Вход

Официальный сервер Firecrawl для AI-агентов: поиск, скрапинг и взаимодействие с веб-сайтами. Позволяет парсить документы и получать структурированные данные.

нужен ключ Удалённый · Streamable HTTP API-ключ ИИ и модели Веб и поиск Автосборка · 15 просмотров

Что умеет

Официальный сервер Firecrawl для AI-агентов: поиск, скрапинг и взаимодействие с веб-сайтами. Позволяет парсить документы и получать структурированные данные.

Перевод каталога (LLM) · показать оригинал автора

Official Firecrawl MCP server, the context API for AI agents: search, scrape, and interact with the web, plus parse, crawl, map, Agent and Monitor, from any MCP client.

  • Скрейпинг страниц в Markdown или JSON со структурой
  • Автоматическое заполнение форм и навигация по сайтам
  • Мониторинг изменений контента на страницах

Кому пригодится

  • Сбор данных для обучения моделей
  • Резервное копирование веб-сайтов
#batch-processing #claude #content-extraction #data-collection #firecrawl #firecrawl-ai #gemini-cli-extension #javascript-rendering #llm-tools #mcp #mcp-server #model-context-protocol

Подключение

Удалённый сервер: клиент обращается по адресу, код на вашей машине не запускается.

Claude Desktop

claude_desktop_config.json

Cursor

~/.cursor/mcp.json

Windsurf

~/.codeium/windsurf/mcp_config.json

Вставьте блок mcpServers в файл конфигурации своего клиента. Ключи не входят в файл: вместо SET_LOCALLY подставьте свои значения.

{
    "mcpServers": {
        "firecrawl-mcp-server": {
            "url": "https://mcp.firecrawl.dev/v2/mcp",
            "headers": {
                "Authorization": "Bearer SET_LOCALLY"
            }
        }
    }
}

Какие ключи понадобятся

FIRECRAWL_API_KEY

Каталог хранит только имена переменных. Значения задаются у вас локально и никогда не попадают на сервер.

Вызов без установки — через шлюз

Агент вызывает инструменты этого сервера через https://www.n2j.ru/mcphub/mcp: hub_call_tool {"server":"firecrawl-mcp-server","tool":"…","arguments":{…}} Сервер требует авторизации — ключ задаётся на стороне каталога.

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

Инструменты

3 схем · ≈ 3 632 условных токенов

MCP Guard · риск: low

firecrawl_scrape

Scrape one URL and return its content: markdown by default, or HTML, links, screenshots, branding data, or a targeted answer. Use it when the request identifies a page and needs its content or defined fields: the user gives a URL or names a page or PDF and wants it read or summarized, or wants prices, specs, contact details or a table from it. Use firecrawl search when additional web sources are needed; on an authenticated session, firecrawl map lists a site's URLs and firecrawl crawl collects a set of pages. url may omit the scheme ( example.com/page ); it is read as https. Firecrawl may serv

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "url",
        "objective"
    ],
    "properties": {
        "url": {
            "type": "string"
        },
        "proxy": {
            "enum": [
                "basic",
                "stealth",
                "enhanced",
                "auto"
            ],
            "type": "string"
        },
        "maxAge": {
            "type": "number"
        },
        "mobile": {
            "type": "boolean"
        },
        "formats": {
            "type": "array",
            "items": {
                "enum": [
                    "markdown",
                    "html",
                    "rawHtml",
                    "screenshot",
                    "links",
                    "images",
                    "summary",
                    "changeTracking",
                    "branding",
                    "query",
                    "audio"
                ],
                "type": "string"
            }
        },
        "parsers": {
            "type": "array",
            "items": {
                "enum": [
                    "pdf"
                ],
                "type": "string"
            }
        },
        "profile": {
            "type": "object",
            "required": [
                "name"
            ],
            "properties": {
                "name": {
                    "type": "string"
                }
            },
            "description": "Loads a saved browser profile without saving changes to it.",
            "additionalProperties": false
        },
        "timeout": {
            "type": "integer",
            "maximum": 9007199254740991,
            "description": "Execution timeout in milliseconds.",
            "exclusiveMinimum": 0
        },
        "waitFor": {
            "type": "number"
        },
        "location": {
            "type": "object",
            "properties": {
                "country": {
                    "type": "string"
                },
                "languages": {
                    "type": "array",
                    "items": {
                        "type": "string"
                    }
                }
            },
            "additionalProperties": false
        },
        "lockdown": {
            "type": "boolean"
        },
        "objective": {
            "type": "string",
            "maxLength": 1000,
            "minLength": 1,
            "description": "The user's underlying goal for this call, in one sentence: what they are ultimately trying to accomplish, not a restatement of the URL or query. Reuse it across related calls. Avoid sensitive information."
        },
        "redactPII": {
            "type": "boolean"
        },
        "pdfOptions": {
            "type": "object",
            "properties": {
                "maxPages": {
                    "type": "integer",
                    "maximum": 10000,
                    "minimum": 1
                }
            },
            "additionalProperties": false
        },
        "toolDetail": {
            "enum": [
                "compact",
                "summary",
                "full"
            ],
            "type": "string",
            "description": "Domain discovery detail, summary by default; compact returns provider/capability/description, full includes contracts."
        },
        "domainTools": {
            "type": "boolean",
            "description": "Include domain-matched Alexandria tools for the page in tools on the returned document."
        },
        "excludeTags": {
            "type": "array",
            "items": {
                "type": "string"
            }
        },
        "includeTags": {
            "type": "array",
            "items": {
                "type": "string"
            }
        },
        "queryOptions": {
            "type": "object",
            "required": [
                "prompt"
            ],
            "properties": {
                "mode": {
                    "enum": [
                        "directQuote",
                        "freeform"
                    ],
                    "type": "string",
                    "default": "freeform"
                },
                "prompt": {
                    "type": "string",
                    "maxLength": 10000
                }
            },
            "additionalProperties": false
        },
        "storeInCache": {
            "type": "boolean"
        },
        "conversationId": {
            "type": "string",
            "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}$",
            "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."
        },
        "onlyMainContent": {
            "type": "boolean"
        },
        "screenshotOptions": {
            "type": "object",
            "properties": {
                "quality": {
                    "type": "number"
                },
                "fullPage": {
                    "type": "boolean"
                },
                "viewport": {
                    "type": "object",
                    "required": [
                        "width",
                        "height"
                    ],
                    "properties": {
                        "width": {
                            "type": "number"
                        },
                        "height": {
                            "type": "number"
                        }
                    },
                    "additionalProperties": false
                }
            },
            "additionalProperties": false
        },
        "zeroDataRetention": {
            "type": "boolean"
        },
        "removeBase64Images": {
            "type": "boolean"
        },
        "skipTlsVerification": {
            "type": "boolean"
        }
    },
    "additionalProperties": false
}

firecrawl_search

Use this when you need current or specific information from the web: recent events, latest releases and versions, prices, people and companies, statistics, or any fact that may have changed since your training data or that you are not sure of. Returns ranked results with query-relevant highlights; each web result is a title, URL, and description. 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 result types to research , pdf

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
        "query",
        "objective"
    ],
    "properties": {
        "tbs": {
            "type": "string"
        },
        "limit": {
            "type": "integer",
            "maximum": 100,
            "minimum": 1
        },
        "query": {
            "type": "string",
            "minLength": 1,
            "description": "Query for web and semantic tool discovery. Operators include quoted phrases, `-term`, `site:host`, `inurl:term`, `intitle:term`, and `related:host`; the set is non-exhaustive. Browse the whole library with alexandria_library_search."
        },
        "filter": {
            "type": "string"
        },
        "sources": {
            "type": "array",
            "items": {
                "anyOf": [
                    {
                        "enum": [
                            "web",
                            "images",
                            "news",
                            "alexandria",
                            "exchange"
                        ],
                        "type": "string"
                    },
                    {
                        "type": "object",
                        "required": [
                            "type"
                        ],
                        "properties": {
                            "type": {
                                "enum": [
                                    "web",
                                    "images",
                                    "news",
                                    "alexandria",
                                    "exchange"
                                ],
                                "type": "string"
                            }
                        },
                        "additionalProperties": false
                    }
                ]
            },
            "description": "Search sources; authenticated sessions default to web + alexandria, keyless sessions to web only. Authenticated searches always add alexandria to the sources, so sources: [\"web\"] also returns providers; domainTools: false turns off website-matched tools only. enterprise zdr or anon searches do not add it. Use [\"alexandria\"] alone for provider discovery without web results."
        },
        "location": {
            "type": "string"
        },
        "objective": {
            "type": "string",
            "maxLength": 5000,
            "minLength": 1,
            "description": "The user's underlying goal for this call, in one sentence: what they are ultimately trying to accomplish, not a restatement of the URL or query. Reuse it across related calls. Avoid sensitive information."
        },
        "categories": {
            "type": "array",
            "items": {
                "enum": [
                    "research",
                    "pdf",
                    "developer",
                    "gov"
                ],
                "type": "string"
            },
            "description": "Limit results to specific source types. `research` restricts ordinary web results to research-affiliated websites and returns page snippets, which is separate from the `firecrawl_research_*` tools that search paper abstracts and full text across biomedical (PubMed, bioRxiv, medRxiv) and arXiv literature; `pdf` searches PDF results; `developer` searches an index built for coding agents over public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation; `gov` searches the Government Index of US federal, state, and local legal and regulatory sources, the index behind firecrawl_gov_search, and cannot be combined with other categories; gov hits can include historical versions, bill text, agency guidance, and third-party reproductions, so verify the issuer, jurisdiction, enacted/effective status, and version before citing current governing law, clarify a missing jurisdiction or ambiguous as-of date, and use general search for non-US questions or missing coverage (no hits does not establish that no applicable law exists). `developer` and `gov` return hits in `data.web` with `category` set to their name; the other categories also filter `data.web`."
        },
        "enterprise": {
            "type": "array",
            "items": {
                "enum": [
                    "default",
                    "anon",
                    "zdr"
                ],
                "type": "string"
            }
        },
        "highlights": {
            "type": "boolean",
            "description": "Return query-relevant page excerpts for web and news results when available (default). Highlights appear in web `description` and news `snippet`; otherwise, original snippets are returned. Set to false to keep the original search snippets."
        },
        "toolDetail": {
            "enum": [
                "compact",
                "summary",
                "full"
            ],
            "type": "string",
            "description": "Compact by default. Compact returns only provider, capability and description; full includes contracts. Read a selected tool's contract with alexandria_library_search."
        },
        "domainTools": {
            "type": "boolean",
            "description": "Include domain-matched tools for result URLs. Defaults to true when Alexandria is combined with web, news or images; semantic-only search leaves domain matching off."
        },
        "scrapeOptions": {
            "type": "object",
            "properties": {
                "proxy": {
                    "enum": [
                        "basic",
                        "stealth",
                        "enhanced",
                        "auto"
                    ],
                    "type": "string"
                },
                "maxAge": {
                    "type": "number"
                },
                "mobile": {
                    "type": "boolean"
                },
                "formats": {
                    "type": "array",
                    "items": {
                        "enum": [
                            "markdown",
                            "html",
                            "rawHtml",
                            "screenshot",
                            "links",
                            "images",
                            "summary",
                            "changeTracking",
                            "branding",
                            "json",
                            "query",
                            "audio"
                        ],
                        "type": "string"
                    }
                },
                "parsers": {
                    "type": "array",
                    "items": {
                        "enum": [
                            "pdf"
                        ],
                        "type": "string"
                    }
                },
                "profile": {
                    "type": "object",
                    "required": [
                        "name"
                    ],
                    "properties": {
                        "name": {
                            "type": "string"
                        }
                    },
                    "description": "Loads a saved browser profile without saving changes to it.",
                    "additionalProperties": false
                },
                "waitFor": {
                    "type": "number"
                },
                "location": {
                    "type": "object",
                    "properties": {
                        "country": {
                            "type": "string"
                        },
                        "languages": {
                            "type": "array",
                            "items": {
                                "type": "string"
                            }
                        }
                    },
                    "additionalProperties": false
                },
                "lockdown": {
                    "type": "boolean"
                },
                "redactPII": {
                    "type": "boolean"
                },
                "pdfOptions": {
                    "type": "object",
                    "properties": {
                        "maxPages": {
                            "type": "integer",
                            "maximum": 10000,
                            "minimum": 1
                        }
                    },
                    "additionalProperties": false
                },
                "excludeTags": {
                    "type": "array",
                    "items": {
                        "type": "string"
                    }
                },
                "includeTags": {
                    "type": "array",
                    "items": {
                        "type": "string"
                    }
                },
                "jsonOptions": {
                    "type": "object",
                    "properties": {
                        "prompt": {
                            "type": "string"
                        },
                        "schema": {
                            "type": "object",
                            "propertyNames": {
                                "type": "string"
                            },
                            "additionalProperties": true
                        }
                    },
                    "additionalProperties": false
                },
                "queryOptions": {
                    "type": "object",
                    "required": [
                        "prompt"
                    ],
                    "properties": {
                        "mode": {
                            "enum": [
                                "directQuote",
                                "freeform"
                            ],
                            "type": "string",
                            "default": "freeform"
                        },
                        "prompt": {
                            "type": "string",
                            "maxLength": 10000
                        }
                    },
                    "additionalProperties": false
                },
                "storeInCache": {
                    "type": "boolean"
                },
                "onlyMainContent": {
                    "type": "boolean"
                },
                "screenshotOptions": {
                    "type": "object",
                    "properties": {
                        "quality": {
                            "type": "number"
                        },
                        "fullPage": {
                            "type": "boolean"
                        },
                        "viewport": {
                            "type": "object",
                            "required": [
                                "width",
                                "height"
                            ],
                            "properties": {
                                "width": {
                                    "type": "number"
                                },
                                "height": {
                                    "type": "number"
                                }
                            },
                            "additionalProperties": false
                        }
                    },
                    "additionalProperties": false
                },
                "removeBase64Images": {
                    "type": "boolean"
                },
                "skipTlsVerification": {
                    "type": "boolean"
                }
            },
            "description": "Fetches the full page of every web result in the same call, and each fetched result is billed as a scrape. Leave it unset unless the task needs the full text of a few results: highlights usually answer, and firecrawl_scrape can fetch only the URLs you need. These fetches ignore maxAge, so use firecrawl_scrape for a live fetch. scrapeOptions fetches web pages, never Alexandria provider tools.",
            "additionalProperties": false
        },
        "conversationId": {
            "type": "string",
            "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}$",
            "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."
        },
        "excludeDomains": {
            "type": "array",
            "items": {
                "type": "string",
                "pattern": "^(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\\.)+[a-z0-9][a-z0-9-]{0,61}[a-z0-9]$",
                "maxLength": 253,
                "minLength": 1
            },
            "description": "Hostnames to leave out of results. Mutually exclusive with includeDomains."
        },
        "includeDomains": {
            "type": "array",
            "items": {
                "type": "string",
                "pattern": "^(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\\.)+[a-z0-9][a-z0-9-]{0,61}[a-z0-9]$",
                "maxLength": 253,
                "minLength": 1
            },
            "description": "Hostnames to restrict results to. Mutually exclusive with excludeDomains."
        }
    },
    "additionalProperties": false
}

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 inform

Показать схему аргументов
{
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
        "proxy": {
            "enum": [
                "basic",
                "auto"
            ],
            "type": "string"
        },
        "maxAge": {
            "type": "number",
            "description": "Ignored: parse never reuses or stores indexed content."
        },
        "formats": {
            "type": "array",
            "items": {
                "enum": [
                    "markdown",
                    "html",
                    "rawHtml",
                    "links",
                    "summary",
                    "json",
                    "query"
                ],
                "type": "string"
            }
        },
        "parsers": {
            "type": "array",
            "items": {
                "enum": [
                    "pdf"
                ],
                "type": "string"
            }
        },
        "filePath": {
            "type": "string",
            "minLength": 1,
            "description": "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": {
            "type": "boolean"
        },
        "uploadRef": {
            "type": "string",
            "minLength": 1,
            "description": "Phase 2 only: short-lived upload reference returned by phase 1 after the local PUT upload completes."
        },
        "pdfOptions": {
            "type": "object",
            "properties": {
                "maxPages": {
                    "type": "integer",
                    "maximum": 10000,
                    "minimum": 1
                }
            },
            "additionalProperties": false
        },
        "contentType": {
            "type": "string",
            "description": "Phase 1 MIME type override. If omitted, the server infers it from the file extension without reading the file."
        },
        "excludeTags": {
            "type": "array",
            "items": {
                "type": "string"
            }
        },
        "includeTags": {
            "type": "array",
            "items": {
                "type": "string"
            }
        },
        "jsonOptions": {
            "type": "object",
            "properties": {
                "prompt": {
                    "type": "string"
                },
                "schema": {
                    "type": "object",
                    "propertyNames": {
                        "type": "string"
                    },
                    "additionalProperties": true
                }
            },
            "additionalProperties": false
        },
        "queryOptions": {
            "type": "object",
            "required": [
                "prompt"
            ],
            "properties": {
                "mode": {
                    "enum": [
                        "directQuote",
                        "freeform"
                    ],
                    "type": "string",
                    "default": "freeform"
                },
                "prompt": {
                    "type": "string",
                    "maxLength": 10000
                }
            },
            "additionalProperties": false
        },
        "storeInCache": {
            "type": "boolean"
        },
        "conversationId": {
            "type": "string",
            "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}$",
            "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."
        },
        "onlyMainContent": {
            "type": "boolean"
        },
        "declaredSizeBytes": {
            "type": "integer",
            "maximum": 9007199254740991,
            "description": "Optional phase 1 size declaration. Hosted MCP does not stat the file; provide this only if the caller already knows it.",
            "exclusiveMinimum": 0
        },
        "zeroDataRetention": {
            "type": "boolean"
        },
        "removeBase64Images": {
            "type": "boolean"
        },
        "skipTlsVerification": {
            "type": "boolean"
        }
    },
    "additionalProperties": false
}

Статическая проверка MCP Guard

Эвристический разбор описаний инструментов. Это не проверка исполняемого кода и не гарантия безопасности.

low: 6 high: 0 medium: 0
  • firecrawl_scrape · low

    Не указано, может ли вызов менять состояние; выставьте корректные аннотации MCP.

  • firecrawl_scrape · low

    Поле «url» не объясняет допустимые значения.

  • firecrawl_search · low

    Не указано, может ли вызов менять состояние; выставьте корректные аннотации MCP.

  • firecrawl_search · low

    Поле «limit» не объясняет допустимые значения.

  • firecrawl_parse · low

    Не указано, может ли вызов менять состояние; выставьте корректные аннотации MCP.

  • firecrawl_parse · low

    Поле «formats» не объясняет допустимые значения.