What are the runtime requirements for Extend Mcp?
Python 3.10 or higher and a valid Extend API key (obtainable at paywithextend.com). Framework-specific packages (e.g., `anthropic` for Claude) may also be needed.
@paywithextend
基本信息
Extend AI Toolkit
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"extend-mcp": {
"command": "python",
"args": [
"-m",
"extend_ai_toolkit.modelcontextprotocol.main",
"--tools=all"
],
"env": {
"EXTEND_API_KEY": "apik_XXXX",
"EXTEND_API_SECRET": "XXXXX"
}
},
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/path/to/receipts/folder"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
Extend Mcp is a Python-based implementation within the Extend AI Toolkit that integrates Extend's spend management APIs with Anthropic’s Model Context Protocol (MCP). It enables existing Extend users to delegate actions such as managing virtual cards, credit cards, transactions, and expense receipts to MCP-compatible clients like Claude Desktop.
Install the package via pip install extend_ai_toolkit, then configure your Extend API key and secret via environment variables (EXTEND_API_KEY, EXTEND_API_SECRET) or command-line arguments (--api-key, --api-secret). Run the MCP server locally with MCP Inspector (npx @modelcontextprotocol/inspector python ...) or integrate it into Claude Desktop by editing the claude_desktop_config.json to add the Extend MCP server. For remote execution, use the SSE transport with python -m extend_ai_toolkit.modelcontextprotocol.main_sse.
Python 3.10 or higher and a valid Extend API key (obtainable at paywithextend.com). Framework-specific packages (e.g., `anthropic` for Claude) may also be needed.
Provide your Extend API key and secret as environment variables or command-line arguments. For Extend API 2.0+, you can use a `BearerAuth` strategy with a JWT token instead.
Yes, but you must also install the filesystem MCP server (`npm install @modelcontextprotocol/server-filesystem`) and add it to the Claude Desktop config. Receipt images from the local filesystem can be uploaded and automatched.
Yes, by launching the server with SSE transport (`python -m extend_ai_toolkit.modelcontextprotocol.main_sse`). You can then connect an MCP client using `mcp_client.py`.
All operations are performed against Extend’s virtual card, credit card, transaction, and expense management APIs. No local data is stored; the server acts as a bridge between the client and Extend’s systems.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Official Porkbun MCP server, maintained by Porkbun. Check domain availability and pricing, register, renew and transfer domains, and manage DNS records, nameservers, URL forwarding, glue records, DNSSEC and domain contac

Verified cyber-physical AI tools. 25 MCP tools, x402-payable on Base.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation
评论