+}Input schema / properties / objectiveAdded value: +{
+ "description": "Optional broader goal for this search, if known. Avoid sensitive information.",
+ "maxLength": 5000,
+ "minLength": 1,
+ "type": "string"
+}firecrawl_parse1 field changedOutput schema / properties / agent_hintsAdded value: +{
+ "description": "Optional response guidance from the Firecrawl API.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+}firecrawl_scrape1 field changedOutput schema / properties / agent_hintsAdded value: +{
+ "description": "Optional response guidance from the Firecrawl API.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+}firecrawl_search1 field changedOutput schema / properties / agent_hintsAdded value: +{
+ "description": "Optional response guidance from the Firecrawl API.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+}firecrawl_scrape3 fields changedInput schema / properties / alexandria / descriptionPrevious value: -"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. nextTool identifies access to retained results without repeating a successful provider call. Requires an API key on a team with Alexandria enabled. THIRD_PARTY_DATA_TERMS_REQUIRED (403) means execution is blocked by provider terms, with requiresAction.url for review by an organization admin. Through this tool, terms/show displays the agreement and terms/accept records acceptance; acceptance requires explicit user authorization for the reviewed version and digest and confirmed:true. A data request does not authorize acceptance. Provider execution remains blocked until acceptance is confirmed."New value: +"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."Input schema / properties / requestId / descriptionPrevious value: -"Identifies one logical Alexandria execution; generated when omitted and returned with the result. Repeated attempts of the identical payload require the same ID. A new ID cannot reconcile a pending or uncertain execution. A caller-supplied ID supports recovery if no response is received. Errors relay a code and may include chargeId. request_in_flight (409) means the execution is pending; request_unresolved (503) requires reconciliation under the same ID; duplicate_request (409) means the ID belongs to a different payload; unknown_provider (404), insufficient_credits (402) and billing_unavailable (503) mean nothing executed."New value: +"Idempotency key bound to one Alexandria execution payload. Generated when omitted and returned with the result."Output schema / properties / requestId / descriptionPrevious value: -"Identifier of this logical execution; reuse it only for a retry of the identical payload."New value: +"Identifier of this Alexandria execution."firecrawl_scrape2 fields changedInput schema / properties / domainTools / descriptionPrevious value: -"URL mode only: include domain-matched Alexandria tools for the page in tools on the returned document."New value: +"URL mode only: include domain-matched Alexandria tools for the page in tools on the returned document. Ignored with alexandria."Input schema / properties / toolDetail / descriptionPrevious value: -"URL domain discovery detail: summary by default, compact returns provider/capability/description, full includes contracts."New value: +"URL mode only: domain discovery detail, summary by default; compact returns provider/capability/description, full includes contracts. Ignored with alexandria."firecrawl_scrape2 fields changedInput schema / properties / alexandria / descriptionPrevious value: -"Execute catalogued Alexandria capabilities instead of scraping a URL. Exactly one of url or alexandria. One {provider, capability, options} object or an array of 1-10, found through firecrawl_search or firecrawl_find_tools. Each call may include version to pin a published workflow; omitting it uses latest. Only timeout also applies at the top level. Read the selected contract before executing: required inputs and requiresOneOf groups (at least one member per group), example.request/example.response when present, and response.key (do not assume records is the result key). Follow the declared pagination input and response cursor, preserving filters; catalogue next is separate from provider pagination. Returns per-capability results in data.alexandria with data, records, or an error with a code; check each item even when the outer response succeeds. If a response provides nextTool, follow it to read a large result instead of repeating a successful provider call. Needs an API key on a team with Alexandria enabled. A terms-gated provider returns THIRD_PARTY_DATA_TERMS_REQUIRED (403) with requiresAction.url: follow the returned terms/show and terms/accept calls through this tool, accepting only after explicit user authorization for the reviewed version and digest; an organization admin can instead accept at the dashboard URL. Retry only after confirmed acceptance."New value: +"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. nextTool identifies access to retained results without repeating a successful provider call. Requires an API key on a team with Alexandria enabled. THIRD_PARTY_DATA_TERMS_REQUIRED (403) means execution is blocked by provider terms, with requiresAction.url for review by an organization admin. Through this tool, terms/show displays the agreement and terms/accept records acceptance; acceptance requires explicit user authorization for the reviewed version and digest and confirmed:true. A data request does not authorize acceptance. Provider execution remains blocked until acceptance is confirmed."Input schema / properties / requestId / descriptionPrevious value: -"Alexandria execution ID. Reuse the returned ID for retries of the identical payload, never a new ID to bypass pending or uncertain execution; generated when omitted. For potentially large workflow results, supply and preserve one before execution. Errors relay a code and chargeId: request_in_flight (409) retry the same requestId later; request_unresolved (503) keep the requestId for reconciliation, never mint a new one; duplicate_request (409) the requestId belongs to a different payload; unknown_provider (404), insufficient_credits (402) and billing_unavailable (503) mean nothing executed."New value: +"Identifies one logical Alexandria execution; generated when omitted and returned with the result. Repeated attempts of the identical payload require the same ID. A new ID cannot reconcile a pending or uncertain execution. A caller-supplied ID supports recovery if no response is received. Errors relay a code and may include chargeId. request_in_flight (409) means the execution is pending; request_unresolved (503) requires reconciliation under the same ID; duplicate_request (409) means the ID belongs to a different payload; unknown_provider (404), insufficient_credits (402) and billing_unavailable (503) mean nothing executed."firecrawl_search1 field changedInput schema / properties / sources / descriptionPrevious value: -"Search sources; authenticated sessions default to web + alexandria, keyless sessions to web only. Passing sources without alexandria in it (for example [\"web\"] or [\"news\"]) excludes Alexandria provider matches; omit sources unless you specifically need web-only or news-only results, or include \"alexandria\" alongside them. Use [\"alexandria\"] alone for provider discovery without web results."New value: +"Search sources; authenticated sessions default to web + alexandria, keyless sessions to web only. A search with sources: [\"web\"] omits semantic provider discovery; domainTools: true can still return website-matched tools. Web-only results use domainTools: false. Use [\"alexandria\"] alone for provider discovery without web results."firecrawl_parse1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "description": "Parsed document content, or the upload instructions for the hosted two-call flow.",
+ "properties": {
+ "data": {
+ "description": "Parsed document content; can include `data.metadata.scrapeId` for parse feedback."
+ },
+ "error": {
+ "description": "Error message or error object when the call did not succeed."
+ },
+ "message": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Guidance for the next call."
+ },
+ "mode": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Which phase of the hosted flow produced this response."
+ },
+ "nextToolCall": {
+ "description": "Hosted phase one: the second `firecrawl_parse` call to make once the upload succeeds, as `{name, arguments}`."
+ },
+ "notes": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Hosted phase one: constraints on completing the upload flow."
+ },
+ "raw": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Response body when it was not JSON."
+ },
+ "success": {
+ "anyOf": [
+ {
+ "type": "boolean"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Whether the API call succeeded."
+ },
+ "upload": {
+ "additionalProperties": false,
+ "description": "Hosted phase one: how to upload the local file.",
+ "properties": {
+ "command": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Local command that performs the upload. It carries no Firecrawl API key."
+ },
+ "expiresAt": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "When the upload URL expires."
+ },
+ "fields": {
+ "description": "Form fields the upload request must send, for a POST upload."
+ },
+ "headers": {
+ "description": "Headers the upload request must send."
+ },
+ "maxSizeBytes": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Largest file the upload URL accepts."
+ },
+ "method": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "HTTP method for the upload."
+ },
+ "uploadRef": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Reference to pass back on the second call."
+ },
+ "uploadUrl": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "URL to upload the local file to."
+ }
+ },
+ "type": "object"
+ },
+ "warning": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Non-fatal warning about the result."
+ }
+ },
+ "type": "object"
+}firecrawl_scrape1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "description": "A scraped document, or the Alexandria execution envelope when `alexandria` was passed.",
+ "properties": {
+ "actions": {
+ "description": "Results of the browser actions that ran during the scrape."
+ },
+ "answer": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Targeted answer to the question that was asked of the page."
+ },
+ "attributes": {
+ "description": "Values collected by the requested attribute selectors."
+ },
+ "audio": {
+ "description": "Audio extracted from the page."
+ },
+ "blocks": {
+ "description": "Typed PDF layout blocks, when `parsers[].blocks` is set."
+ },
+ "branding": {
+ "description": "Branding data extracted from the page."
+ },
+ "changeTracking": {
+ "description": "Change-tracking comparison against the previous scrape."
+ },
+ "creditsCost": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Credits this call consumed."
+ },
+ "data": {
+ "description": "Alexandria mode: per-capability results in `data.alexandria`, each with `data`, `records`, or an `error`."
+ },
+ "delivery": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "`retained` when the full result stayed server-side instead of being inlined."
+ },
+ "error": {
+ "description": "Error message or error object when the call did not succeed."
+ },
+ "estimatedTokens": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Estimated token cost of the full result."
+ },
+ "feedbackTool": {
+ "description": "Pointer to the feedback tool for reporting how this result served the task."
+ },
+ "highlights": {
+ "description": "Highlighted passages from the page."
+ },
+ "html": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Processed HTML of the page."
+ },
+ "idleTtlSeconds": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Seconds a retained workspace stays available while idle."
+ },
+ "images": {
+ "description": "Images found on the page."
+ },
+ "inlineTokenBudget": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Token budget above which a result is retained rather than inlined."
+ },
+ "json": {
+ "description": "Structured data matching the requested JSON schema or prompt."
+ },
+ "links": {
+ "description": "Links found on the page."
+ },
+ "markdown": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Page content as markdown."
+ },
+ "menu": {
+ "description": "Menu data extracted from the page."
+ },
+ "message": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Guidance that accompanies the result."
+ },
+ "metadata": {
+ "description": "Page metadata; authenticated responses can include `metadata.scrapeId` for scrape feedback."
+ },
+ "nextTool": {
+ "description": "A follow-up tool call (`{name, arguments}`) that continues or inspects this result."
+ },
+ "pages": {
+ "description": "Physical PDF pages, when `parsers[].pages` is set."
+ },
+ "product": {
+ "description": "Product data extracted from the page."
+ },
+ "rawHtml": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Unprocessed HTML of the page."
+ },
+ "receipt": {
+ "description": "Billing receipt for the execution."
+ },
+ "requestId": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Identifier of this logical execution; reuse it only for a retry of the identical payload."
+ },
+ "responseBytes": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Size of the full result in bytes."
+ },
+ "scrape_id": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Identifier of the underlying scrape."
+ },
+ "screenshot": {
+ "description": "Screenshot of the page."
+ },
+ "success": {
+ "anyOf": [
+ {
+ "type": "boolean"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Whether the API call succeeded."
+ },
+ "summary": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Summary of the page content."
+ },
+ "tokenEstimateMethod": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "How `estimatedTokens` was derived."
+ },
+ "tools": {
+ "description": "Domain-matched Alexandria tools for the page, when `domainTools` is set."
+ },
+ "video": {
+ "description": "Video extracted from the page."
+ },
+ "warning": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Non-fatal warning about the result."
+ },
+ "workspaceId": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Workspace holding a retained result, for inspection through virtual Bash."
+ }
+ },
+ "type": "object"
+}firecrawl_search1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "description": "Ranked search results grouped by source.",
+ "properties": {
+ "creditsUsed": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Credits this search consumed."
+ },
+ "data": {
+ "description": "Ranked results grouped by source, such as `web`, `news`, `images`, and `alexandria`."
+ },
+ "error": {
+ "description": "Error message or error object when the call did not succeed."
+ },
+ "feedbackTool": {
+ "description": "Pointer to the feedback tool for this search."
+ },
+ "id": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Search identifier, for optional `firecrawl_search_feedback`."
+ },
+ "nextTool": {
+ "description": "A follow-up tool call that continues this search."
+ },
+ "success": {
+ "anyOf": [
+ {
+ "type": "boolean"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Whether the API call succeeded."
+ },
+ "tools": {
+ "description": "Domain-matched Alexandria tools for the results."
+ },
+ "warning": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Non-fatal warning about the result."
+ }
+ },
+ "type": "object"
+}firecrawl_scrape2 fields changedInput schema / properties / alexandria / descriptionPrevious value: -"Execute catalogued Alexandria capabilities instead of scraping a URL. Exactly one of url or alexandria."New value: +"Execute catalogued Alexandria capabilities instead of scraping a URL. Exactly one of url or alexandria. One {provider, capability, options} object or an array of 1-10, found through firecrawl_search or firecrawl_find_tools. Each call may include version to pin a published workflow; omitting it uses latest. Only timeout also applies at the top level. Read the selected contract before executing: required inputs and requiresOneOf groups (at least one member per group), example.request/example.response when present, and response.key (do not assume records is the result key). Follow the declared pagination input and response cursor, preserving filters; catalogue next is separate from provider pagination. Returns per-capability results in data.alexandria with data, records, or an error with a code; check each item even when the outer response succeeds. If a response provides nextTool, follow it to read a large result instead of repeating a successful provider call. Needs an API key on a team with Alexandria enabled. A terms-gated provider returns THIRD_PARTY_DATA_TERMS_REQUIRED (403) with requiresAction.url: follow the returned terms/show and terms/accept calls through this tool, accepting only after explicit user authorization for the reviewed version and digest; an organization admin can instead accept at the dashboard URL. Retry only after confirmed acceptance."Input schema / properties / requestId / descriptionPrevious value: -"Alexandria execution ID. Reuse for retries of the identical payload; generated when omitted and returned with the result."New value: +"Alexandria execution ID. Reuse the returned ID for retries of the identical payload, never a new ID to bypass pending or uncertain execution; generated when omitted. For potentially large workflow results, supply and preserve one before execution. Errors relay a code and chargeId: request_in_flight (409) retry the same requestId later; request_unresolved (503) keep the requestId for reconciliation, never mint a new one; duplicate_request (409) the requestId belongs to a different payload; unknown_provider (404), insufficient_credits (402) and billing_unavailable (503) mean nothing executed."firecrawl_search4 fields changedInput schema / properties / excludeDomains / descriptionAdded value: +"Hostnames to leave out of results. Mutually exclusive with includeDomains."Input schema / properties / includeDomains / descriptionAdded value: +"Hostnames to restrict results to. Mutually exclusive with excludeDomains."Input schema / properties / query / descriptionPrevious value: -"Query for web and semantic tool discovery. Catalogue browsing is available through firecrawl_find_tools."New value: +"Query for web and semantic tool discovery. Operators include quoted phrases, `-term`, `site:host`, `inurl:term`, `intitle:term`, and `related:host`; the set is non-exhaustive. Catalogue browsing is available through firecrawl_find_tools."Input schema / properties / scrapeOptions / descriptionAdded value: +"Attach page content for web results in the same call. These fetches ignore maxAge, so use firecrawl_scrape when you need a live fetch. scrapeOptions fetches web pages, never Alexandria provider tools."firecrawl_search2 fields changedInput schema / properties / query / descriptionPrevious value: -"Query for web and semantic tool discovery. Catalogue browsing is available on the full MCP surface."New value: +"Query for web and semantic tool discovery. Catalogue browsing is available through firecrawl_find_tools."Input schema / properties / toolDetail / descriptionPrevious value: -"Compact by default. Compact returns only provider, capability and description; full includes contracts. Inspect selected compact tools on the full MCP surface using firecrawl_find_tools providers and capabilities."New value: +"Compact by default. Compact returns only provider, capability and description; full includes contracts. Inspect selected compact tools with firecrawl_find_tools providers and capabilities."firecrawl_search3 fields changedInput schema / properties / categories / descriptionPrevious value: -"Limit results to specific source types. `github` searches GitHub repositories, code, issues, and docs; `research` restricts ordinary web results to research-affiliated websites and returns page snippets, which is separate from the `firecrawl_research_*` tools that search paper abstracts and full text across biomedical (PubMed, bioRxiv, medRxiv) and arXiv literature; `pdf` searches PDF results; `developer` searches an index built for coding agents over repositories, GitHub issues, merged pull requests, repository READMEs, and curated documentation sites. `developer` returns hits in `data.web` with `category: \"developer\"`; the other categories also filter `data.web`."New value: +"Limit results to specific source types. `research` restricts ordinary web results to research-affiliated websites and returns page snippets, which is separate from the `firecrawl_research_*` tools that search paper abstracts and full text across biomedical (PubMed, bioRxiv, medRxiv) and arXiv literature; `pdf` searches PDF results; `developer` searches an index built for coding agents over public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation. `developer` returns hits in `data.web` with `category: \"developer\"`; the other categories also filter `data.web`."Input schema / properties / categories / items / enumPrevious value: -[
- "github",
- "research",
- "pdf",
- "developer"
-]New value: +[
+ "research",
+ "pdf",
+ "developer"
+]Input schema / properties / highlights / descriptionPrevious value: -"Return query-relevant highlights for each search result. Set to false to keep the original search snippets."New value: +"Return query-relevant page excerpts for web and news results when available (default). Highlights appear in web `description` and news `snippet`; otherwise, original snippets are returned. Set to false to keep the original search snippets."firecrawl_search1 field changedInput schema / properties / sources / descriptionPrevious value: -"Search sources; authenticated sessions default to web + alexandria, keyless sessions to web only. Use alexandria alone for semantic tool discovery."New value: +"Search sources; authenticated sessions default to web + alexandria, keyless sessions to web only. Passing sources without alexandria in it (for example [\"web\"] or [\"news\"]) excludes Alexandria provider matches; omit sources unless you specifically need web-only or news-only results, or include \"alexandria\" alongside them. Use [\"alexandria\"] alone for provider discovery without web results."
Add one secure layer between your agents and this server.