Firecrawl MCP Server

Firecrawl file parsing

firecrawl_parse

Read-only

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.

Input Schema

Name	Required	Description
`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
`conversationId`	No	conversationId 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.
`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

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}`.
`conversationId`	No	Pass on later Firecrawl calls in this conversation.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026
- changedInput schema / properties / jsonOptions / properties / schema / additionalProperties
```
Previous value: -{}New value: +true
```

Changed2 schema fields changedOct 31, 2026

addedInput schema / properties / conversationId

Added value: +{
+  "description": "conversationId 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.",
+  "pattern": "^[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}$",
+  "type": "string"
+}

addedOutput schema / properties / conversationId

Added value: +{
+  "description": "Pass on later Firecrawl calls in this conversation.",
+  "type": "string"
+}

Changed1 schema field changedOct 27, 2026
- changedInput schema / properties / jsonOptions / properties / schema / additionalProperties
```
Previous value: -falseNew value: +{}
```

Changed1 schema field changedOct 13, 2026

removedOutput schema / description

Removed value: -"Parsed document content, or the upload instructions for the hosted two-call flow."

First observedSep 29, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the two-phase hosted flow with what each phase returns, the authenticated-account requirement for `zeroDataRetention`, PII redaction semantics, and the optional `data.metadata.scrapeId` feedback channel. It does not address failure modes or size limits beyond the brief `pdfOptions.maxPages` mention.

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?

Organized into a purpose sentence, an input/mode paragraph, and a parameters/returns paragraph, so the mode distinction is front-loaded where an agent needs it. Dense but nearly every sentence carries operational information; the only near-redundancy is restating return values that the output schema already supplies.

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 exists, so return values needn't be spelled out, and the critical path (local vs hosted, phase 1 vs phase 2, PDF bounding) is well covered. For a 20-parameter tool with only 30% schema coverage, though, roughly half the options remain opaque to an agent that wants to control tags, image handling, or JSON/query extraction behavior.

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 description coverage is only 30% across 20 parameters, so the description carries real weight, and it does clarify `filePath`/`uploadRef` phase semantics, `pdfOptions.maxPages`, `redactPII`, and the output-format family of `formats`. However, many parameters (`proxy`, `parsers`, `includeTags`/`excludeTags`, `onlyMainContent`, `storeInCache`, `removeBase64Images`, `skipTlsVerification`, `jsonOptions`) get no meaning from either source, so the gap is only partly closed.

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) plus the concrete output formats, lists the accepted input file types, and explicitly routes remote web URLs to firecrawl_scrape. An agent can separate this from both siblings without opening a 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 explicit when-to-use conditions: local MCP reads `filePath` from the server filesystem, hosted MCP requires the two-call upload flow, and neither `filePath` nor `uploadRef` may be sent together. It also names the alternative (`firecrawl_scrape`) and the condition that selects it, plus when to omit `zeroDataRetention`.

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

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.