### Server Configuration Example Source: https://github.com/brightdata/brightdata-mcp/blob/main/mcp-evals/README.md Example server configuration file defining timeout and server connection details, including URL and authentication headers. ```json { "timeout": 600000, "servers": { "ecommerce-server": { "url": "http://mcp.brightdata.com/mcp?groups=ecommerce&browser=scraping_browser", "requestInit": { "headers": { "Authorization": "Bearer YOUR_AUTH_TOKEN" } } } } } ``` -------------------------------- ### Install mcpjam CLI Source: https://github.com/brightdata/brightdata-mcp/blob/main/mcp-evals/README.md Install the mcpjam evaluation CLI globally using npm. ```bash npm install -g @mcpjam/cli ``` -------------------------------- ### Example AI-Powered Search Queries Source: https://github.com/brightdata/brightdata-mcp/blob/main/README.md These examples demonstrate natural language queries that the MCP can understand and execute for various information retrieval tasks. ```yaml ✅ "What's Tesla's current stock price?" ✅ "Find the best-rated restaurants in Tokyo right now" ✅ "Get today's weather forecast for New York" ✅ "What movies are releasing this week?" ✅ "What are the trending topics on Twitter today?" ✅ "What's the latest version of express on npm?" ✅ "Get the README for the langchain-brightdata PyPI package" ``` -------------------------------- ### E-commerce Evaluation Output Example Source: https://github.com/brightdata/brightdata-mcp/blob/main/mcp-evals/README.md Example output from running an e-commerce tool group evaluation, showing test progress, tool calls, tool results, and PASS status. ```text Running tests Connected to 1 server: ecommerce-server Found 13 total tools Running 2 tests Test 1: Test E-commerce - Amazon product search Using openai:gpt-5.1-2025-11-13 run 1/1 user: Search for wireless headphones on Amazon and show me the top products with reviews [tool-call] web_data_amazon_product_search { "keyword": "wireless headphones", "url": "https://www.amazon.com" } [tool-result] web_data_amazon_product_search { "content": [...] } assistant: Here are some of the top wireless headphones currently on Amazon... Expected: [web_data_amazon_product_search] Actual: [web_data_amazon_product_search] PASS (23.8s) Tokens • input 20923 • output 1363 • total 22286 ``` -------------------------------- ### Configure LLM API Keys Source: https://github.com/brightdata/brightdata-mcp/blob/main/mcp-evals/README.md Configure your LLM provider API keys in the llms.json file. This example shows configuration for OpenAI. ```json { "openai": "sk-your-api-key-here" } ``` -------------------------------- ### Test Output Components: Connection Info Source: https://github.com/brightdata/brightdata-mcp/blob/main/mcp-evals/README.md Example of connection information displayed during test execution, showing the number of connected servers and the total tools found. ```text Connected to 1 server: ecommerce-server Found 13 total tools ``` -------------------------------- ### Tool Group Test Case Example Source: https://github.com/brightdata/brightdata-mcp/blob/main/mcp-evals/README.md Example of a single test case within a tool group definition file. It includes query, model, expected tool calls, and advanced configuration for the LLM. ```json { "title": "Test E-commerce - Amazon product search", "query": "Search for wireless headphones on Amazon and show me the top products with reviews", "runs": 1, "model": "gpt-5.1-2025-11-13", "provider": "openai", "expectedToolCalls": ["web_data_amazon_product_search"], "selectedServers": ["ecommerce-server"], "advancedConfig": { "instructions": "You are a shopping assistant helping users find products on Amazon", "temperature": 0.1, "maxSteps": 5, "toolChoice": "required" } } ``` -------------------------------- ### Add New Test Case Configuration Source: https://github.com/brightdata/brightdata-mcp/blob/main/mcp-evals/README.md JSON structure for defining a new test case, including title, query, expected tool calls, model configuration, and advanced settings. This example demonstrates tracking product price history on Amazon. ```json { "title": "Test E-commerce - Product price tracking", "query": "Track the price history for AirPods Pro on Amazon", "runs": 1, "model": "gpt-5.1-2025-11-13", "provider": "openai", "expectedToolCalls": ["web_data_amazon_product_search"], "selectedServers": ["ecommerce-server"], "advancedConfig": { "instructions": "You are a price tracking assistant", "temperature": 0.1, "maxSteps": 5, "toolChoice": "required" } } ``` -------------------------------- ### Hosted Server URL for MCP Client Source: https://github.com/brightdata/brightdata-mcp/blob/main/README.md Use this URL to connect your MCP client to the hosted server without any local installation. Replace YOUR_API_TOKEN_HERE with your actual API token. ```url https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN_HERE ``` -------------------------------- ### Test Output Components: Test Result Source: https://github.com/brightdata/brightdata-mcp/blob/main/mcp-evals/README.md Example of a test result indicating a PASS status, along with the expected and actual tool calls and the execution time. ```text Expected: [web_data_amazon_product_search] Actual: [web_data_amazon_product_search] PASS (23.8s) ``` -------------------------------- ### Basic MCP Server Configuration Source: https://github.com/brightdata/brightdata-mcp/blob/main/README.md This JSON snippet shows the minimal configuration required to set up an MCP server for Bright Data. It includes the command to run the MCP and the necessary API token environment variable. ```json { "mcpServers": { "Bright Data": { "command": "npx", "args": ["@brightdata/mcp"], "env": { "API_TOKEN": "your-token-here" } } } } ``` -------------------------------- ### Local MCP Server Configuration Source: https://github.com/brightdata/brightdata-mcp/blob/main/README.md Configure and run the MCP locally on your machine using npx. Ensure you replace with your actual API token. ```json { "mcpServers": { "Bright Data": { "command": "npx", "args": ["@brightdata/mcp"], "env": { "API_TOKEN": "" } } } } ``` -------------------------------- ### Run Finance Tool Group Evals Source: https://github.com/brightdata/brightdata-mcp/blob/main/mcp-evals/README.md Execute evaluation tests for the finance tool group using specified configurations. Ensure the tool-groups.finance.json, server-configs/server-config.finance.json, and llms.json files are correctly set up. ```bash mcpjam evals run \ -t tool-groups.json/tool-groups.finance.json \ -e server-configs/server-config.finance.json \ -l llms.json ``` -------------------------------- ### Configure MCP for Coding Agents (Claude Code / Cursor / Windsurf) Source: https://github.com/brightdata/brightdata-mcp/blob/main/README.md Enable real-time package intelligence from npm and PyPI for coding agents by configuring MCP with the 'code' group. Replace '' with your API token. ```json { "mcpServers": { "Bright Data": { "command": "npx", "args": ["@brightdata/mcp"], "env": { "API_TOKEN": "", "GROUPS": "code" } } } } ``` -------------------------------- ### Configure MCP for Claude Desktop Source: https://github.com/brightdata/brightdata-mcp/blob/main/README.md Use this configuration to enable browser automation and advanced scraping tools for Claude Desktop. Ensure you replace '' with your actual API token. ```json { "mcpServers": { "Bright Data": { "command": "npx", "args": ["@brightdata/mcp"], "env": { "API_TOKEN": "", "GROUPS": "browser,advanced_scraping", "TOOLS": "extract" } } } } ``` -------------------------------- ### Pro Mode Configuration Source: https://github.com/brightdata/brightdata-mcp/blob/main/README.md Enable Pro Mode for enhanced features. This setting is used when opting for the Pro pricing tier. ```env PRO_MODE=true ``` -------------------------------- ### Run E-commerce Tool Group Evaluation Source: https://github.com/brightdata/brightdata-mcp/blob/main/mcp-evals/README.md Command to run evaluations for the e-commerce tool group, specifying the tool groups file, server configuration, and LLM configuration. ```bash mcpjam evals run \ -t tool-groups.json/tool-groups.ecommerce.json \ -e server-configs/server-config.ecommerce.json \ -l llms.json ``` -------------------------------- ### Advanced MCP Server Configuration Source: https://github.com/brightdata/brightdata-mcp/blob/main/README.md This JSON snippet demonstrates advanced configuration options for the Bright Data MCP. It includes settings for enabling pro mode, custom rate limiting, and specifying custom zones for web unlocker and browser. ```json { "mcpServers": { "Bright Data": { "command": "npx", "args": ["@brightdata/mcp"], "env": { "API_TOKEN": "your-token-here", "PRO_MODE": "true", // Enable all 60+ tools "RATE_LIMIT": "100/1h", // Custom rate limiting "WEB_UNLOCKER_ZONE": "custom", // Custom unlocker zone "BROWSER_ZONE": "custom_browser", // Custom browser zone "POLLING_TIMEOUT": "600" // Polling timeout in seconds (default: 600) } } } } ``` -------------------------------- ### Custom Mode Configuration - Scrape as HTML Tool Source: https://github.com/brightdata/brightdata-mcp/blob/main/README.md Configure Custom Mode to specifically include the 'scrape_as_html' tool. This is useful for selecting individual tools. ```env TOOLS="scrape_as_html" ``` -------------------------------- ### Test Output Components: Token Usage Source: https://github.com/brightdata/brightdata-mcp/blob/main/mcp-evals/README.md Displays the token consumption for a test run, including input, output, and total tokens used. ```text Tokens • input 20923 • output 1363 • total 22286 ``` -------------------------------- ### Specify Node.js Path for ENOENT Error Source: https://github.com/brightdata/brightdata-mcp/blob/main/README.md When encountering the 'spawn npx ENOENT' error, specify the full path to your Node.js executable. This ensures the system can locate and run Node.js commands. ```json "command": "/usr/local/bin/node" // macOS/Linux ``` ```json "command": "C:\\Program Files\\nodejs\\node.exe" // Windows ``` -------------------------------- ### Custom Mode Configuration - Browser Group Source: https://github.com/brightdata/brightdata-mcp/blob/main/README.md Configure Custom Mode to include the 'browser' tool group. This allows for specific tool selection based on your needs. ```env GROUPS="browser" ``` -------------------------------- ### Run Research Tool Group Evaluation Source: https://github.com/brightdata/brightdata-mcp/blob/main/mcp-evals/README.md Command to run evaluations for the research tool group, specifying the tool groups file, server configuration, and LLM configuration. ```bash mcpjam evals run \ -t tool-groups.json/tool-groups.research.json \ -e server-configs/server-config.research.json \ -l llms.json ``` === COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.