MCP Server

​

Before you start

1. A Spidra account. Sign up at app.spidra.io.
2. An MCP-compatible client. Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Antigravity, OpenCode, and other MCP clients can connect to Spidra.

​

Connect a client

​

Run the server locally

claude mcp add spidra \
  -e SPIDRA_API_KEY=spd_YOUR_API_KEY \
  -- npx -y spidra-mcp

{
  "mcpServers": {
    "spidra": {
      "command": "npx",
      "args": ["-y", "spidra-mcp"],
      "env": {
        "SPIDRA_API_KEY": "spd_YOUR_API_KEY"
      }
    }
  }
}

{
  "mcpServers": {
    "spidra": {
      "command": "npx",
      "args": ["-y", "spidra-mcp"],
      "env": {
        "SPIDRA_API_KEY": "spd_YOUR_API_KEY"
      }
    }
  }
}

{
  "servers": {
    "spidra": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "spidra-mcp"],
      "env": {
        "SPIDRA_API_KEY": "spd_YOUR_API_KEY"
      }
    }
  }
}

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "spidra": {
      "command": "npx",
      "args": ["-y", "spidra-mcp"],
      "env": {
        "SPIDRA_API_KEY": "spd_YOUR_API_KEY"
      }
    }
  }
}

{
  "mcpServers": {
    "spidra": {
      "command": "npx",
      "args": ["-y", "spidra-mcp"],
      "env": {
        "SPIDRA_API_KEY": "spd_YOUR_API_KEY"
      }
    }
  }
}

export SPIDRA_API_KEY=spd_YOUR_API_KEY

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "servers": {
      "spidra": {
        "type": "local",
        "command": ["npx", "-y", "spidra-mcp"],
        "environment": {
          "SPIDRA_API_KEY": "{env:SPIDRA_API_KEY}"
        }
      }
    }
  }
}

​

Try it

“Search for the best espresso machines of 2026 and summarize the top 3.”

“Scrape https://news.ycombinator.com and give me the top five stories with their points.”

“Compare the pricing pages for stripe.com and paddle.com and tell me which is cheaper for a small SaaS.”

“Here are 12 product URLs. Get the name, price, and rating from each one and return a table.”

“Crawl the first 10 pages of docs.spidra.io and summarize what the product does.”

​

Choose the right tool

• Use spidra_search when you don’t know the URL yet. It finds pages, news, images, videos, academic papers, or GitHub issues and PRs for a query, and can optionally fetch each web result’s actual page content in the same call.
• Use spidra_scrape when you know one page’s URL. It takes a single URL.
• Use spidra_batch_scrape for anything involving more than one URL, even just two, even to compare them, each URL is processed independently and gets its own result. It accepts 2 to 50 URLs.
• Use spidra_parse for documents rather than web pages: a PDF, Word, Excel or PowerPoint file, from a link or a small file the user shared. It returns Markdown page by page, and JSON if you ask for fields.
• Use spidra_map to see which pages a site has. It lists a site’s URLs in a few seconds for 1 credit, ranked by a search if you give one, so you can scrape just the right pages.
• Use spidra_crawl when you know where to start but do not already know every page URL. Spidra discovers pages by following links according to your instructions.

​

Credit-efficient behavior

• Tool descriptions guide the model toward the most appropriate operation for each request.
• Crawl guidance encourages smaller maxPages values when a large crawl is not necessary.
• Long-running operations return job IDs and explicit polling instructions instead of encouraging the model to submit the same job again.
• Timeout responses tell the assistant that the existing job is still running and should be checked, not restarted.
• Rate-limit errors tell the assistant how long to wait before retrying.
• Validation errors identify what needs to change.
• Permanent errors tell the assistant when repeating the same request will not help.
• Cancelling a batch or crawl refunds credits for work that has not yet been processed.
• Retrying a batch or crawl page re-runs only the failed items, not the whole job.

​

Output limits

• individual strings longer than 5,000 characters are truncated
• a single MCP tool response is capped at 80,000 characters
• truncated values are marked so the assistant knows content was omitted

​

Configuration

Authorization: Bearer spd_YOUR_API_KEY

​

Troubleshooting

{
  "env": {
    "SPIDRA_API_KEY": "spd_YOUR_API_KEY"
  }
}

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    }
  }
}