Home / Directory / Firecrawl / firecrawl_parse

Firecrawl parse

An MCP tool from the Firecrawl server, run by Firecrawl.

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 on the gateway: firecrawl__firecrawl_parse.

Parameters

NameTypeDescription
formatsarray
jsonOptionsobject
queryOptionsobject
parsersarray
pdfOptionsobject
onlyMainContentboolean
redactPIIboolean
includeTagsarray
excludeTagsarray
removeBase64Imagesboolean
skipTlsVerificationboolean
storeInCacheboolean
zeroDataRetentionboolean
maxAgenumberIgnored: parse never reuses or stores indexed content.
proxybasic | auto
filePathstringPhase 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.
uploadRefstringPhase 2 only: short-lived upload reference returned by phase 1 after the local PUT upload completes.
contentTypestringPhase 1 MIME type override. If omitted, the server infers it from the file extension without reading the file.
declaredSizeBytesintegerOptional phase 1 size declaration. Hosted MCP does not stat the file; provide this only if the caller already knows it.
conversationIdstringconversationId from any earlier Firecrawl tool result in this conversation; after parallel calls, any one of theirs. Omit only on the first call of a conversation; the result returns one to pass on every later call.

How to call it

Through the Smart Gateway, any client can run it by name with call_tool, or let the gateway find it with search_tools:

call_tool arguments
{
  "name": "firecrawl__firecrawl_parse",
  "arguments": {}
}

The first call connects Firecrawl to your account automatically; nothing to set up. About this server.

Try asking

Use the firecrawl parse tool with formats set to ….

More from Firecrawl