Skip to main content
Glama

Firecrawl by Nova (CIVAI)

firecrawl_parse

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

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "firecrawl_parse"
  }
}

Input Schema

NameRequiredDescriptionDefault
proxyNo
maxAgeNoIgnored: parse never reuses or stores indexed content.
formatsNo
parsersNo
filePathNoPhase 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.
objectiveNoThe user's underlying goal in one sentence, not a restatement of this call's arguments. Reuse it across related calls. Firecrawl uses it to learn what agents need and improve its results. No personal data, secrets or the user's exact words.
redactPIINo
uploadRefNoPhase 2 only: short-lived upload reference returned by phase 1 after the local PUT upload completes.
pdfOptionsNo
contentTypeNoPhase 1 MIME type override. If omitted, the server infers it from the file extension without reading the file.
excludeTagsNo
includeTagsNo
jsonOptionsNo
queryOptionsNo
storeInCacheNo
conversationIdNoconversationId 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.
onlyMainContentNo
declaredSizeBytesNoOptional phase 1 size declaration. Hosted MCP does not stat the file; provide this only if the caller already knows it.
zeroDataRetentionNo
removeBase64ImagesNo
skipTlsVerificationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / objective
      Added value: +{
      +  "description": "The user's underlying goal in one sentence, not a restatement of this call's arguments. Reuse it across related calls. Firecrawl uses it to learn what agents need and improve its results. No personal data, secrets or the user's exact words.",
      +  "maxLength": 5000,
      +  "minLength": 1,
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / jsonOptions / properties / schema / additionalProperties
      Previous value: -{}New value: +true
  3. First observed

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full disclosure burden and does well: it explains the two-phase hosted flow and its return values, the PII redaction behavior, the auth requirement for zero data retention, and the optional `data.metadata.scrapeId` feedback path. Gaps remain around several parameters and side effects (caching via `storeInCache`, tag filtering, TLS skipping, and what `proxy`/`skipTlsVerification` change about behavior).

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?

The description is front-loaded with what the tool does, then progresses to the local/hosted split, then to optional flags and return values — a sensible order for a complex tool. Paragraphs are dense but purposeful; the only waste is the output-format enumeration in sentence one, which partly duplicates the `formats` enum in the schema.

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?

For a 21-parameter tool with nested objects, no annotations, and no output schema, the description covers the highest-risk failure mode (the hosted two-call upload sequence and the prohibition on sending both fields) and describes return values including the phase-1 upload instructions and scrapeId. Remaining incompleteness is in the long tail of tuning parameters, which is a moderate rather than disqualifying gap.

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 33% across 21 parameters, so the description must compensate. It adds real meaning for `filePath`/`uploadRef` (phase 1 vs phase 2), `pdfOptions.maxPages`, `redactPII`, and the `formats` outputs, but leaves roughly half the parameters (proxy, maxAge, storeInCache, onlyMainContent, include/excludeTags, skipTlsVerification, parsers, jsonOptions, queryOptions, contentType, declaredSizeBytes, conversationId) with no explanation in either the description or the schema.

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?

The opening sentence names a specific verb ("Parse one supported document") and enumerates the output targets (markdown, HTML, links, summary, targeted answers, schema-matched JSON). It also differentiates from the sibling by stating "Remote web URLs belong in `firecrawl_scrape`" and lists the accepted input file families, so an agent can select it without opening the 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?

The description gives explicit routing rules: local MCP reads `filePath` directly, hosted MCP requires a two-call upload flow, and both fields must never be sent together. It also names the alternative tool for remote URLs and states when `zeroDataRetention` is usable (eligible authenticated account) versus when to omit it for keyless use.

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.

Resources