symbolics-mcp
An MCP server that enables LLMs to evaluate Lisp expressions on a Symbolics Genera machine over TCP. It bridges JSON-RPC requests to the Genera environment to return evaluation results, stdout, and stderr.
README
symbolics-mcp
An MCP (Model Context Protocol) server that lets LLMs evaluate Lisp expressions on a Symbolics Genera machine over TCP.
The system has two parts:
- eval-server.lisp -- a TCP evaluation server that runs on the Genera machine
- genera-mcp.lisp -- an MCP stdio server that runs on the host (SBCL) and bridges JSON-RPC requests to Genera over TCP
Prerequisites
- A Symbolics Genera virtual machine (e.g. via Open Genera on a Linux/Alpha host or the VLM)
- SBCL on the host machine running the virtual Genera
- Quicklisp installed in SBCL (the MCP server loads
usocketandyasonvia Quicklisp)
Setting up the Genera side
First, copy eval-server.lisp to the Genera SYS:SITE; directory on the host filesystem:
cp eval-server.lisp /opt/symbolics/lib/sys.sct/site/eval-server.lisp
Then load it from the Genera Lisp Listener:
Load File SYS:SITE;eval-server.lisp
The file must be loaded once per boot. It does two things:
- Defines a TCP server (
:mcp-server) that accepts connections, reads length-prefixed Lisp expressions, evaluates them, and returns the result, stdout, and stderr as length-prefixed fields. - Registers the server on TCP port 8888 via
tcp:add-tcp-port-for-protocol.
After loading, the server starts automatically -- there is no separate start command. It listens on port 8888 and handles each connection in its own process.
To verify it is running, you can send a test expression from the host:
echo -n '11 (+ 1 2 3 4)' | nc -w 2 192.168.11.2 8888 | cat -v
The number before the space is the byte length of the expression ((+ 1 2 3 4) = 11 bytes). If the server is working, you should see a response containing 10 (the result of the expression).
MCP configuration
Add the following to your .mcp.json (or the MCP configuration of your client), adjusting the path and IP address for your setup:
{
"mcpServers": {
"symbolics-genera": {
"command": "/path/to/genera-mcp.sh",
"env": {
"GENERA_HOST": "192.168.11.2",
"GENERA_PORT": "8888"
}
}
}
}
Environment variables
| Variable | Default | Description |
|---|---|---|
GENERA_HOST |
genera |
Hostname or IP of the Genera machine |
GENERA_PORT |
8888 |
TCP port of the eval server |
GENERA_TIMEOUT |
30 |
Timeout in seconds for each evaluation |
Exposed tool
The MCP server exposes a single tool:
- eval_lisp -- Evaluate a Common Lisp / Zetalisp expression on the Genera machine and return the result. The response includes the return value, stdout, and stderr (if any).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.