MCP Web Search & Scrape in Rovo Dev CLI

​

Requirements

• Rovo Dev CLI, installed as an extension of the Atlassian CLI (acli) and signed in with acli rovodev auth login.
• A Firecrawl API key.

​

Quick setup

1. Run acli rovodev mcp to open ~/.rovodev/mcp.json in your default editor.
2. Add Firecrawl, replace the key, and save:

{
  "mcpServers": {
    "firecrawl": {
      "url": "https://mcp.firecrawl.dev/v2/mcp",
      "transport": "http",
      "headers": {
        "Authorization": "Bearer fc-YOUR-API-KEY"
      }
    }
  }
}

3. Start Rovo Dev with acli rovodev run, enter /mcp, and confirm that firecrawl is listed with its tools.

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

​

Try it

Search the web for the latest Jira Cloud REST API changes and summarize the sources.

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

​

What you can do

​

Troubleshooting

• /mcp does not list Firecrawl: check that the JSON is valid and that transport is "http" for the hosted URL.
• The server shows 401: replace the key in mcp.json and restart acli rovodev run.
• Firecrawl is listed but disabled: open /mcp and enable it, and check that it is not listed under disabledMcpServers in ~/.rovodev/config.yml.
• Server instructions are not wanted: set "enable_instructions": false on the Firecrawl entry.