pyslang-mcp is a read-only Model Context Protocol server for compiler-backed Verilog and SystemVerilog analysis. It uses pyslang to parse HDL projects, report diagnostics, inspect design units and hierarchy, and expose structured semantic information to AI tools.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"pyslang-mcp": {
"args": [
"-m",
"pyslang_mcp",
"--transport",
"stdio"
],
"command": "/path/to/python"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
pyslang-mcp is an alpha-quality, local-first Model Context Protocol server for read-only, compiler-backed analysis of Verilog and SystemVerilog projects using pyslang.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
uvx 'pyslang-mcp' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked pyslang-mcp against OSV.dev.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in ai-ml / developer-tools
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
Manage Supabase projects — databases, auth, storage, and edge functions
Dynamic problem-solving through sequential thought chains
MCP Security Weekly
Get CVE alerts and security updates for Pyslang Mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
pyslang-mcp is an alpha-quality, local-first Model Context Protocol server
for read-only, compiler-backed analysis of Verilog and SystemVerilog projects
using pyslang.
The goal is narrow and explicit: give AI clients structured HDL project context through real parsing and elaboration, not raw text search. This project is a semantic analysis MCP, not a simulator, synthesizer, waveform viewer, or code generator.
[!IMPORTANT] This repo now contains a runnable alpha implementation, but it is not yet a published or broadly hosted MCP product.
AI coding agents can already search HDL repositories as text. That is useful,
but weak. pyslang-mcp exists to answer questions that benefit from a real
compiler frontend:
As of 2026-04-19, the repository contains:
pyproject.toml packaging metadataFastMCP server under src/pyslang_mcp/stdio entrypoint via python -m pyslang_mcpcall_tool() pathsWhat is still not done:
The current alpha implements these read-only tools:
| Area | Tools |
|---|---|
| Parse / load | pyslang_parse_files, pyslang_parse_filelist |
| Diagnostics | pyslang_get_diagnostics |
| Semantic inventory | pyslang_list_design_units, pyslang_describe_design_unit |
| Structure | pyslang_get_hierarchy, pyslang_get_project_summary |
| Lookup | pyslang_find_symbol |
| Syntax / preprocessing summaries | pyslang_dump_syntax_tree_summary, pyslang_preprocess_files |
stdio transport firstpyslang_preprocess_files behavior that returns preprocessing metadata
and excerpts, not a claimed full preprocessed text streamThe implemented .f parser intentionally supports a practical subset:
-f and -F+incdir+..., -I dir, and -Idir+define+..., -D NAME, and -DNAMEUnsupported directives are reported back in pyslang_parse_filelist output instead of
being silently ignored.
The repo now includes a generated HDL corpus under
examples/hdl with:
easy, medium, and hardpyslang and VerilatorRun the full corpus validator locally:
./.venv/bin/python scripts/validate_hdl_examples.py
CI only runs a small smoke subset so the repository keeps representative HDL coverage without turning the example corpus into the product.
Local development setup:
cd /path/to/pyslang-mcp
python -m venv .venv
./.venv/bin/pip install -e '.[dev]'
Run