Firecrawl MCP Server

Firecrawl file parsing

firecrawl_parse

Read-only

Parse local HTML, PDF, Word, RTF, OpenDocument, and spreadsheet files into markdown, HTML, links, summaries, targeted answers, or schema-matched JSON.

Instructions

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.

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": {
      "filePath": "<filePath>"
    },
    "name": "firecrawl_parse"
  }
}

Input Schema

Name	Required	Description
`proxy`	No
`maxAge`	No	Ignored: parse never reuses or stores indexed content.
`formats`	No
`parsers`	No
`filePath`	Yes	Absolute or relative path to a local file to parse. Supported: .html, .htm, .pdf, .docx, .doc, .odt, .rtf, .xlsx, .xls
`redactPII`	No
`pdfOptions`	No
`contentType`	No	Optional MIME type override. If omitted, the server infers the file kind from the extension.
`excludeTags`	No
`includeTags`	No
`jsonOptions`	No
`queryOptions`	No
`storeInCache`	No
`onlyMainContent`	No
`zeroDataRetention`	No
`removeBase64Images`	No
`skipTlsVerification`	No

Output Schema

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}`.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.28.2Nov 4, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover read-only and closed-world safety, and the description adds real operational context: the hosted vs local distinction, redaction behavior, the auth requirement for zeroDataRetention, and what each phase returns. It leaves several behavioral knobs (proxy, storeInCache, caching, TLS skipping) unexplained, so 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.

Conciseness4/5

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

Front-loaded and logically ordered (what it does, input constraints, local/hosted flow, flags, returns), with no filler sentences. Some sentences are densely packed with multiple parameters, but nothing is redundant.

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

Completeness3/5

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

The output schema means return values needn't be spelled out, and the description addresses the hardest part (the two-phase hosted flow). However, for a 17-parameter, nested-object tool it remains silent on too many options for an agent to invoke it confidently in all configurations.

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 coverage is only 18% across 17 parameters, so the description must carry weight. It does explain filePath, pdfOptions.maxPages, redactPII, zeroDataRetention, and the output formats, but leaves proxy, parsers, contentType, include/excludeTags, jsonOptions, queryOptions, storeInCache, onlyMainContent, removeBase64Images, and skipTlsVerification undocumented.

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 (parse) and resource (one supported document) with the output form, and explicitly separates it from firecrawl_scrape for remote URLs. The sibling differentiation is unambiguous.

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?

Explicitly names when not to use it (remote URLs → firecrawl_scrape) and gives the full when-to-use protocol for both local and hosted MCP, including the two-phase upload flow and the warning not to send filePath and uploadRef together.

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