Wolfram Language Paclet Repository
Community-contributed installable additions to the Wolfram Language
Client for Docker MCP Toolkit
Introduction
This notebook has a complete usage example of a thin Model Context Protocol (MCP) client of the Raku paclet "MCPClient".
"MCPClient" provides a set of functions for using MCP server's methods by converting them to objects. Those objects can be used with Wolfram Language's Large Language Model (LLM) framework. (, , .)
Install the paclet and load it
In[2]:=
PacletInstall["AntonAntonov/MCPClient"];Needs["AntonAntonov`MCPClient`"];
MCP Setup and initialization
Get Docker profile file name
In[26]:=
profileFile=FileNameJoin[{PacletFind["AntonAntonov/MCPClient"]〚1〛["Location"],"Resources","default_docker_profile.json"}];
Import the profile
In[32]:=
RunProcess[{"/usr/local/bin/docker","mcp","profile","import",profileFile}]
Setup MCP server process creation command elements
In[33]:=
cmd={"/usr/local/bin/docker","mcp","gateway","run","--profile","default-docker-profile"};
Create the MCP client object
In[34]:=
client=
[cmd,ProcessEnvironmentGetEnvironment[]];
 | MCPStart |
Function[ |
Initialize the client
In[36]:=
r=
[client,"Pause"10];
| MCPInitialize |
Function[ |
Tools discovery and creation
Get the MCP server tools list (and tabulate parts of it)
In[42]:=
mcpTools=
[client,"Pause"8];mcpTools//Map[KeyTake[#,{"name","description"}]&,#]&//Dataset//ResourceFunction["GridTableForm"]
| MCPListTools |
Make LLMTool objects
In[18]:=
tools=
[client,mcpTools]
 | MCPToLLMTool |
Make a configuration with the tools
In[19]:=
conf=LLMConfiguration["Model"{"OpenAI","gpt-5.3-chat-latest"},"MaxTokens"8192,"Tools"tools];
LLM invocations
Find the unaccepted GitHub Pull Requests (PRs):
In[24]:=
LLMSynthesize["Which of my -- antononcube -- GitHub pull requests are pending?",LLMEvaluatorconf]
Stopping the MCP server process
Kill the MCP client process
In[43]:=
MCPKill[client]
 |
|
 |
|
""