mcp-rtl-review
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_RTL_REVIEW_IMAGE | No | The container image to use for the RTL review server. Defaults to 'localhost/zesun33/verilog'. | localhost/zesun33/verilog |
| MCP_RTL_REVIEW_RUNTIME | No | The container runtime to use for the RTL review server. Defaults to 'podman'. | podman |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| rtl_reviewA | Performs full AST-backed static RTL review and semantic code audit on Verilog/SystemVerilog designs, evaluating assignment discipline, reset polarity, bitwidths, undriven nets, and computing a 0–100 quality score with actionable fix suggestions. |
| rtl_check_assignmentsA | Audits Verilog/SystemVerilog source files specifically for assignment discipline violations: blocking '=' in sequential clocked blocks, or non-blocking '<=' in combinational blocks. |
| rtl_check_widthsB | Performs semantic bitwidth analysis on Verilog/SystemVerilog designs, detecting implicit truncation and bit expansion mismatches. |
| rtl_toolchain_infoB | Returns active container/host runtime and version information for the Verilator AST parser and supported rule list. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
The full review tool overlaps with the two targeted check tools, but each has a clearly scoped purpose: comprehensive audit versus specific assignment or width checks. The toolchain info tool is entirely distinct. Some ambiguity exists about when to run the full review versus individual checks, but descriptions mitigate it well.
All tools share the rtl_ prefix, but the naming pattern is mixed: two use verb_noun (rtl_check_assignments, rtl_check_widths), while rtl_review is verb-only and rtl_toolchain_info is noun_noun. The inconsistency is noticeable but still readable and predictable given the shared prefix.
Four tools is well-scoped for a focused RTL review server: one comprehensive review, two targeted checks, and one metadata query. Each tool has a clear purpose and the count feels neither thin nor bloated.
The full review tool provides broad static-analysis coverage including assignments, reset polarity, widths, and undriven nets, while the targeted check tools allow narrower queries. The toolchain info tool supplies environment and rule-compatibility context. No obvious missing operations are apparent for the stated purpose.