Firecrawl MCP · Firecrawl

Operational

Unclaimed — claim this pagedata Streamable HTTP2025-06-18 API key expected

https://mcp.firecrawl.dev/v2/mcp Docs

Badge

100%

Availability · 30 days · 355 checks

69 ms

Latency (last observation)

rev 2

Contract

17days

Schema stable

Incidents · 30 days

Aug 6, 2026

Observed since

Availability — last 30 days

No failures Some failures Mostly failing Auth required No observations

Last observed 2 h ago by MCP Tools Edge Scanner · scheduled every 120 min

Descriptions or metadata changed Informational Sep 16, 2026 — 5:30 AM

3 description/metadata changes; the functional contract is unchanged (hash sha256:b3576f9850fda608…).

VerifiedDescriptions or metadata for firecrawl_parse changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.firecrawl_parse	description changed	Informational	Descriptions or metadata for `firecrawl_parse` changed. No structural change. Wording changes can still influence model tool selection.
tools.firecrawl_scrape	description changed	Informational	Descriptions or metadata for `firecrawl_scrape` changed. No structural change. Wording changes can still influence model tool selection.
tools.firecrawl_search	description changed	Informational	Descriptions or metadata for `firecrawl_search` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Latency recovered below 1,000 ms Informational Sep 7, 2026 — 11:55 PM

Latest observation: 153 ms.

VerifiedObserved initialization latency: 153 ms.

Observed by MCP Tools Edge Scanner

Latency crossed above 1,000 ms Informational Aug 31, 2026 — 5:25 PM

Three consecutive observations exceeded 1,000 ms (latest: 1031 ms).

VerifiedObserved initialization latency: 1031 ms.

InterpretationClients may experience slow tool discovery and responses.

Observed by MCP Tools Edge Scanner

Breaking contract change: firecrawl_search.inputSchema.limit Breaking Aug 31, 2026 — 9:05 AM

1 breaking change. firecrawl_search.inputSchema.limit changed from number to integer.

Verifiedfirecrawl_search.inputSchema.limit changed from number to integer.

InterpretationExisting calls that send number values may fail schema validation.

Raw event details

{
  "beforeRev": 1,
  "afterRev": 2,
  "changeCount": 1
}

View full diff Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Aug 27, 2026 — 11:50 PM

1 description/metadata change; the functional contract is unchanged (hash sha256:90599d877303e7cd…).

VerifiedDescriptions or metadata for firecrawl_search changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.firecrawl_search	description changed	Informational	Descriptions or metadata for `firecrawl_search` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 26, 2026 — 8:15 AM

Server reports version 3.24.1 (was 3.24.0).

Verifiedinitialize returned serverInfo.version 3.24.1.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 12, 2026 — 5:25 PM

Server reports version 3.24.0 (was 3.23.9).

Verifiedinitialize returned serverInfo.version 3.24.0.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Aug 12, 2026 — 5:25 PM

1 description/metadata change; the functional contract is unchanged (hash sha256:90599d877303e7cd…).

VerifiedDescriptions or metadata for firecrawl_search changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.firecrawl_search	description changed	Informational	Descriptions or metadata for `firecrawl_search` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 11, 2026 — 6:00 AM

Server reports version 3.23.9 (was 3.23.8).

Verifiedinitialize returned serverInfo.version 3.23.9.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 10, 2026 — 3:25 PM

Server reports version 3.23.8 (was 3.23.7).

Verifiedinitialize returned serverInfo.version 3.23.8.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 10, 2026 — 1:20 PM

Server reports version 3.23.7 (was 3.23.6).

Verifiedinitialize returned serverInfo.version 3.23.7.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 7, 2026 — 10:56 PM

Server reports version 3.23.6 (was 3.23.5).

Verifiedinitialize returned serverInfo.version 3.23.6.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 7, 2026 — 2:06 AM

Server reports version 3.23.5 (was 3.23.4).

Verifiedinitialize returned serverInfo.version 3.23.5.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Aug 6, 2026 — 3:50 PM

2 description/metadata changes; the functional contract is unchanged (hash sha256:90599d877303e7cd…).

VerifiedDescriptions or metadata for firecrawl_scrape changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.firecrawl_scrape	description changed	Informational	Descriptions or metadata for `firecrawl_scrape` changed. No structural change. Wording changes can still influence model tool selection.
tools.firecrawl_search	description changed	Informational	Descriptions or metadata for `firecrawl_search` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 6, 2026 — 11:40 AM

Server reports version 3.23.4 (was 3.23.3).

Verifiedinitialize returned serverInfo.version 3.23.4.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Baseline captured Aug 6, 2026 — 5:00 AM

3 tools, 0 resources, 0 prompts observed. Future observations will identify outages, recoveries, protocol changes, and contract drift from this state.

VerifiedCanonical contract hash sha256:90599d877303e7cd… computed from the normalized capability inventory.

Raw event details

{
  "contractHash": "sha256:90599d877303e7cd51228b4c2e3250d48c95b293d0010cd83517463ecd9d95a6"
}

Observed by MCP Tools Edge Scanner

Advertised capabilities

Tools · 3 Resources Prompts Logging Completions Experimental

Tools 3

firecrawl_scrape 22 params · 1 required Retrieve and extract content from one supplied URL through Firecrawl. Use this when the request identifies a …

Retrieve and extract content from one supplied URL through Firecrawl. Use this when the request identifies a page and needs its content or defined fields. It can return markdown, HTML, links, screenshots, branding data, a targeted answer, or JSON matching a supplied schema; JSON is useful when the requested result has defined fields, while markdown preserves readable page content. This tool operates on a known page. For a set of pages use `firecrawl_crawl`, and to discover page URLs use `firecrawl_map` or `firecrawl_search`. Options include JavaScript render delay, cache age, main-content filtering, PII redaction, and lockdown cache-only retrieval. Browser actions may change the live page when interactive actions are enabled. Firecrawl may reuse recently indexed content instead of refetching the page, and the reuse window varies by domain. Set `maxAge: 0` to force a live fetch, or a smaller `maxAge` to bound how stale reused content may be. A successful response does not by itself confirm that the state it describes is still current. Returns the selected content formats and page metadata.

Input schema

Parameter	Type	Description & constraints
url*	string	— format: uri
formats	array<enum(11)>	—
jsonOptions	object	—
jsonOptions.prompt	string	—
jsonOptions.schema	object	—
queryOptions	object	—
queryOptions.prompt*	string	— maxLen: 10000
queryOptions.mode*	enum(2)	— one of: "directQuote", "freeform" · default: "freeform"
screenshotOptions	object	—
screenshotOptions.fullPage	boolean	—
screenshotOptions.quality	number	—
screenshotOptions.viewport	object	—
screenshotOptions.viewport.width*	number	—
screenshotOptions.viewport.height*	number	—
parsers	array<enum(1)>	—
pdfOptions	object	—
pdfOptions.maxPages	integer	— min: 1 · max: 10000
onlyMainContent	boolean	—
redactPII	boolean	—
includeTags	array<string>	—
excludeTags	array<string>	—
waitFor	number	—
mobile	boolean	—
skipTlsVerification	boolean	—
removeBase64Images	boolean	—
location	object	—
location.country	string	—
location.languages	array<string>	—
storeInCache	boolean	—
zeroDataRetention	boolean	—
maxAge	number	—
lockdown	boolean	—
proxy	enum(4)	— one of: "basic", "stealth", "enhanced", "auto"
profile	object	—
profile.name*	string	—
profile.saveChanges	boolean	—

Raw schema JSON

firecrawl_scrape — raw

{
  "name": "firecrawl_scrape",
  "description": "\nRetrieve and extract content from one supplied URL through Firecrawl. Use this when the request identifies a page and needs its content or defined fields. It can return markdown, HTML, links, screenshots, branding data, a targeted answer, or JSON matching a supplied schema; JSON is useful when the requested result has defined fields, while markdown preserves readable page content.\n\nThis tool operates on a known page. For a set of pages use `firecrawl_crawl`, and to discover page URLs use `firecrawl_map` or `firecrawl_search`. Options include JavaScript render delay, cache age, main-content filtering, PII redaction, and lockdown cache-only retrieval. Browser actions may change the live page when interactive actions are enabled.\n\nFirecrawl may reuse recently indexed content instead of refetching the page, and the reuse window varies by domain. Set `maxAge: 0` to force a live fetch, or a smaller `maxAge` to bound how stale reused content may be. A successful response does not by itself confirm that the state it describes is still current.\n\nReturns the selected content formats and page metadata.\n",
  "inputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "url": {
        "type": "string",
        "format": "uri"
      },
      "formats": {
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "markdown",
            "html",
            "rawHtml",
            "screenshot",
            "links",
            "summary",
            "changeTracking",
            "branding",
            "json",
            "query",
            "audio"
          ]
        }
      },
      "jsonOptions": {
        "type": "object",
        "properties": {
          "prompt": {
            "type": "string"
          },
          "schema": {
            "type": "object",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": false
          }
        },
        "additionalProperties": false
      },
      "queryOptions": {
        "type": "object",
        "properties": {
          "prompt": {
            "type": "string",
            "maxLength": 10000
          },
          "mode": {
            "default": "freeform",
            "type": "string",
            "enum": [
              "directQuote",
              "freeform"
            ]
          }
        },
        "required": [
          "prompt",
          "mode"
        ],
        "additionalProperties": false
      },
      "screenshotOptions": {
        "type": "object",
        "properties": {
          "fullPage": {
            "type": "boolean"
          },
          "quality": {
            "type": "number"
          },
          "viewport": {
            "type": "object",
            "properties": {
              "width": {
                "type": "number"
              },
              "height": {
                "type": "number"
              }
            },
            "required": [
              "width",
              "height"
            ],
            "additionalProperties": false
          }
        },
        "additionalProperties": false
      },
      "parsers": {
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "pdf"
          ]
        }
      },
      "pdfOptions": {
        "type": "object",
        "properties": {
          "maxPages": {
            "type": "integer",
            "minimum": 1,
            "maximum": 10000
          }
        },
        "additionalProperties": false
      },
      "onlyMainContent": {
        "type": "boolean"
      },
      "redactPII": {
        "type": "boolean"
      },
      "includeTags": {
        "type": "array",
        "items": {
          "type": "string"
        }
      },
      "excludeTags": {
        "type": "array",
        "items": {
          "type": "string"
        }
      },
      "waitFor": {
        "type": "number"
      },
      "mobile": {
        "type": "boolean"
      },
      "skipTlsVerification": {
        "type": "boolean"
      },
      "removeBase64Images": {
        "type": "boolean"
      },
      "location": {
        "type": "object",
        "properties": {
          "country": {
            "type": "string"
          },
          "languages": {
            "type": "array",
            "items": {
              "type": "string"
            }
          }
        },
        "additionalProperties": false
      },
      "storeInCache": {
        "type": "boolean"
      },
      "zeroDataRetention": {
        "type": "boolean"
      },
      "maxAge": {
        "type": "number"
      },
      "lockdown": {
        "type": "boolean"
      },
      "proxy": {
        "type": "string",
        "enum": [
          "basic",
          "stealth",
          "enhanced",
          "auto"
        ]
      },
      "profile": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string"
          },
          "saveChanges": {
            "type": "boolean"
          }
        },
        "required": [
          "name"
        ],
        "additionalProperties": false
      }
    },
    "required": [
      "url"
    ],
    "additionalProperties": false
  }
}

firecrawl_search 12 params · 1 required Search web, news, or image sources and return ranked results. Operators include quoted phrases, `-term`, `sit…

Search web, news, or image sources and return ranked results. Operators include quoted phrases, `-term`, `site:host`, `inurl:term`, `intitle:term`, and `related:host`; the set is non-exhaustive. `includeDomains` and `excludeDomains` are mutually exclusive hostname filters; categories limit results to GitHub, research, PDF, or developer sources. For a programming question, add `categories: ["developer"]`. It searches an index of repositories, GitHub issues, merged pull requests, repository READMEs, and curated documentation sites, and returns the hits in `data.web` with `category: "developer"`. `categories: ["research"]` restricts these web results to research-affiliated websites and returns page snippets. The `firecrawl_research_*` tools are a separate surface that searches paper abstracts and full text across biomedical (PubMed, bioRxiv, medRxiv) and arXiv literature. Each web result is a title, URL, and description, not the page. Add `scrapeOptions` to attach page content in the same call; those fetches ignore `maxAge`, so use `firecrawl_scrape` when you need a live fetch. Returns source-type result groups and usage metadata. Authenticated responses can include an `id` for optional search feedback.

Input schema

Parameter	Type	Description & constraints
query*	string	— minLen: 1
highlights	boolean	—
limit	integer	— min: 1 · max: 100
tbs	string	—
filter	string	—
location	string	—
includeDomains	array<string>	—
excludeDomains	array<string>	—
sources	array<object>	—
sources[].type*	enum(3)	— one of: "web", "images", "news"
categories	array<enum(4)>	—
enterprise	array<enum(3)>	—
scrapeOptions	object	—
scrapeOptions.formats	array<enum(11)>	—
scrapeOptions.jsonOptions	object	—
scrapeOptions.jsonOptions.prompt	string	—
scrapeOptions.jsonOptions.schema	object	—
scrapeOptions.queryOptions	object	—
scrapeOptions.queryOptions.prompt*	string	— maxLen: 10000
scrapeOptions.queryOptions.mode*	enum(2)	— one of: "directQuote", "freeform" · default: "freeform"
scrapeOptions.screenshotOptions	object	—
scrapeOptions.screenshotOptions.fullPage	boolean	—
scrapeOptions.screenshotOptions.quality	number	—
scrapeOptions.screenshotOptions.viewport	object	—
scrapeOptions.screenshotOptions.viewport.width*	number	—
scrapeOptions.screenshotOptions.viewport.height*	number	—
scrapeOptions.parsers	array<enum(1)>	—
scrapeOptions.pdfOptions	object	—
scrapeOptions.pdfOptions.maxPages	integer	— min: 1 · max: 10000
scrapeOptions.onlyMainContent	boolean	—
scrapeOptions.redactPII	boolean	—
scrapeOptions.includeTags	array<string>	—
scrapeOptions.excludeTags	array<string>	—
scrapeOptions.waitFor	number	—
scrapeOptions.mobile	boolean	—
scrapeOptions.skipTlsVerification	boolean	—
scrapeOptions.removeBase64Images	boolean	—
scrapeOptions.location	object	—
scrapeOptions.location.country	string	—
scrapeOptions.location.languages	array<string>	—
scrapeOptions.storeInCache	boolean	—
scrapeOptions.zeroDataRetention	boolean	—
scrapeOptions.maxAge	number	—
scrapeOptions.lockdown	boolean	—
scrapeOptions.proxy	enum(4)	— one of: "basic", "stealth", "enhanced", "auto"
scrapeOptions.profile	object	—
scrapeOptions.profile.name*	string	—
scrapeOptions.profile.saveChanges	boolean	—

Raw schema JSON

firecrawl_search — raw

{
  "name": "firecrawl_search",
  "description": "\nSearch web, news, or image sources and return ranked results. Operators include quoted phrases, `-term`, `site:host`, `inurl:term`, `intitle:term`, and `related:host`; the set is non-exhaustive. `includeDomains` and `excludeDomains` are mutually exclusive hostname filters; categories limit results to GitHub, research, PDF, or developer sources.\n\nFor a programming question, add `categories: [\"developer\"]`. It searches an index of repositories, GitHub issues, merged pull requests, repository READMEs, and curated documentation sites, and returns the hits in `data.web` with `category: \"developer\"`.\n\n`categories: [\"research\"]` restricts these web results to research-affiliated websites and returns page snippets. The `firecrawl_research_*` tools are a separate surface that searches paper abstracts and full text across biomedical (PubMed, bioRxiv, medRxiv) and arXiv literature.\n\nEach web result is a title, URL, and description, not the page. Add `scrapeOptions` to attach page content in the same call; those fetches ignore `maxAge`, so use `firecrawl_scrape` when you need a live fetch. Returns source-type result groups and usage metadata. Authenticated responses can include an `id` for optional search feedback.\n",
  "inputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "query": {
        "type": "string",
        "minLength": 1
      },
      "highlights": {
        "type": "boolean"
      },
      "limit": {
        "type": "integer",
        "minimum": 1,
        "maximum": 100
      },
      "tbs": {
        "type": "string"
      },
      "filter": {
        "type": "string"
      },
      "location": {
        "type": "string"
      },
      "includeDomains": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1,
          "maxLength": 253,
          "pattern": "^(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\\.)+[a-z0-9][a-z0-9-]{0,61}[a-z0-9]$"
        }
      },
      "excludeDomains": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1,
          "maxLength": 253,
          "pattern": "^(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\\.)+[a-z0-9][a-z0-9-]{0,61}[a-z0-9]$"
        }
      },
      "sources": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "type": {
              "type": "string",
              "enum": [
                "web",
                "images",
                "news"
              ]
            }
          },
          "required": [
            "type"
          ],
          "additionalProperties": false
        }
      },
      "categories": {
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "github",
            "research",
            "pdf",
            "developer"
          ]
        }
      },
      "enterprise": {
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "default",
            "anon",
            "zdr"
          ]
        }
      },
      "scrapeOptions": {
        "type": "object",
        "properties": {
          "formats": {
            "type": "array",
            "items": {
              "type": "string",
              "enum": [
                "markdown",
                "html",
                "rawHtml",
                "screenshot",
                "links",
                "summary",
                "changeTracking",
                "branding",
                "json",
                "query",
                "audio"
              ]
            }
          },
          "jsonOptions": {
            "type": "object",
            "properties": {
              "prompt": {
                "type": "string"
              },
              "schema": {
                "type": "object",
                "propertyNames": {
                  "type": "string"
                },
                "additionalProperties": false
              }
            },
            "additionalProperties": false
          },
          "queryOptions": {
            "type": "object",
            "properties": {
              "prompt": {
                "type": "string",
                "maxLength": 10000
              },
              "mode": {
                "default": "freeform",
                "type": "string",
                "enum": [
                  "directQuote",
                  "freeform"
                ]
              }
            },
            "required": [
              "prompt",
              "mode"
            ],
            "additionalProperties": false
          },
          "screenshotOptions": {
            "type": "object",
            "properties": {
              "fullPage": {
                "type": "boolean"
              },
              "quality": {
                "type": "number"
              },
              "viewport": {
                "type": "object",
                "properties": {
                  "width": {
                    "type": "number"
                  },
                  "height": {
                    "type": "number"
                  }
                },
                "required": [
                  "width",
                  "height"
                ],
                "additionalProperties": false
              }
            },
            "additionalProperties": false
          },
          "parsers": {
            "type": "array",
            "items": {
              "type": "string",
              "enum": [
                "pdf"
              ]
            }
          },
          "pdfOptions": {
            "type": "object",
            "properties": {
              "maxPages": {
                "type": "integer",
                "minimum": 1,
                "maximum": 10000
              }
            },
            "additionalProperties": false
          },
          "onlyMainContent": {
            "type": "boolean"
          },
          "redactPII": {
            "type": "boolean"
          },
          "includeTags": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "excludeTags": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "waitFor": {
            "type": "number"
          },
          "mobile": {
            "type": "boolean"
          },
          "skipTlsVerification": {
            "type": "boolean"
          },
          "removeBase64Images": {
            "type": "boolean"
          },
          "location": {
            "type": "object",
            "properties": {
              "country": {
                "type": "string"
              },
              "languages": {
                "type": "array",
                "items": {
                  "type": "string"
                }
              }
            },
            "additionalProperties": false
          },
          "storeInCache": {
            "type": "boolean"
          },
          "zeroDataRetention": {
            "type": "boolean"
          },
          "maxAge": {
            "type": "number"
          },
          "lockdown": {
            "type": "boolean"
          },
          "proxy": {
            "type": "string",
            "enum": [
              "basic",
              "stealth",
              "enhanced",
              "auto"
            ]
          },
          "profile": {
            "type": "object",
            "properties": {
              "name": {
                "type": "string"
              },
              "saveChanges": {
                "type": "boolean"
              }
            },
            "required": [
              "name"
            ],
            "additionalProperties": false
          }
        },
        "additionalProperties": false
      }
    },
    "required": [
      "query"
    ],
    "additionalProperties": false
  }
}

firecrawl_parse 19 params Parse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema…

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.

Input schema

Parameter	Type	Description & constraints
formats	array<enum(7)>	—
jsonOptions	object	—
jsonOptions.prompt	string	—
jsonOptions.schema	object	—
queryOptions	object	—
queryOptions.prompt*	string	— maxLen: 10000
queryOptions.mode*	enum(2)	— one of: "directQuote", "freeform" · default: "freeform"
parsers	array<enum(1)>	—
pdfOptions	object	—
pdfOptions.maxPages	integer	— min: 1 · max: 10000
onlyMainContent	boolean	—
redactPII	boolean	—
includeTags	array<string>	—
excludeTags	array<string>	—
removeBase64Images	boolean	—
skipTlsVerification	boolean	—
storeInCache	boolean	—
zeroDataRetention	boolean	—
maxAge	number	—
proxy	enum(2)	— one of: "basic", "auto"
filePath	string	— minLen: 1
uploadRef	string	— minLen: 1
contentType	string	—
declaredSizeBytes	integer	— max: 9007199254740991

Raw schema JSON

firecrawl_parse — raw

{
  "name": "firecrawl_parse",
  "description": "\nParse 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`.\n\nLocal 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`.\n\nSet `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.\n",
  "inputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "formats": {
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "markdown",
            "html",
            "rawHtml",
            "links",
            "summary",
            "json",
            "query"
          ]
        }
      },
      "jsonOptions": {
        "type": "object",
        "properties": {
          "prompt": {
            "type": "string"
          },
          "schema": {
            "type": "object",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": false
          }
        },
        "additionalProperties": false
      },
      "queryOptions": {
        "type": "object",
        "properties": {
          "prompt": {
            "type": "string",
            "maxLength": 10000
          },
          "mode": {
            "default": "freeform",
            "type": "string",
            "enum": [
              "directQuote",
              "freeform"
            ]
          }
        },
        "required": [
          "prompt",
          "mode"
        ],
        "additionalProperties": false
      },
      "parsers": {
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "pdf"
          ]
        }
      },
      "pdfOptions": {
        "type": "object",
        "properties": {
          "maxPages": {
            "type": "integer",
            "minimum": 1,
            "maximum": 10000
          }
        },
        "additionalProperties": false
      },
      "onlyMainContent": {
        "type": "boolean"
      },
      "redactPII": {
        "type": "boolean"
      },
      "includeTags": {
        "type": "array",
        "items": {
          "type": "string"
        }
      },
      "excludeTags": {
        "type": "array",
        "items": {
          "type": "string"
        }
      },
      "removeBase64Images": {
        "type": "boolean"
      },
      "skipTlsVerification": {
        "type": "boolean"
      },
      "storeInCache": {
        "type": "boolean"
      },
      "zeroDataRetention": {
        "type": "boolean"
      },
      "maxAge": {
        "type": "number"
      },
      "proxy": {
        "type": "string",
        "enum": [
          "basic",
          "auto"
        ]
      },
      "filePath": {
        "type": "string",
        "minLength": 1
      },
      "uploadRef": {
        "type": "string",
        "minLength": 1
      },
      "contentType": {
        "type": "string"
      },
      "declaredSizeBytes": {
        "type": "integer",
        "exclusiveMinimum": 0,
        "maximum": 9007199254740991
      }
    },
    "additionalProperties": false
  }
}

Resources 0

No resources advertised.

Prompts 0

No prompts advertised.

Inventory recorded Aug 31, 2026 — 9:05 AM as rev 2. Listing calls only — tools are never invoked.

Canonical contract hash

contract hash — rev 2

sha256:b3576f9850fda608f30ee72f9239056df9aa0b8620150c5b5549f74d455c30dd

Computed centrally from the normalized capability inventory (normalizer v1). Scanners submit raw observations; the control plane normalizes and hashes, so every scanner agrees on the same value.

Revisions 2

Rev	Observed	Hash
rev 2	Aug 31, 2026 — 9:05 AM (17 d ago)
rev 1 baseline	Aug 6, 2026 — 5:00 AM (43 d ago)

Contract changes 1

Breaking 1 breaking change. firecrawl_search.inputSchema.limit changed from number to integer. rev 1 → 2 · 17 d ago

Full snapshots are stored only when the canonical hash changes — unchanged observations update freshness without duplicating the contract.

Recent observations latest 30

Observed	Result	Latency
Sep 17, 2026 — 6:30 PM (2 h ago)	Reachable	69 ms
Sep 17, 2026 — 4:30 PM (4 h ago)	Reachable	149 ms
Sep 17, 2026 — 2:25 PM (6 h ago)	Reachable	146 ms
Sep 17, 2026 — 12:25 PM (8 h ago)	Reachable	50 ms
Sep 17, 2026 — 10:20 AM (10 h ago)	Reachable	63 ms
Sep 17, 2026 — 8:15 AM (12 h ago)	Reachable	51 ms
Sep 17, 2026 — 6:10 AM (14 h ago)	Reachable	80 ms
Sep 17, 2026 — 4:05 AM (16 h ago)	Reachable	157 ms
Sep 17, 2026 — 2:00 AM (18 h ago)	Reachable	71 ms
Sep 16, 2026 — 11:55 PM (20 h ago)	Reachable	76 ms
Sep 16, 2026 — 9:55 PM (22 h ago)	Reachable	123 ms
Sep 16, 2026 — 7:50 PM (1 d ago)	Reachable	59 ms
Sep 16, 2026 — 5:50 PM (1 d ago)	Reachable	157 ms
Sep 16, 2026 — 3:50 PM (1 d ago)	Reachable	102 ms
Sep 16, 2026 — 1:45 PM (1 d ago)	Reachable	78 ms
Sep 16, 2026 — 11:40 AM (1 d ago)	Reachable	70 ms
Sep 16, 2026 — 9:40 AM (1 d ago)	Reachable	135 ms
Sep 16, 2026 — 7:35 AM (2 d ago)	Reachable	74 ms
Sep 16, 2026 — 5:30 AM (2 d ago)	Reachable	132 ms
Sep 16, 2026 — 3:25 AM (2 d ago)	Reachable	125 ms
Sep 16, 2026 — 1:25 AM (2 d ago)	Reachable	70 ms
Sep 15, 2026 — 11:20 PM (2 d ago)	Reachable	190 ms
Sep 15, 2026 — 9:15 PM (2 d ago)	Reachable	147 ms
Sep 15, 2026 — 7:10 PM (2 d ago)	Reachable	135 ms
Sep 15, 2026 — 5:05 PM (2 d ago)	Reachable	90 ms
Sep 15, 2026 — 3:05 PM (2 d ago)	Reachable	62 ms
Sep 15, 2026 — 1:05 PM (2 d ago)	Reachable	69 ms
Sep 15, 2026 — 11:00 AM (2 d ago)	Reachable	137 ms
Sep 15, 2026 — 9:00 AM (2 d ago)	Reachable	141 ms
Sep 15, 2026 — 6:55 AM (3 d ago)	Reachable	1215 ms

Latest check — evidence & validation Sep 17, 2026 — 6:30 PM

Reachable MCP Tools Edge Scanner ScheduledHTTP 20069 msStreamable HTTP2025-06-18

response headers (as observed)

{
  "server": "cloudflare",
  "content-type": "text/event-stream"
}

serverInfo — from initialize

{
  "name": "firecrawl-fastmcp",
  "version": "3.24.1",
  "title": null
}

Server name	`firecrawl-fastmcp`
Server version	`3.24.1`
Transport	Streamable HTTP
Protocol version	`2025-06-18`
First observed	Aug 6, 2026
Last observed	2 h ago
Last successful	2 h ago
Origin	Registry seed

Firecrawl MCP · Firecrawl

Availability — last 30 days

Advertised capabilities

Tools 3

Input schema

Input schema

Input schema

Resources 0

Prompts 0

Canonical contract hash

Revisions 2

Contract changes 1

Recent observations latest 30

Publisher supplied

Independently observed

Name	Firecrawl MCP
Vendor	Firecrawl
Category	data
Docs	https://docs.firecrawl.dev/mcp-server/clients
Repository	—
Auth expected	API key expected