mcp -bwt
Model Context Protocol (MCP) server for Bing Webmaster Tools (BWT) allowing Claude.ai and other clients to interact with the BWT API
claude mcp add --transport stdio zizzfizzix-mcp-server-bwt uvx --from git+https://github.com/zizzfizzix/mcp-server-bwt mcp_server_bwt \ --env BING_WEBMASTER_API_KEY="YOUR_API_KEY_HERE"
How to use
This MCP server exposes Bing Webmaster Tools functionality as MCP tools that can be consumed by AI assistants like Claude or Cursor. It wraps the Bing Webmaster Tools API (via bing-webmaster-tools) and makes actions such as site management, URL submission, traffic analysis, crawling, keyword and link analysis, content management, and regional settings available as discrete MCP commands. Typical usage involves authenticating with a Bing Webmaster Tools API key and invoking the appropriate tool, for example to list verified sites, submit URLs for indexing, or fetch traffic statistics for a site. The server is designed to be integrated into your MCP environment so that your assistants can issue natural language prompts that map to these tools (e.g., “List all my verified sites in Bing Webmaster Tools” or “Get traffic statistics for my website”).
How to install
Prerequisites:\n- Python 3.13 or newer\n- Node.js installed (for tooling or compatibility)\n- A Bing Webmaster Tools API key (for API access)\n\nRecommended installation path (uvx):\n1) Ensure uvx is installed following its docs.\n2) Start using the MCP server directly from your client with uvx by referencing the repository:\n\nbash\n# Example: add the server to your Claude config via uvx (from README)\n"mcpServers": {\n "mcp_server_bwt": {\n "command": "uvx",\n "args": [\n "--from",\n "git+https://github.com/zizzfizzix/mcp-server-bwt",\n "mcp_server_bwt"\n ]\n }\n}\n\n\n3) If you prefer a local install using the repo, you can install via make (see below) and point the command to your local Python executable, passing the main module path as shown in the README examples.\n\nAlternative install (make):\n1) Install the package locally:\nbash\nmake install\n\n2) Start the server by invoking Python with the main module as described in your environment (paths will vary).\n\nNote: When using make, you must provide the Bing Webmaster Tools API key via an environment variable (BING_WEBMASTER_API_KEY) in your MCP client configuration.\n
Additional notes
Tips and common considerations:\n- Environment variable: Set BING_WEBMASTER_API_KEY in your MCP client configuration or environment where the server runs. Without it, API calls to Bing Webmaster Tools will fail.\n- If using uvx from a remote source, ensure network access to the Git URL and that your environment can run Python/mcp_server_bwt.\n- The server aggregates a wide range of Bing Webmaster Tools capabilities; use the provided tool names (e.g., get_sites, submit_url, get_query_stats) to construct MCP prompts for your assistants.\n- If you update the repository, re-emit the MCP server reference in your client config to pick up changes.\n- For troubleshooting, verify that the API key has the necessary permissions and that the Bing Webmaster Tools account is linked correctly.\n
Related MCP Servers
web-eval-agent
An MCP server that autonomously evaluates web applications.
web-agent-protocol
🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
Lambda
Creates a simple MCP tool server with "streaming" HTTP.
mcp-tool-kit
Agentic abstraction layer for building high precision vertical AI agents written in python for Model Context Protocol.
fhir
FHIR MCP Server – helping you expose any FHIR Server or API as a MCP Server.
unitree-go2
The Unitree Go2 MCP Server is a server built on the MCP that enables users to control the Unitree Go2 robot using natural language commands interpreted by a LLM.