Send247 Human Logistics

The Send247 Delivery MCP is aModel Context Protocol (MCP) serverthat allows AI assistants toquote and book UK deliveriesthrough a structured, safe, and auditable interface.

It is designed forChatGPT, Claude, GitHub Copilot, and other MCP-compatible clients.

The MCP server exposes delivery functionality as tools that an AI assistant can safely invoke:

- Get real-time delivery quotes between UK addresses
- Create (book) a delivery using a previously generated quote
- Enforce confirmation before any irreversible action
- Maintain server-side state so LLM session continuity is not required

This app is intended forend users located in the United Kingdom.

Returns delivery options and prices for a shipment.

- User wants to know delivery cost
- User compares services before booking

- Not read-only (stateful quote caching)
- Open world (uses external delivery providers)
- Non-destructive

Creates a delivery booking using a previously issued quote.

- User explicitly confirms they want to book a delivery

- Writes data
- Open world
- Destructive (creates irreversible delivery bookings)

This toolmust only be invoked after explicit user confirmation.

This MCP server is publicly accessible and can be connected to by any MCP-compatible client.

Authentication and request validation are handledat the gateway level. No client-side API keys are required.

{ "mcpServers": { "send247-delivery": { "url": "https://mcp.send247.uk/api/v1/mcp" } } }

Once connected, enable the app in a conversation and prompt normally (for example:“Get a delivery quote from London to Manchester”).

Claude runs MCP servers locally and does not yet support direct remote MCP URLs. To connect Claude to send247, we use the official MCP remote bridge (@modelcontextprotocol/remote), which proxies the remote MCP server over stdio.
-

Install MCP Remote: npm install -g @modelcontextprotocol/remote

{ "mcpServers": { "send247-delivery": { "command": "npx", "args": [ "@modelcontextprotocol/remote", "https://mcp.send247.uk/api/v1/mcp" ] } } }

Claude will automatically discover available tools viatools/list.

GitHub Copilot (VS Code) MCP Configuration

{ "mcpServers": { "send247-delivery": { "url": "https://mcp.send247.uk/api/v1/mcp" } } }

When using Copilot Chat, tools will appear when delivery-related prompts are detected.

Optional: MCP Manifest (Discoverability)

For platforms or registries that support MCP manifests, you may include the following file:

{ "name": "Send247 Delivery", "description": "UK delivery quotes and booking via the Model Context Protocol", "version": "1.0.0", "endpoint": "https://mcp.send247.uk/api/v1/mcp", "capabilities": { "tools": true } }

This is optional but improves discoverability.

- No deliveries are created without explicit confirmation
- Quotes expire automatically
- Tool schemas are strictly validated
- Server-side state ensures reliability across LLM sessions
- All write actions are auditable

- AI assistants offering delivery services
- Agentic workflows that require logistics actions
- End users in the United Kingdom

It isnota general logistics SDK and does not expose raw provider APIs.

- MCP server deployed and publicly accessible
- Tested with MCP Inspector and ChatGPT developer mode
- Submitted for review in the OpenAI Apps Directory

For integration questions or issues, please contact the maintainer via the repository or official project channels. Emailtech@clickdrop.co.uk

The Ultimate Control Plane for MCP Unlock the full power of Model Context Protocol with zero friction. One-Click GPT Integration: Bridge the gap between MCP servers and ChatGPT/LLMs instantly. No more manual config hunting. Pro-Level Orchestration: Manage, monitor, and toggle multiple MCP tools from a single, intuitive dashboard. Secure by Design: Built-in support for complex auth flows and 2FA, making enterprise-grade tool integration seamless. Streamlined Debugging: Test queries and inspect tool responses in real-time without leaving the hub. Stop wrestling with JSON configs. Start building agentic workflows that actually work.