devsignal-mcp
Enables AI agents to control Siglent SDG-series signal generators, configure waveforms, and switch outputs via natural language.
README
devsignal
Agent-friendly signal generator control for the embedded bench, built for the Agentic Firmware Workbench. Configure waveforms and switch outputs on Siglent SDG-series generators — from the command line or from an AI agent via MCP.
Sibling of devpower (USB power control). Typical use: an agent testing an ADC driver or input-capture firmware needs a known stimulus — it sets a 1 kHz sine at 2 Vpp, enables the output, runs the test, and switches the output off.
Supported hardware
Built and verified against the SDG2042X; the C{n}:BSWV / C{n}:OUTP
SCPI dialect is shared across the Siglent SDG family (SDG1000X/2000X/6000X),
so other models are expected to work.
Transport is PyVISA with the pure-Python pyvisa-py backend:
- USB (USBTMC): plug in and go — needs
libusb(brew install libusb/ distro package). - LAN: pass
--resource "TCPIP::<ip>::INSTR"— no drivers needed.
Install
pip install .
Requires Python 3.10+.
CLI
devsignal list # find instruments (USB)
devsignal idn # identity
devsignal status # both channels: wave + output
devsignal wave 1 sine --freq 1000 --amp 3.3 # configure CH1
devsignal wave 1 square --freq 1e6 --amp 3.3 --duty 25
devsignal output 1 on --load HZ # enable CH1 into Hi-Z
devsignal output 1 off
devsignal raw "C1:BSWV?" # raw SCPI escape hatch
devsignal --json status # machine-readable
MCP server
devsignal-mcp runs an MCP server over stdio exposing list_instruments,
get_status, set_wave, set_output, and scpi (raw escape hatch), with
agent-facing safety guidance baked into the tool descriptions.
Register with Claude Code:
claude mcp add --scope user devsignal devsignal-mcp
Safety notes
- Load setting scales the delivered voltage. A 50 Ω setting driving a
high-impedance input delivers twice the programmed amplitude. Use
--load HZwhen driving MCU/logic inputs. - Session limits (human-in-the-loop): on the first amplitude-affecting
MCP call of a session, the user is prompted (MCP elicitation) for the
session's max amplitude; agent requests above it require explicit user
approval, and raw
scpiamplitude changes are gated the same way. Hosts without elicitation support fail safe (over-limit requests are refused). - Hard ceiling: set
DEVSIGNAL_MAX_VPP(e.g.3.3) in the MCP server's environment and nothing above it is accepted - not even with in-session user approval. - Configure the waveform first, verify with
status, then enable the output.
Development
pip install -e ".[dev]"
pytest
The test suite runs against a fake VISA layer — no instrument required.
License
MIT
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.