MCP Web Search & Scrape in Qodo

​

Requirements

• Qodo Command, installed with npm install -g @qodo/command and signed in with qodo login.
• Node.js 22 or newer.
• A Firecrawl API key.

​

Quick setup

1. In your project root, create mcp.json:

{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": ["-y", "firecrawl-mcp@3.33.2"],
      "env": {
        "FIRECRAWL_API_KEY": "fc-YOUR-API-KEY"
      }
    }
  }
}

2. Create agents/research.toml and give the agent access to the server by name:

version = "1.0"

[commands.research]
description = "Research a topic on the web with Firecrawl"
instructions = """
Use the Firecrawl tools to search the web and read pages, then summarize the sources.
"""
tools = ["firecrawl"]
execution_strategy = "act"

3. Import the agent from agent.toml at the project root:

version = "1.0"

imports = ["agents/research.toml"]

4. Run the agent and list the available tools:

qodo list-mcp
qodo research "Find the latest release notes for Node.js"

​

Try it

Search the web for the latest Go release notes and summarize the sources.

Scrape https://firecrawl.dev and explain what it does.

​

What you can do

​

Troubleshooting

• list-mcp shows no Firecrawl entry: confirm mcp.json sits at the project root, or pass --mcp-file=path.
• The agent never calls Firecrawl: check that tools in the agent file contains "firecrawl", matching the key in mcp.json.
• The server fails to start: run node --version and confirm it prints 22 or newer.
• The server returns 401: replace the value of FIRECRAWL_API_KEY in mcp.json.