What is Epics Mcp Server

EPICS-MCP-Server is a Python-based server designed to interact with EPICS (Experimental Physics and Industrial Control System) process variables (PVs). It provides tools for retrieving, setting, and fetching detailed information about PVs, making it suitable for integration into larger control systems.

Use cases

Use cases for EPICS-MCP-Server include real-time monitoring of experimental setups, automated control of laboratory equipment, and integration into larger data acquisition systems for research and industrial applications.

How to use

To use EPICS-MCP-Server, first install the required dependencies using ‘pip install -r requirements.txt’. Then, configure the server parameters in your code to point to the server script and ensure EPICS is installed on your local machine.

Key features

Key features of EPICS-MCP-Server include: 1. ‘get_pv_value’ for retrieving PV values, 2. ‘set_pv_value’ for updating PV values, and 3. ‘get_pv_info’ for fetching detailed information about PVs. Each function returns a JSON object indicating success or error.

Where to use

EPICS-MCP-Server is primarily used in environments where EPICS PVs are utilized for monitoring and controlling hardware or software parameters, such as in scientific research facilities, industrial automation, and control systems.

EPICS-MCP-Server

Overview

• The EPICS MCP Server is a Python-based server designed to interact with EPICS (Experimental Physics and Industrial Control System) process variables (PVs). It provides a set of tools to retrieve PV values, set PV values, and fetch detailed information about PVs. The server is built
  using the mcp framework and communicates over stdio, making it suitable for integration into larger control systems or workflows.

• This tool is particularly useful in environments where EPICS PVs are used for monitoring and controlling hardware or software parameters.

Features

• The EPICS MCP Server provides the following tools:

1. get_pv_value

   • Create or update a single file in a repository
   • Inputs:
     • pv_name (string): The name of the PV variable.
   • Returns: A JSON object containing the status (success or error) and the retrieved value or an error message.

2. set_pv_value

   • Set 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 containing the status (success or error) and a confirmation message or an error message.

3. get_pv_info

   • Fetches detailed information about a specified PV.
   • Inputs:
     • pv_name (string): The name of the PV variable.
   • Returns: A JSON object containing the status (success or error) and the detailed information about the PV or an error message.

Usage with Langchain

• To use this with Langchain, you must install the dependencies required for the project.

pip install -r requirements.txt

• Langchain

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

• EPICS

• Before using the EPCIS mcp server, you must successfully install EPCIS on your local machine, ensure that IOC can start normally, and verify that functions such as caget, caput, and cainfo are working properly. For detailed installation instructions, please refer to https://epics-controls.org/resources-and-support/base/.

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>

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

Test Result

• Mcp 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
)

• Result:

================================ Human Message =================================

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

{
 "status": "success",
 "value": 88.0
}
================================== Ai Message ==================================

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