EPICS Process Variable Bridge MCP server

Provides a bridge between AI and EPICS process variables, enabling real-time monitoring and control of industrial systems through tools for getting, setting, and retrieving detailed information about hardware systems.
Back to servers
Provider
Yan Jiang
Release date
Apr 25, 2025
Language
Python
Stats
2 stars

The EPICS MCP Server is a Python-based server designed to interact with EPICS (Experimental Physics and Industrial Control System) process variables (PVs). It allows you to retrieve PV values, set PV values, and fetch detailed information about PVs using the MCP framework, making it ideal for integration into larger control systems or workflows.

Prerequisites

EPICS Installation

Before using the EPICS MCP Server, you must install EPICS on your local machine and ensure it's working properly. Verify that functions such as caget, caput, and cainfo are operational.

For detailed EPICS installation instructions, visit the EPICS Controls website.

Example of a working EPICS setup:

jiangyan@DESKTOP-84CO9VB:~$ softIoc -d ~/EPICS/DB/test.db
Starting iocInit
############################################################################
## EPICS R7.0.8
## Rev. 2025-02-13T14:29+0800
## Rev. Date build date/time:
############################################################################
iocRun: All initialization complete
epics>

Verify EPICS functionality:

jiangyan@DESKTOP-84CO9VB:~$ caget temperature:water
temperature:water              88
jiangyan@DESKTOP-84CO9VB:~$ caput temperature:water 100
Old : temperature:water              88
New : temperature:water              100
jiangyan@DESKTOP-84CO9VB:~$ cainfo temperature:water
temperature:water
    State:            connected
    Host:             127.0.0.1:5056
    Access:           read, write
    Native data type: DBF_DOUBLE
    Request type:     DBR_DOUBLE
    Element count:    1

Installation

Install the EPICS MCP Server and its dependencies:

pip install -r requirements.txt

Available Tools

get_pv_value

Retrieves the current value of a specified PV.

Inputs:

  • pv_name (string): The name of the PV variable.

Returns: A JSON object with the status (success or error) and the retrieved value or an error message.

set_pv_value

Sets a new value for a specified PV.

Inputs:

  • pv_name (string): The name of the PV variable.
  • pv_value (string): The new value to be set for the PV.

Returns: A JSON object with the status (success or error) and a confirmation message or an error message.

get_pv_info

Fetches detailed information about a specified PV.

Inputs:

  • pv_name (string): The name of the PV variable.

Returns: A JSON object with the status (success or error) and detailed information about the PV or an error message.

Using with Langchain

To use the EPICS MCP Server with Langchain:

server_params = StdioServerParameters(
    command="python",
    # Make sure to update to the full absolute path to your server.py file
    args=["/path/server.py"],
)

Example Usage

Here's a complete example of using the EPICS MCP Server with a client:

async def run():
    async with stdio_client(server_params) as (read, write):
        async with ClientSession(read, write) as session:
            # Initialize the connection
            await session.initialize()

            # Get tools
            tools = await load_mcp_tools(session)

            # Create and run the agent
            agent = create_react_agent(model, tools)
            agent_response = await agent.ainvoke({"messages": "To query the value of a PV (Process Variable) named temperature:water"})
            return agent_response

Example Result

================================[1m Human Message [0m=================================

To query the value of a PV (Process Variable) named temperature:water
==================================[1m Ai Message [0m==================================
Tool Calls:
  get_pv_value (call_vvbXwi51CyYUxEM0hcyvCFCY)
 Call ID: call_vvbXwi51CyYUxEM0hcyvCFCY
  Args:
    pv_name: temperature:water
=================================[1m Tool Message [0m=================================
Name: get_pv_value

{
  "status": "success",
  "value": 88.0
}
==================================[1m Ai Message [0m==================================

The current value of the PV named `temperature:water` is 88.0.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later