AgentHubAgentHub

Agent Web Search MCP Setup & Guide

MCP ServerMCP RegistryOfficial

io.github.JerryLiu369/agent-web-search · v0.8.0

Provider-neutral web_search for AI agents. Grounding + agent search APIs, keyless defaults.

Copy the install config on this page first, then verify docs and permissions upstream.

Overview

Provider-neutral web_search for AI agents. Grounding + agent search APIs, keyless defaults. Agent Web Search is a MCP Server listed from MCP Registry. Transports: stdio. This page includes an overview, setup tutorial, install commands, and use cases for Trae, Tongyi Lingma, Cursor, Claude Code, and VS Code.

Use cases

AgentHub Verified AvailabilityTested & Ready

Automated pipeline validated install commands, protocol & client compatibility

Verified At2026-10-04
Install Snippets TestedCLI & JSON config syntax verified
Protocol Handshake ReadyComplies with JSON-RPC 2.0 specifications
Origin Registry ActiveSourced from official-mcp-registry
Verified ClientsClaude Code、Claude Desktop、Cursor 等
Security Tier: A+ 级 · 官方认证推荐 (A+)·Maintained by official/verified teams, audited for standard MCP protocol compliance.

Copy by platform

Choose your platform

  1. Open or create .cursor/mcp.json in your project root
  2. Click Copy config and paste; merge only this mcpServers entry if others exist
  3. Replace <placeholders> in env with real secrets (see Environment variables below)
  4. Save, then Cmd+Shift+P → Reload Window

Pre-fill Environment Variables (Optional)

secret
secret
secret
secret
secret
secret
secret
secret
secret
secret
secret
secret
secret
secret
Privacy Guarantee: Keys are replaced 100% locally in your browser memory and are NEVER uploaded or stored on any server.
Click to copy snippet
{
  "mcpServers": {
    "agent-web-search": {
      "command": "uvx",
      "args": [
        "agent-web-search-mcp"
      ]
    }
  }
}

Setup tutorial

  1. Open the Agent Web Search page and confirm this MCP Server (source: MCP Registry).
  2. Copy the Cursor, Claude Code, or VS Code snippet.
  3. Merge it into mcpServers and replace env placeholders with real secrets.
  4. Reload the window, then call the MCP tools from your agent chat.

Install commands

Install commands and setup steps are in the HTML so search engines and no-JS browsers can read them without running client JavaScript.

Claude Code (local)

  1. Install Claude Code CLI
  2. Copy the command below, replace <placeholders> with real env values, then run in terminal
  3. See Environment variables below if listed
claude mcp add agent-web-search -- uvx agent-web-search-mcp

Cursor — .cursor/mcp.json (local)

  1. Open or create .cursor/mcp.json in your project root
  2. Click Copy config and paste; merge only this mcpServers entry if others exist
  3. Replace <placeholders> in env with real secrets (see Environment variables below)
  4. Save, then Cmd+Shift+P → Reload Window
{
  "mcpServers": {
    "agent-web-search": {
      "command": "uvx",
      "args": [
        "agent-web-search-mcp"
      ]
    }
  }
}

VS Code — .vscode/mcp.json (local)

  1. Install GitHub Copilot in VS Code with MCP support
  2. Open or create .vscode/mcp.json in your project root
  3. Click Copy config and paste; merge only this mcpServers entry if others exist
  4. Replace <placeholders> in env with real secrets
  5. Save and Developer: Reload Window
{
  "mcpServers": {
    "agent-web-search": {
      "command": "uvx",
      "args": [
        "agent-web-search-mcp"
      ]
    }
  }
}

Claude Desktop — claude_desktop_config.json (local)

  1. Open Claude Desktop claude_desktop_config.json (see remote guide for paths)
  2. Click Copy config and merge under mcpServers
  3. Replace <placeholders> in env with real secrets
  4. Fully quit and restart Claude Desktop
{
  "mcpServers": {
    "agent-web-search": {
      "command": "uvx",
      "args": [
        "agent-web-search-mcp"
      ]
    }
  }
}

Trae — .trae/mcp.json (local)

  1. Trae → Settings → MCP, or edit .trae/mcp.json / global mcp.json
  2. Click Copy config and merge mcpServers
  3. Replace <placeholders> in env with real secrets
  4. Save and reload Trae
{
  "mcpServers": {
    "agent-web-search": {
      "command": "uvx",
      "args": [
        "agent-web-search-mcp"
      ]
    }
  }
}

Cherry Studio — MCP settings (local)

  1. Cherry Studio → Settings → MCP Servers → Add (STDIO)
  2. Or import JSON: click Copy config and merge mcpServers
  3. Replace <placeholders> in env; ensure Node.js / uv (npx, uvx) are installed
  4. Enable the server and check tools load
{
  "mcpServers": {
    "agent-web-search": {
      "command": "uvx",
      "args": [
        "agent-web-search-mcp"
      ]
    }
  }
}

Tongyi Lingma — MCP config (local)

  1. Lingma Settings → MCP → + → STDIO or config file
  2. Click Copy config and merge mcpServers
  3. Replace <placeholders> in env; need Node.js 18+ (npx) or uv (uvx)
  4. Confirm connected before using tools in agent chat
{
  "mcpServers": {
    "agent-web-search": {
      "command": "uvx",
      "args": [
        "agent-web-search-mcp"
      ]
    }
  }
}

Windsurf — mcp_config.json (local)

  1. Edit ~/.codeium/windsurf/mcp_config.json
  2. Click Copy config and merge mcpServers (stdio same as Cursor)
  3. Replace <placeholders> in env, save, refresh Cascade
{
  "mcpServers": {
    "agent-web-search": {
      "command": "uvx",
      "args": [
        "agent-web-search-mcp"
      ]
    }
  }
}

Cline — MCP Servers (local)

  1. Cline panel → Settings → MCP Servers
  2. Click Copy config and merge
  3. Replace <placeholders> in env, then save
{
  "mcpServers": {
    "agent-web-search": {
      "command": "uvx",
      "args": [
        "agent-web-search-mcp"
      ]
    }
  }
}

WorkBuddy — .workbuddy/mcp.json (local)

  1. Edit ~/.workbuddy/mcp.json (user) or project .workbuddy/mcp.json
  2. Or Plugins → MCP Servers → Configure MCP and paste the JSON below
  3. Replace <placeholders> in env; on Windows prefer absolute paths for command/scripts
  4. Save, restart WorkBuddy, confirm connector status is green
{
  "mcpServers": {
    "agent-web-search": {
      "command": "uvx",
      "args": [
        "agent-web-search-mcp"
      ]
    }
  }
}

Troubleshooting & Common ErrorsFAQ

Common connection errors and verified fixes for Agent Web Search

Getting 'connection closed' or exit code 1 in Cursor / Claude Code for Agent Web Search?

Usually caused by missing runtime paths or IDE environment inheritance. Fix steps: 1. Verify Node.js 18+ (npx) or Python 3.10+ (uvx) is installed; 2. Run 'which npx' or 'which uvx' in terminal, and replace 'command' with absolute path; 3. Reload or restart the client window after modifying config.

Fix Snippet
# Check binary path in terminal:
which npx
node -v
Getting 'spawn npx ENOENT' or 'command not found'?

The editor background process does not inherit your full terminal PATH. Solution: Globally install the package, or set the absolute binary path (e.g. C:\Program Files\nodejs\npx.cmd on Windows, or /usr/local/bin/npx on macOS).

Missing required environment variable or authentication failure?

Agent Web Search requires environment variables (AGENT_WEB_SEARCH_PROVIDERS、ARK_API_KEY、GEMINI_API_KEY、XAI_API_KEY、DEEPSEEK_API_KEY、AGENT_WEB_SEARCH_RESPONSES_API_KEY、AGENT_WEB_SEARCH_RESPONSES_BASE_URL、AGENT_WEB_SEARCH_MESSAGES_API_KEY、AGENT_WEB_SEARCH_MESSAGES_BASE_URL、TAVILY_API_KEY、BRAVE_SEARCH_API_KEY、PERPLEXITY_API_KEY、YDC_API_KEY、EXA_API_KEY、PARALLEL_API_KEY、ZHIPU_WEB_SEARCH_API_KEY、ZHIPU_CHAT_SEARCH_API_KEY). Ensure you have added valid keys under the 'env' object in your config file without trailing whitespace.

Fix Snippet
// .cursor/mcp.json 或 claude_desktop_config.json
{
  "env": {
    "API_KEY": "your_actual_key_here"
  }
}

Tool Mock Playground

Sandbox

Agent Web Search Tool Interface Simulation · Preview tool schema & outputs without local runtime

Sandbox Ready
fn: agent_web_searchExecute the core tool interface of Agent Web Search
Request ArgumentsJSON Schema
{
  "target": "Agent Web Search",
  "action": "execute",
  "options": {
    "mode": "standard",
    "timeoutMs": 5000
  }
}
💡Parameters generated dynamically by Agent runtime
Agent Tool Output

Click 'Run Mock' above

to preview the raw response returned to the LLM

Env: AgentHub Virtual SandboxJSON-RPC 2.0

Decision Guide: Why & When to Use

Assess suitability before installing to save trial-and-error time

Best Suited For
  • PR review
  • Changelog generation
  • Cross-repo issue search
When NOT to Use
  • Replacing human security audit
  • Unauthorized repo access
Recommended Workflow Pairing:View Scenario →

Agent Web Search + Scenario Prompt → Complete Agent Automation

MCP hands-on: install to visible results

Follow the full lab (expected UI/output + contrast checks). After installing this item, verify with the tutorial prompts.

Open tutorial →

Related resources

Often paired with

Keep exploring AgentHub

Most people compare similar tools or check scenario guides before installing—start here.

Listing badge: put AgentHub on your site

Copy either snippet into your project homepage, docs, or GitHub README. The badge is a hotlinked SVG — nothing to host — and it links back to this page so visitors can find the install steps.

PreviewListed on AgentHub: Agent Web Search
HTML
<a href="https://myagenthub.cn/p/io.github.JerryLiu369/agent-web-search" title="Listed on AgentHub: Agent Web Search" target="_blank" rel="noopener">
  <img src="https://myagenthub.cn/badge/io.github.JerryLiu369/agent-web-search?lang=en" alt="Listed on AgentHub: Agent Web Search" height="20" style="border:0"/>
</a>
Markdown (GitHub README)
[![Listed on AgentHub: Agent Web Search](https://myagenthub.cn/badge/io.github.JerryLiu369/agent-web-search?lang=en)](https://myagenthub.cn/p/io.github.JerryLiu369/agent-web-search)

Badges are generated on the fly from /badge/<package-id>, so name and listing changes propagate automatically. Keep the link target unchanged — it is what counts as the referral.

Unified Manifest

{
  "id": "io.github.JerryLiu369/agent-web-search",
  "type": "mcp-server",
  "version": "0.8.0",
  "displayName": "Agent Web Search",
  "description": "Provider-neutral web_search for AI agents. Grounding + agent search APIs, keyless defaults.",
  "repository": {
    "url": "https://github.com/JerryLiu369/agent-web-search",
    "source": "github"
  },
  "homepage": "https://github.com/JerryLiu369/agent-web-search",
  "distribution": {
    "packages": [
      {
        "registryType": "pypi",
        "identifier": "agent-web-search-mcp",
        "version": "0.8.0",
        "transport": "stdio",
        "environmentVariables": [
          {
            "name": "AGENT_WEB_SEARCH_PROVIDERS",
            "description": "Comma-separated startup-enabled provider set; defaults to ddgs,exa,parallel (all keyless)"
          },
          {
            "name": "ARK_API_KEY",
            "description": "Volcengine Ark API key for Doubao grounding",
            "isSecret": true
          },
          {
            "name": "GEMINI_API_KEY",
            "description": "Google Gemini API key for Google Search grounding",
            "isSecret": true
          },
          {
            "name": "XAI_API_KEY",
            "description": "xAI API key for Grok web/X search",
            "isSecret": true
          },
          {
            "name": "DEEPSEEK_API_KEY",
            "description": "DeepSeek API key for native web search",
            "isSecret": true
          },
          {
            "name": "AGENT_WEB_SEARCH_RESPONSES_API_KEY",
            "description": "Generic Responses API key for web search grounding (falls back to OPENAI_API_KEY)",
            "isSecret": true
          },
          {
            "name": "AGENT_WEB_SEARCH_RESPONSES_BASE_URL",
            "description": "Generic Responses API base URL; defaults to https://api.openai.com/v1"
          },
          {
            "name": "AGENT_WEB_SEARCH_MESSAGES_API_KEY",
            "description": "Generic Anthropic Messages API key for web search grounding",
            "isSecret": true
          },
          {
            "name": "AGENT_WEB_SEARCH_MESSAGES_BASE_URL",
            "description": "Generic Anthropic Messages API base URL; defaults to https://api.anthropic.com"
          },
          {
            "name": "TAVILY_API_KEY",
            "description": "Tavily API key for agent-oriented search",
            "isSecret": true
          },
          {
            "name": "BRAVE_SEARCH_API_KEY",
            "description": "Brave Search API key",
            "isSecret": true
          },
          {
            "name": "PERPLEXITY_API_KEY",
            "description": "Perplexity API key for structured search",
            "isSecret": true
          },
          {
            "name": "YDC_API_KEY",
            "description": "You.com API key",
            "isSecret": true
          },
          {
            "name": "EXA_API_KEY",
            "description": "Optional Exa key; free MCP fallback without it",
            "isSecret": true
          },
          {
            "name": "PARALLEL_API_KEY",
            "description": "Optional Parallel key; free MCP fallback without it",
            "isSecret": true
          },
          {
            "name": "ZHIPU_WEB_SEARCH_API_KEY",
            "description": "Zhipu standalone Web Search API key",
            "isSecret": true
          },
          {
            "name": "ZHIPU_CHAT_SEARCH_API_KEY",
            "description": "Zhipu Chat Completions native web search key",
            "isSecret": true
          }
        ]
      }
    ],
    "remotes": []
  },
  "dependencies": [],
  "installTargets": [
    "claude-code",
    "claude-desktop",
    "cursor",
    "vscode",
    "trae",
    "cherry-studio",
    "lingma",
    "windsurf",
    "cline",
    "workbuddy"
  ],
  "keywords": [],
  "provenance": {
    "origin": "official-mcp-registry",
    "originalId": "io.github.JerryLiu369/agent-web-search",
    "originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.JerryLiu369%2Fagent-web-search/versions/latest",
    "isOfficial": true,
    "status": "active"
  }
}
Agent Web Search MCP Setup & Guide - AgentHub