code2mcp

{ "timestamp": "2025-11-17T23:29:02.186Z", "scenarioA": { "preloadTokens": 3843, "toolUsageTokens": 130, "totalTokens": 3981, "duration": 3543, "toolCallsNeeded": 2, "description": "## context7__resolve-library-id\n[context7] Resolves a package/product name to a Context7-compatible library ID and returns a list of matching libraries.\n\nYou MUST call this function before 'get-library-docs' to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nSelection Process:\n1. Analyze the query to understand what library/package the user is looking for\n2. Return the most relevant match based on:\n- Name similarity to the query (exact matches prioritized)\n- Description relevance to the query's intent\n- Documentation coverage (prioritize libraries with higher Code Snippet counts)\n- Source reputation (consider libraries with High or Medium reputation more authoritative)\n- Benchmark Score: Quality indicator (100 is the highest score)\n\nResponse Format:\n- Return the selected library ID in a clearly marked section\n- Provide a brief explanation for why this library was chosen\n- If multiple good matches exist, acknowledge this but proceed with the most relevant one\n- If no good matches exist, clearly state this and suggest query refinements\n\nFor ambiguous queries, request clarification before proceeding with a best-guess match.\n**Parameters:** libraryName: string\n\n## context7__get-library-docs\n[context7] Fetches up-to-date documentation for a library. You must call 'resolve-library-id' first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n**Parameters:** context7CompatibleLibraryID: string, topic?: string, page?: integer\n\n## playwright__start_codegen_session\n[playwright] Start a new code generation session to record Playwright actions\n**Parameters:** options: object\n\n## playwright__end_codegen_session\n[playwright] End a code generation session and generate the test file\n**Parameters:** sessionId: string\n\n## playwright__get_codegen_session\n[playwright] Get information about a code generation session\n**Parameters:** sessionId: string\n\n## playwright__clear_codegen_session\n[playwright] Clear a code generation session without generating a test\n**Parameters:** sessionId: string\n\n## playwright__playwright_navigate\n[playwright] Navigate to a URL\n**Parameters:** url: string, browserType?: string, width?: number, height?: number, timeout?: number, waitUntil?: string, headless?: boolean\n\n## playwright__playwright_screenshot\n[playwright] Take a screenshot of the current page or a specific element\n**Parameters:** name: string, selector?: string, width?: number, height?: number, storeBase64?: boolean, fullPage?: boolean, savePng?: boolean, downloadsDir?: string\n\n## playwright__playwright_click\n[playwright] Click an element on the page\n**Parameters:** selector: string\n\n## playwright__playwright_iframe_click\n[playwright] Click an element in an iframe on the page\n**Parameters:** iframeSelector: string, selector: string\n\n## playwright__playwright_iframe_fill\n[playwright] Fill an element in an iframe on the page\n**Parameters:** iframeSelector: string, selector: string, value: string\n\n## playwright__playwright_fill\n[playwright] fill out an input field\n**Parameters:** selector: string, value: string\n\n## playwright__playwright_select\n[playwright] Select an element on the page with Select tag\n**Parameters:** selector: string, value: string\n\n## playwright__playwright_hover\n[playwright] Hover an element on the page\n**Parameters:** selector: string\n\n## playwright__playwright_upload_file\n[playwright] Upload a file to an input[type='file'] element on the page\n**Parameters:** selector: string, filePath: string\n\n## playwright__playwright_evaluate\n[playwright] Execute JavaScript in the browser console\n**Parameters:** script: string\n\n## playwright__playwright_console_logs\n[playwright] Retrieve console logs from the browser with filtering options\n**Parameters:** type?: string, search?: string, limit?: number, clear?: boolean\n\n## playwright__playwright_close\n[playwright] Close the browser and release all resources\n\n## playwright__playwright_get\n[playwright] Perform an HTTP GET request\n**Parameters:** url: string\n\n## playwright__playwright_post\n[playwright] Perform an HTTP POST request\n**Parameters:** url: string, value: string, token?: string, headers?: object\n\n## playwright__playwright_put\n[playwright] Perform an HTTP PUT request\n**Parameters:** url: string, value: string\n\n## playwright__playwright_patch\n[playwright] Perform an HTTP PATCH request\n**Parameters:** url: string, value: string\n\n## playwright__playwright_delete\n[playwright] Perform an HTTP DELETE request\n**Parameters:** url: string\n\n## playwright__playwright_expect_response\n[playwright] Ask Playwright to start waiting for a HTTP response. This tool initiates the wait operation but does not wait for its completion.\n**Parameters:** id: string, url: string\n\n## playwright__playwright_assert_response\n[playwright] Wait for and validate a previously initiated HTTP response wait operation.\n**Parameters:** id: string, value?: string\n\n## playwright__playwright_custom_user_agent\n[playwright] Set a custom User Agent for the browser\n**Parameters:** userAgent: string\n\n## playwright__playwright_get_visible_text\n[playwright] Get the visible text content of the current page\n\n## playwright__playwright_get_visible_html\n[playwright] Get the HTML content of the current page. By default, all <script> tags are removed from the output unless removeScripts is explicitly set to false.\n**Parameters:** selector?: string, removeScripts?: boolean, removeComments?: boolean, removeStyles?: boolean, removeMeta?: boolean, cleanHtml?: boolean, minify?: boolean, maxLength?: number\n\n## playwright__playwright_go_back\n[playwright] Navigate back in browser history\n\n## playwright__playwright_go_forward\n[playwright] Navigate forward in browser history\n\n## playwright__playwright_drag\n[playwright] Drag an element to a target location\n**Parameters:** sourceSelector: string, targetSelector: string\n\n## playwright__playwright_press_key\n[playwright] Press a keyboard key\n**Parameters:** key: string, selector?: string\n\n## playwright__playwright_save_as_pdf\n[playwright] Save the current page as a PDF file\n**Parameters:** outputPath: string, filename?: string, format?: string, printBackground?: boolean, margin?: object\n\n## playwright__playwright_click_and_switch_tab\n[playwright] Click a link and switch to the newly opened tab\n**Parameters:** selector: string\n\n## firecrawl-mcp__firecrawl_scrape\n[firecrawl-mcp] \nScrape content from a single URL with advanced options. \nThis is the most powerful, fastest and most reliable scraper tool, if available you should always default to using this tool for any web scraping needs.\n\n**Best for:** Single page content extraction, when you know exactly which page contains the information.\n**Not recommended for:** Multiple pages (use batch_scrape), unknown page (use search), structured data (use extract).\n**Common mistakes:** Using scrape for a list of URLs (use batch_scrape instead). If batch scrape doesnt work, just use scrape and call it multiple times.\n**Prompt Example:** \"Get the content of the page at https://example.com.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_scrape\",\n \"arguments\": {\n \"url\": \"https://example.com\",\n \"formats\": [\"markdown\"],\n \"maxAge\": 172800000\n }\n}\n```\n**Performance:** Add maxAge parameter for 500% faster scrapes using cached data.\n**Returns:** Markdown, HTML, or other formats as specified.\n\n\n**Parameters:** url: string, formats?: array, parsers?: array, onlyMainContent?: boolean, includeTags?: array, excludeTags?: array, waitFor?: number, actions?: array, mobile?: boolean, skipTlsVerification?: boolean, removeBase64Images?: boolean, location?: object, storeInCache?: boolean, maxAge?: number\n\n## firecrawl-mcp__firecrawl_map\n[firecrawl-mcp] \nMap a website to discover all indexed URLs on the site.\n\n**Best for:** Discovering URLs on a website before deciding what to scrape; finding specific sections of a website.\n**Not recommended for:** When you already know which specific URL you need (use scrape or batch_scrape); when you need the content of the pages (use scrape after mapping).\n**Common mistakes:** Using crawl to discover URLs instead of map.\n**Prompt Example:** \"List all URLs on example.com.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_map\",\n \"arguments\": {\n \"url\": \"https://example.com\"\n }\n}\n```\n**Returns:** Array of URLs found on the site.\n\n**Parameters:** url: string, search?: string, sitemap?: string, includeSubdomains?: boolean, limit?: number, ignoreQueryParameters?: boolean\n\n## firecrawl-mcp__firecrawl_search\n[firecrawl-mcp] \nSearch the web and optionally extract content from search results. This is the most powerful web search tool available, and if available you should always default to using this tool for any web search needs.\n\nThe query also supports search operators, that you can use if needed to refine the search:\n| Operator | Functionality | Examples |\n---|-|-|\n| `\"\"` | Non-fuzzy matches a string of text | `\"Firecrawl\"`\n| `-` | Excludes certain keywords or negates other operators | `-bad`, `-site:firecrawl.dev`\n| `site:` | Only returns results from a specified website | `site:firecrawl.dev`\n| `inurl:` | Only returns results that include a word in the URL | `inurl:firecrawl`\n| `allinurl:` | Only returns results that include multiple words in the URL | `allinurl:git firecrawl`\n| `intitle:` | Only returns results that include a word in the title of the page | `intitle:Firecrawl`\n| `allintitle:` | Only returns results that include multiple words in the title of the page | `allintitle:firecrawl playground`\n| `related:` | Only returns results that are related to a specific domain | `related:firecrawl.dev`\n| `imagesize:` | Only returns images with exact dimensions | `imagesize:1920x1080`\n| `larger:` | Only returns images larger than specified dimensions | `larger:1920x1080`\n\n**Best for:** Finding specific information across multiple websites, when you don't know which website has the information; when you need the most relevant content for a query.\n**Not recommended for:** When you need to search the filesystem. When you already know which website to scrape (use scrape); when you need comprehensive coverage of a single website (use map or crawl.\n**Common mistakes:** Using crawl or map for open-ended questions (use search instead).\n**Prompt Example:** \"Find the latest research papers on AI published in 2023.\"\n**Sources:** web, images, news, default to web unless needed images or news.\n**Scrape Options:** Only use scrapeOptions when you think it is absolutely necessary. When you do so default to a lower limit to avoid timeouts, 5 or lower.\n**Optimal Workflow:** Search first using firecrawl_search without formats, then after fetching the results, use the scrape tool to get the content of the relevantpage(s) that you want to scrape\n\n**Usage Example without formats (Preferred):**\n```json\n{\n \"name\": \"firecrawl_search\",\n \"arguments\": {\n \"query\": \"top AI companies\",\n \"limit\": 5,\n \"sources\": [\n \"web\"\n ]\n }\n}\n```\n**Usage Example with formats:**\n```json\n{\n \"name\": \"firecrawl_search\",\n \"arguments\": {\n \"query\": \"latest AI research papers 2023\",\n \"limit\": 5,\n \"lang\": \"en\",\n \"country\": \"us\",\n \"sources\": [\n \"web\",\n \"images\",\n \"news\"\n ],\n \"scrapeOptions\": {\n \"formats\": [\"markdown\"],\n \"onlyMainContent\": true\n }\n }\n}\n```\n**Returns:** Array of search results (with optional scraped content).\n\n**Parameters:** query: string, limit?: number, tbs?: string, filter?: string, location?: string, sources?: array, scrapeOptions?: object\n\n## firecrawl-mcp__firecrawl_crawl\n[firecrawl-mcp] \n Starts a crawl job on a website and extracts content from all pages.\n \n **Best for:** Extracting content from multiple related pages, when you need comprehensive coverage.\n **Not recommended for:** Extracting content from a single page (use scrape); when token limits are a concern (use map + batch_scrape); when you need fast results (crawling can be slow).\n **Warning:** Crawl responses can be very large and may exceed token limits. Limit the crawl depth and number of pages, or use map + batch_scrape for better control.\n **Common mistakes:** Setting limit or maxDiscoveryDepth too high (causes token overflow) or too low (causes missing pages); using crawl for a single page (use scrape instead). Using a /* wildcard is not recommended.\n **Prompt Example:** \"Get all blog posts from the first two levels of example.com/blog.\"\n **Usage Example:**\n ```json\n {\n \"name\": \"firecrawl_crawl\",\n \"arguments\": {\n \"url\": \"https://example.com/blog/*\",\n \"maxDiscoveryDepth\": 5,\n \"limit\": 20,\n \"allowExternalLinks\": false,\n \"deduplicateSimilarURLs\": true,\n \"sitemap\": \"include\"\n }\n }\n ```\n **Returns:** Operation ID for status checking; use firecrawl_check_crawl_status to check progress.\n \n \n**Parameters:** url: string, prompt?: string, excludePaths?: array, includePaths?: array, maxDiscoveryDepth?: number, sitemap?: string, limit?: number, allowExternalLinks?: boolean, allowSubdomains?: boolean, crawlEntireDomain?: boolean, delay?: number, maxConcurrency?: number, webhook?: any, deduplicateSimilarURLs?: boolean, ignoreQueryParameters?: boolean, scrapeOptions?: object\n\n## firecrawl-mcp__firecrawl_check_crawl_status\n[firecrawl-mcp] \nCheck the status of a crawl job.\n\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_check_crawl_status\",\n \"arguments\": {\n \"id\": \"550e8400-e29b-41d4-a716-446655440000\"\n }\n}\n```\n**Returns:** Status and progress of the crawl job, including results if available.\n\n**Parameters:** id: string\n\n## firecrawl-mcp__firecrawl_extract\n[firecrawl-mcp] \nExtract structured information from web pages using LLM capabilities. Supports both cloud AI and self-hosted LLM extraction.\n\n**Best for:** Extracting specific structured data like prices, names, details from web pages.\n**Not recommended for:** When you need the full content of a page (use scrape); when you're not looking for specific structured data.\n**Arguments:**\n- urls: Array of URLs to extract information from\n- prompt: Custom prompt for the LLM extraction\n- schema: JSON schema for structured data extraction\n- allowExternalLinks: Allow extraction from external links\n- enableWebSearch: Enable web search for additional context\n- includeSubdomains: Include subdomains in extraction\n**Prompt Example:** \"Extract the product name, price, and description from these product pages.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_extract\",\n \"arguments\": {\n \"urls\": [\"https://example.com/page1\", \"https://example.com/page2\"],\n \"prompt\": \"Extract product information including name, price, and description\",\n \"schema\": {\n \"type\": \"object\",\n \"properties\": {\n \"name\": { \"type\": \"string\" },\n \"price\": { \"type\": \"number\" },\n \"description\": { \"type\": \"string\" }\n },\n \"required\": [\"name\", \"price\"]\n },\n \"allowExternalLinks\": false,\n \"enableWebSearch\": false,\n \"includeSubdomains\": false\n }\n}\n```\n**Returns:** Extracted structured data as defined by your schema.\n\n**Parameters:** urls: array, prompt?: string, schema?: object, allowExternalLinks?: boolean, enableWebSearch?: boolean, includeSubdomains?: boolean\n\n" }, "scenarioB": { "preloadTokens": 3967, "toolUsageTokens": 92, "totalTokens": 4067, "duration": 3523, "toolCallsNeeded": 1, "description": "# Execute TypeScript Code with MCP Tool Access\n\nYou can execute TypeScript code that calls MCP tools using the execute_code tool.\n\n**Available APIs:**\n\n\n**context7**:\n - `__mcp_call('context7__resolve-library-id', {libraryName: value})`\n [context7] Resolves a package/product name to a Context7-compatible library ID and returns a list of matching libraries.\n\nYou MUST call this function before 'get-library-docs' to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nSelection Process:\n1. Analyze the query to understand what library/package the user is looking for\n2. Return the most relevant match based on:\n- Name similarity to the query (exact matches prioritized)\n- Description relevance to the query's intent\n- Documentation coverage (prioritize libraries with higher Code Snippet counts)\n- Source reputation (consider libraries with High or Medium reputation more authoritative)\n- Benchmark Score: Quality indicator (100 is the highest score)\n\nResponse Format:\n- Return the selected library ID in a clearly marked section\n- Provide a brief explanation for why this library was chosen\n- If multiple good matches exist, acknowledge this but proceed with the most relevant one\n- If no good matches exist, clearly state this and suggest query refinements\n\nFor ambiguous queries, request clarification before proceeding with a best-guess match.\n - `__mcp_call('context7__get-library-docs', {context7CompatibleLibraryID: value, topic: value, page: value})`\n [context7] Fetches up-to-date documentation for a library. You must call 'resolve-library-id' first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\n**playwright**:\n - `__mcp_call('playwright__start_codegen_session', {options: value})`\n [playwright] Start a new code generation session to record Playwright actions\n - `__mcp_call('playwright__end_codegen_session', {sessionId: value})`\n [playwright] End a code generation session and generate the test file\n - `__mcp_call('playwright__get_codegen_session', {sessionId: value})`\n [playwright] Get information about a code generation session\n - `__mcp_call('playwright__clear_codegen_session', {sessionId: value})`\n [playwright] Clear a code generation session without generating a test\n - `__mcp_call('playwright__playwright_navigate', {url: value, browserType: value, width: value, height: value, timeout: value, waitUntil: value, headless: value})`\n [playwright] Navigate to a URL\n - `__mcp_call('playwright__playwright_screenshot', {name: value, selector: value, width: value, height: value, storeBase64: value, fullPage: value, savePng: value, downloadsDir: value})`\n [playwright] Take a screenshot of the current page or a specific element\n - `__mcp_call('playwright__playwright_click', {selector: value})`\n [playwright] Click an element on the page\n - `__mcp_call('playwright__playwright_iframe_click', {iframeSelector: value, selector: value})`\n [playwright] Click an element in an iframe on the page\n - `__mcp_call('playwright__playwright_iframe_fill', {iframeSelector: value, selector: value, value: value})`\n [playwright] Fill an element in an iframe on the page\n - `__mcp_call('playwright__playwright_fill', {selector: value, value: value})`\n [playwright] fill out an input field\n - `__mcp_call('playwright__playwright_select', {selector: value, value: value})`\n [playwright] Select an element on the page with Select tag\n - `__mcp_call('playwright__playwright_hover', {selector: value})`\n [playwright] Hover an element on the page\n - `__mcp_call('playwright__playwright_upload_file', {selector: value, filePath: value})`\n [playwright] Upload a file to an input[type='file'] element on the page\n - `__mcp_call('playwright__playwright_evaluate', {script: value})`\n [playwright] Execute JavaScript in the browser console\n - `__mcp_call('playwright__playwright_console_logs', {type: value, search: value, limit: value, clear: value})`\n [playwright] Retrieve console logs from the browser with filtering options\n - `__mcp_call('playwright__playwright_close', {})`\n [playwright] Close the browser and release all resources\n - `__mcp_call('playwright__playwright_get', {url: value})`\n [playwright] Perform an HTTP GET request\n - `__mcp_call('playwright__playwright_post', {url: value, value: value, token: value, headers: value})`\n [playwright] Perform an HTTP POST request\n - `__mcp_call('playwright__playwright_put', {url: value, value: value})`\n [playwright] Perform an HTTP PUT request\n - `__mcp_call('playwright__playwright_patch', {url: value, value: value})`\n [playwright] Perform an HTTP PATCH request\n - `__mcp_call('playwright__playwright_delete', {url: value})`\n [playwright] Perform an HTTP DELETE request\n - `__mcp_call('playwright__playwright_expect_response', {id: value, url: value})`\n [playwright] Ask Playwright to start waiting for a HTTP response. This tool initiates the wait operation but does not wait for its completion.\n - `__mcp_call('playwright__playwright_assert_response', {id: value, value: value})`\n [playwright] Wait for and validate a previously initiated HTTP response wait operation.\n - `__mcp_call('playwright__playwright_custom_user_agent', {userAgent: value})`\n [playwright] Set a custom User Agent for the browser\n - `__mcp_call('playwright__playwright_get_visible_text', {})`\n [playwright] Get the visible text content of the current page\n - `__mcp_call('playwright__playwright_get_visible_html', {selector: value, removeScripts: value, removeComments: value, removeStyles: value, removeMeta: value, cleanHtml: value, minify: value, maxLength: value})`\n [playwright] Get the HTML content of the current page. By default, all <script> tags are removed from the output unless removeScripts is explicitly set to false.\n - `__mcp_call('playwright__playwright_go_back', {})`\n [playwright] Navigate back in browser history\n - `__mcp_call('playwright__playwright_go_forward', {})`\n [playwright] Navigate forward in browser history\n - `__mcp_call('playwright__playwright_drag', {sourceSelector: value, targetSelector: value})`\n [playwright] Drag an element to a target location\n - `__mcp_call('playwright__playwright_press_key', {key: value, selector: value})`\n [playwright] Press a keyboard key\n - `__mcp_call('playwright__playwright_save_as_pdf', {outputPath: value, filename: value, format: value, printBackground: value, margin: value})`\n [playwright] Save the current page as a PDF file\n - `__mcp_call('playwright__playwright_click_and_switch_tab', {selector: value})`\n [playwright] Click a link and switch to the newly opened tab\n\n**firecrawl-mcp**:\n - `__mcp_call('firecrawl-mcp__firecrawl_scrape', {url: value, formats: value, parsers: value, onlyMainContent: value, includeTags: value, excludeTags: value, waitFor: value, actions: value, mobile: value, skipTlsVerification: value, removeBase64Images: value, location: value, storeInCache: value, maxAge: value})`\n [firecrawl-mcp] \nScrape content from a single URL with advanced options. \nThis is the most powerful, fastest and most reliable scraper tool, if available you should always default to using this tool for any web scraping needs.\n\n**Best for:** Single page content extraction, when you know exactly which page contains the information.\n**Not recommended for:** Multiple pages (use batch_scrape), unknown page (use search), structured data (use extract).\n**Common mistakes:** Using scrape for a list of URLs (use batch_scrape instead). If batch scrape doesnt work, just use scrape and call it multiple times.\n**Prompt Example:** \"Get the content of the page at https://example.com.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_scrape\",\n \"arguments\": {\n \"url\": \"https://example.com\",\n \"formats\": [\"markdown\"],\n \"maxAge\": 172800000\n }\n}\n```\n**Performance:** Add maxAge parameter for 500% faster scrapes using cached data.\n**Returns:** Markdown, HTML, or other formats as specified.\n\n\n - `__mcp_call('firecrawl-mcp__firecrawl_map', {url: value, search: value, sitemap: value, includeSubdomains: value, limit: value, ignoreQueryParameters: value})`\n [firecrawl-mcp] \nMap a website to discover all indexed URLs on the site.\n\n**Best for:** Discovering URLs on a website before deciding what to scrape; finding specific sections of a website.\n**Not recommended for:** When you already know which specific URL you need (use scrape or batch_scrape); when you need the content of the pages (use scrape after mapping).\n**Common mistakes:** Using crawl to discover URLs instead of map.\n**Prompt Example:** \"List all URLs on example.com.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_map\",\n \"arguments\": {\n \"url\": \"https://example.com\"\n }\n}\n```\n**Returns:** Array of URLs found on the site.\n\n - `__mcp_call('firecrawl-mcp__firecrawl_search', {query: value, limit: value, tbs: value, filter: value, location: value, sources: value, scrapeOptions: value})`\n [firecrawl-mcp] \nSearch the web and optionally extract content from search results. This is the most powerful web search tool available, and if available you should always default to using this tool for any web search needs.\n\nThe query also supports search operators, that you can use if needed to refine the search:\n| Operator | Functionality | Examples |\n---|-|-|\n| `\"\"` | Non-fuzzy matches a string of text | `\"Firecrawl\"`\n| `-` | Excludes certain keywords or negates other operators | `-bad`, `-site:firecrawl.dev`\n| `site:` | Only returns results from a specified website | `site:firecrawl.dev`\n| `inurl:` | Only returns results that include a word in the URL | `inurl:firecrawl`\n| `allinurl:` | Only returns results that include multiple words in the URL | `allinurl:git firecrawl`\n| `intitle:` | Only returns results that include a word in the title of the page | `intitle:Firecrawl`\n| `allintitle:` | Only returns results that include multiple words in the title of the page | `allintitle:firecrawl playground`\n| `related:` | Only returns results that are related to a specific domain | `related:firecrawl.dev`\n| `imagesize:` | Only returns images with exact dimensions | `imagesize:1920x1080`\n| `larger:` | Only returns images larger than specified dimensions | `larger:1920x1080`\n\n**Best for:** Finding specific information across multiple websites, when you don't know which website has the information; when you need the most relevant content for a query.\n**Not recommended for:** When you need to search the filesystem. When you already know which website to scrape (use scrape); when you need comprehensive coverage of a single website (use map or crawl.\n**Common mistakes:** Using crawl or map for open-ended questions (use search instead).\n**Prompt Example:** \"Find the latest research papers on AI published in 2023.\"\n**Sources:** web, images, news, default to web unless needed images or news.\n**Scrape Options:** Only use scrapeOptions when you think it is absolutely necessary. When you do so default to a lower limit to avoid timeouts, 5 or lower.\n**Optimal Workflow:** Search first using firecrawl_search without formats, then after fetching the results, use the scrape tool to get the content of the relevantpage(s) that you want to scrape\n\n**Usage Example without formats (Preferred):**\n```json\n{\n \"name\": \"firecrawl_search\",\n \"arguments\": {\n \"query\": \"top AI companies\",\n \"limit\": 5,\n \"sources\": [\n \"web\"\n ]\n }\n}\n```\n**Usage Example with formats:**\n```json\n{\n \"name\": \"firecrawl_search\",\n \"arguments\": {\n \"query\": \"latest AI research papers 2023\",\n \"limit\": 5,\n \"lang\": \"en\",\n \"country\": \"us\",\n \"sources\": [\n \"web\",\n \"images\",\n \"news\"\n ],\n \"scrapeOptions\": {\n \"formats\": [\"markdown\"],\n \"onlyMainContent\": true\n }\n }\n}\n```\n**Returns:** Array of search results (with optional scraped content).\n\n - `__mcp_call('firecrawl-mcp__firecrawl_crawl', {url: value, prompt: value, excludePaths: value, includePaths: value, maxDiscoveryDepth: value, sitemap: value, limit: value, allowExternalLinks: value, allowSubdomains: value, crawlEntireDomain: value, delay: value, maxConcurrency: value, webhook: value, deduplicateSimilarURLs: value, ignoreQueryParameters: value, scrapeOptions: value})`\n [firecrawl-mcp] \n Starts a crawl job on a website and extracts content from all pages.\n \n **Best for:** Extracting content from multiple related pages, when you need comprehensive coverage.\n **Not recommended for:** Extracting content from a single page (use scrape); when token limits are a concern (use map + batch_scrape); when you need fast results (crawling can be slow).\n **Warning:** Crawl responses can be very large and may exceed token limits. Limit the crawl depth and number of pages, or use map + batch_scrape for better control.\n **Common mistakes:** Setting limit or maxDiscoveryDepth too high (causes token overflow) or too low (causes missing pages); using crawl for a single page (use scrape instead). Using a /* wildcard is not recommended.\n **Prompt Example:** \"Get all blog posts from the first two levels of example.com/blog.\"\n **Usage Example:**\n ```json\n {\n \"name\": \"firecrawl_crawl\",\n \"arguments\": {\n \"url\": \"https://example.com/blog/*\",\n \"maxDiscoveryDepth\": 5,\n \"limit\": 20,\n \"allowExternalLinks\": false,\n \"deduplicateSimilarURLs\": true,\n \"sitemap\": \"include\"\n }\n }\n ```\n **Returns:** Operation ID for status checking; use firecrawl_check_crawl_status to check progress.\n \n \n - `__mcp_call('firecrawl-mcp__firecrawl_check_crawl_status', {id: value})`\n [firecrawl-mcp] \nCheck the status of a crawl job.\n\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_check_crawl_status\",\n \"arguments\": {\n \"id\": \"550e8400-e29b-41d4-a716-446655440000\"\n }\n}\n```\n**Returns:** Status and progress of the crawl job, including results if available.\n\n - `__mcp_call('firecrawl-mcp__firecrawl_extract', {urls: value, prompt: value, schema: value, allowExternalLinks: value, enableWebSearch: value, includeSubdomains: value})`\n [firecrawl-mcp] \nExtract structured information from web pages using LLM capabilities. Supports both cloud AI and self-hosted LLM extraction.\n\n**Best for:** Extracting specific structured data like prices, names, details from web pages.\n**Not recommended for:** When you need the full content of a page (use scrape); when you're not looking for specific structured data.\n**Arguments:**\n- urls: Array of URLs to extract information from\n- prompt: Custom prompt for the LLM extraction\n- schema: JSON schema for structured data extraction\n- allowExternalLinks: Allow extraction from external links\n- enableWebSearch: Enable web search for additional context\n- includeSubdomains: Include subdomains in extraction\n**Prompt Example:** \"Extract the product name, price, and description from these product pages.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_extract\",\n \"arguments\": {\n \"urls\": [\"https://example.com/page1\", \"https://example.com/page2\"],\n \"prompt\": \"Extract product information including name, price, and description\",\n \"schema\": {\n \"type\": \"object\",\n \"properties\": {\n \"name\": { \"type\": \"string\" },\n \"price\": { \"type\": \"number\" },\n \"description\": { \"type\": \"string\" }\n },\n \"required\": [\"name\", \"price\"]\n },\n \"allowExternalLinks\": false,\n \"enableWebSearch\": false,\n \"includeSubdomains\": false\n }\n}\n```\n**Returns:** Extracted structured data as defined by your schema.\n\n\n**Example Usage:**\n\n```typescript\nconst result = await __mcp_call('context7__resolve-library-id', {\n libraryName: 'react'\n});\nconsole.log('Result:', result);\n```\n" }, "analysis": { "tokenSavings": -86, "tokenSavingsPercent": -2.2, "speedDiff": 20 } }