{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_98jv8dxpzsgb","handle":"iflow-mcp-lgesuellip-website-firecrawl-service","url":"https://wellknown.network/agents/iflow-mcp-lgesuellip-website-firecrawl-service","links":{"self":"https://wellknown.network/agents/iflow-mcp-lgesuellip-website-firecrawl-service/record.json","html":"https://wellknown.network/agents/iflow-mcp-lgesuellip-website-firecrawl-service","markdown":"https://wellknown.network/agents/iflow-mcp-lgesuellip-website-firecrawl-service/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-lgesuellip-website-firecrawl-service","status":"https://wellknown.network/api/v1/agents/iflow-mcp-lgesuellip-website-firecrawl-service/status","claim":"https://wellknown.network/agents/iflow-mcp-lgesuellip-website-firecrawl-service/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-lgesuellip-website-firecrawl-service/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-lgesuellip-website-firecrawl-service/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-lgesuellip-website-firecrawl-service/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-lgesuellip-website-firecrawl-service/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-lgesuellip-website-firecrawl-service","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_lgesuellip-website-firecrawl-service","summary":"This tool leverages Firecrawl to generate concise summaries of web pages directly from their URLs. Firecrawl processes the content of the provided website, extracting key insights and metadata to deliver a brief, focused summary.","description":"# website_firecrawl_service - MCP Server\n\n🔍 Internet research just got smarter! Built an MCP server that turns any website into structured, relevant content based on your queries!\n\nUsing @Firecrawl's powerful features (mapping, selection, scraping), combined with GPT-4o for smart URL filtering, it's like having an AI research assistant that knows exactly what you're looking for! Works seamlessly with Claude, or any MCP-compatible client!\n\n![Agentic Web Scraping Architecture](web_firecrawl_service_v0.1.0.png)\n\n*An agentic web scraping system powered by Firecrawl: Map → Select → Scrape → Extract*\n\n---\n\n## Features\n\n- **Efficient Web Crawling**: Crawls websites using the Firecrawl API with customizable link limits and intelligent URL selection\n- **Intelligent URL Selection**: Uses GPT-4 to select the most relevant URLs based on user queries\n- **Smart Content Processing**: Extracts and cleans HTML content, providing readable text output\n\n## Setup\n\n1. Create a `.env` file with the following required environment variables:\n   ```\n   FIRECRAWL_API_KEY=your_firecrawl_api_key\n   OPENAI_API_KEY=your_openai_api_key\n   ```\n\n## Usage\n\nThe server exposes a single tool:\n\n### website_firecrawl\n\n**Description**: Crawls a website and returns relevant content based on a query.\n\n**Parameters**:\n- `query` (string): The search query to filter relevant content\n- `base_url` (string): The target website URL to crawl\n- `max_links` (integer, optional): Maximum number of links to process (default: 100)\n\n## Technical Details\n\n- Built using the MCP (Model Control Protocol) server framework\n- Implements retry logic with exponential backoff for API calls\n- Integrates with LangSmith for tracing and monitoring\n- Implements singleton patterns for API clients to manage resources efficiently\n- Uses Pydantic for robust data validation and serialization:\n  - `WebsiteCrawlArgs`: Validates input parameters for the crawling service\n  - `CrawlerModel`: Handles URL selection and justification\n  - `Page`: St…","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_lgesuellip-website-firecrawl-service","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"data.web-scraping","name":"Web Scraping","confidence":1,"provenance":"derived"}],"categories":["data"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"iflow-mcp_lgesuellip-website-firecrawl-service","registry":"pypi","observedAt":"2026-11-09T09:28:58.000Z","publishedAt":"2026-02-08T08:20:05.338568Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_lgesuellip-website-firecrawl-service","url":"https://pypi.org/project/iflow-mcp_lgesuellip-website-firecrawl-service/","firstSeenAt":"2026-09-09T19:24:51.946Z","fetchedAt":"2026-11-09T09:27:44.967Z","normalizedAt":"2026-11-09T09:27:44.967Z"}]},"firstSeenAt":"2026-09-09T19:24:51.946Z","updatedAt":"2026-11-09T09:28:58.000Z"}