Skip to main content
The Parallel Search MCP Server provides drop-in web search and content extraction capabilities for any MCP-aware model. The tools invoke the Search API endpoint but present a simpler interface to ensure effective use by agents. The tools use the Search API in agentic mode, which returns more concise results than the default one-shot mode. The Search MCP comprises two tools:
  • web_search - Search the web for information and retrieve relevant results
  • web_fetch - Extract and retrieve content from specific URLs

​
Use Cases

The Search MCP is suited for any application where real-world information is needed as part of an AI agent’s reasoning loop. Common use cases include:
  • Real-time fact checking and verification during conversations
  • Gathering current information to answer user questions
  • Researching topics that require recent or live data
  • Retrieving content from specific URLs to analyze or summarize
  • Competitive intelligence and market research

​
Installation

The Search MCP can be installed in any MCP client. The server URL is: https://search-mcp.parallel.ai/mcp The Search MCP can also be used programmatically by providing your Parallel API key in the Authorization header as a Bearer token.

​
Cursor

Add to ~/.cursor/mcp.json or .cursor/mcp.json (project-specific): 
{
  "mcpServers": {
    "Parallel Search MCP": {
      "url": "https://search-mcp.parallel.ai/mcp"
    }
  }
}
Deep Link: 🔗 Install Search MCP For more details, see the Cursor MCP documentation.

​
VS Code

Add to settings.json in VS Code: 
{
  "mcp": {
    "servers": {
      "Parallel Search MCP": {
        "type": "http",
        "url": "https://search-mcp.parallel.ai/mcp"
      }
    }
  }
}
Deep Link: 🔗 Install Search MCP For more details, see the VS Code MCP documentation.

​
Claude Desktop / Claude.ai

Go to Settings → Connectors → Add Custom Connector, and fill in: 
Name: Parallel Search MCP
URL: https://search-mcp.parallel.ai/mcp
If you are part of an organization, you may not have access to custom connectors. Contact your organization administrator for assistance. If you are not an admin, go to Settings → Developer → Edit Config and add the following JSON after retrieving your API key from Platform: 
"Parallel Search MCP": {
  "command": "npx",
  "args": [
    "-y",
    "mcp-remote",
    "https://search-mcp.parallel.ai/mcp",
    "--header", "authorization: Bearer YOUR-PARALLEL-API-KEY"
  ]
}
For more details, see the Claude remote MCP documentation.

​
Claude Code

Run this command in your terminal: 
claude mcp add --transport http "Parallel-Search-MCP" https://search-mcp.parallel.ai/mcp
In Claude code, use the command: 
/mcp
Then follow the steps in your browser to login. For more details, see the Claude Code MCP documentation.

​
Windsurf

Add to ~/.codeium/windsurf/mcp_config.json: 
{
  "mcpServers": {
    "Parallel Search MCP": {
      "serverUrl": "https://search-mcp.parallel.ai/mcp"
    }
  }
}
For more details, see the Windsurf MCP documentation.

​
Cline

Go to MCP Servers → Remote Servers → Edit Configuration: 
{
  "mcpServers": {
    "Parallel Search MCP": {
      "url": "https://search-mcp.parallel.ai/mcp",
      "type": "streamableHttp"
    }
  }
}
For more details, see the Cline MCP documentation.

​
Gemini CLI

Add to ~/.gemini/settings.json: 
{
  "mcpServers": {
    "Parallel Search MCP": {
      "httpUrl": "https://search-mcp.parallel.ai/mcp"
    }
  }
}
For more details, see the Gemini CLI MCP documentation.

​
ChatGPT

WARNING: Please note that Developer Mode must be enabled, and this feature may not be available to everyone. Additionally, MCPs in ChatGPT are experimental and may not work reliably. First, go to Settings → Connectors → Advanced Settings, and turn on Developer Mode. Then, in connector settings, click Create and fill in: 
Name: Parallel Search MCP
URL: https://search-mcp.parallel.ai/mcp
Authentication: OAuth
In a new chat, ensure Developer Mode is turned on with the connector(s) selected. For more details, see the ChatGPT Developer Mode documentation.

​
OpenAI Codex CLI

Add to ~/.codex/config.toml: 
[mcp_servers.parallel-search]
url = "https://search-mcp.parallel.ai/mcp"
Alternatively, run this in your terminal. This should start the OAuth flow: 
codex mcp add parallel-search --url https://search-mcp.parallel.ai/mcp
For more details, see the Codex MCP documentation.

​
Amp

Run this command in your terminal: 
amp mcp add "Parallel-Search-MCP" https://search-mcp.parallel.ai/mcp
The OAuth flow will start when you start Amp. For more details, see the Amp MCP documentation.

​
Kiro

Add to .kiro/settings/mcp.json (workspace) or ~/.kiro/settings/mcp.json (global): 
{
  "mcpServers": {
    "Parallel Search MCP": {
      "url": "https://search-mcp.parallel.ai/mcp"
    }
  }
}
For more details, see the Kiro MCP documentation.

​
Google Antigravity

In the Antigravity Agent pane, click the menu (⋮) → MCP Servers → Manage MCP Servers → View raw config, then add: 
{
  "mcpServers": {
    "Parallel-Search-MCP": {
      "serverUrl": "https://search-mcp.parallel.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
For more details, see the Antigravity MCP documentation.

​
Best practices

​
Filtering by date or domain

To filter search results by date or domain, include these constraints directly in your search query or objective rather than expecting separate parameters. For example:
  • “Latest AI research papers from 2025”
  • “News about climate change from nytimes.com”
  • “Product announcements from apple.com in the last month”
If date or domain filtering is important for your task, prompt the agent explicitly to include these details when using the tool.
We have experimented with adding dedicated date and domain parameters to the Search MCP tools, but found they harm quality overall—LLMs tend to overuse them, which overconstrains search results.

​
Troubleshooting

​
Common Installation Issues

This error occurs when Cline attempts OAuth authentication but the redirect URI isn’t using HTTPS.Solution: Use the API key approach instead of OAuth:
  1. Get your API key from platform.parallel.ai
  2. Configure Cline with the bearer token method:
{
  "mcpServers": {
    "Parallel Search MCP": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://search-mcp.parallel.ai/mcp",
        "--header",
        "authorization: Bearer YOUR-PARALLEL-API-KEY"
      ]
    }
  }
}
Replace YOUR-PARALLEL-API-KEY with your actual API key.
Gemini CLI uses HTTP MCPs and authenticates via OAuth. If OAuth isn’t working, you can provide your API key directly.Solution: Use environment variables or the mcp-remote proxy:
{
  "mcpServers": {
    "Parallel Search MCP": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://search-mcp.parallel.ai/mcp",
        "--header",
        "authorization: Bearer YOUR-PARALLEL-API-KEY"
      ]
    }
  }
}
Add this to ~/.gemini/settings.json and replace YOUR-PARALLEL-API-KEY with your key from platform.parallel.ai.
VS Code requires a specific configuration format. Common mistakes include using the wrong property names.Incorrect (Cursor format):
{
  "mcpServers": {
    "parallel-search": {
      "url": "https://search-mcp.parallel.ai/mcp"
    }
  }
}
Correct (VS Code format):
{
  "mcp": {
    "servers": {
      "Parallel Search MCP": {
        "type": "http",
        "url": "https://search-mcp.parallel.ai/mcp"
      }
    }
  }
}
Note: VS Code uses mcp.servers (not mcpServers) and requires the type: "http" field.
Windsurf uses a different configuration format than Cursor.Correct Windsurf configuration:
{
  "mcpServers": {
    "Parallel Search MCP": {
      "serverUrl": "https://search-mcp.parallel.ai/mcp"
    }
  }
}
Note: Windsurf uses serverUrl instead of url. Add this to your Windsurf MCP configuration file.
If you’re getting connection errors:
  1. Check your network: Ensure you can reach https://search-mcp.parallel.ai
  2. Verify API key: Make sure your key is valid at platform.parallel.ai
  3. Check balance: A 402 error means insufficient credits—add funds to your account
  4. Restart your IDE: Some clients cache MCP connections
If the MCP installs but tools don’t show up:
  1. Restart your IDE completely (not just reload)
  2. Check configuration syntax: Ensure valid JSON with no trailing commas
  3. Verify the server URL: Must be exactly https://search-mcp.parallel.ai/mcp
  4. Check IDE logs: Look for MCP-related errors in your IDE’s output/debug panel