mcpField
O
Ordnance Survey - MCP Server

Ordnance Survey - MCP Server

Local
github.com/CHRISCARLONProductivity2Updated 52w ago
Repository

About Ordnance Survey - MCP Server

Ordnance Survey - MCP Server gives LLMs access to UK geospatial data through Ordnance Survey Data Hub APIs. It requires a search plan before queries and includes prompt templates for use cases such as planning and road networks.

Key features

  1. 01Access Ordnance Survey Data Hub APIs
  2. 02Search UK geospatial data
  3. 03Require a plan before searches
  4. 04Prompt templates for domain-specific queries

Use cases

  1. 01Find places such as cinemas in a city centre
  2. 02Explore street works and planning data
  3. 03Query road network information
  4. 04Plan searches before retrieving geospatial results

MCP support

Exposes Ordnance Survey Data Hub access to MCP clients through tools, resources, and prompts.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "os": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "build"
      ]
    }
  }
}
Run commanddocker run -i --rm build

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocibuild

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Ordnance Survey MCP Server

A MCP server for accessing UK geospatial data through Ordnance Survey APIs.

What it does

Provides LLM access to the Ordnance Survey's Data Hub APIs.

Ask simple questions such as find me all cinemas in Leeds City Centre or use the prompts templates for more complex, speciifc use cases - relating to street works, planning, etc.

Use the prompts templates for more complex, speciifc use cases - relating to road networks, etc.

This MCP server enforces a 2 step workflow plan to ensure the user gets the best results - it must always produce a plan before making searches.

Quick Start

1. Get an OS API Key

Register at OS Data Hub to get your free API key and set up a project.

2. Run with Docker and add to your Claude Desktop config (easiest)
Clone the repository:
git clone https://github.com/your-username/os-mcp-server.git
cd os-mcp-server

Then build the Docker image:

docker build -t os-mcp-server .

Add the following to your Claude Desktop config:

{
  "mcpServers": {
    "os-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "OS_API_KEY=your_api_key_here",
        "-e",
        "STDIO_KEY=any_value",
        "os-mcp-server"
      ]
    }
  }
}

Open Claude Desktop and you show see all available tools, resources, and prompts.

License

MIT License. This project does not have the endorsement of Ordnance Survey. This is a personal project and not affiliated with Ordnance Survey. This is not a commercial product. It is actively being worked on so expect breaking changes and bugs.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.