Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-vcd show changes for signal 'clock' between 0ns and 100ns"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A model context protocol (MCP) server for value change dump (VCD) waveforms.
https://github.com/user-attachments/assets/9d1a6a64-de22-4b5a-a597-685c663c9c79
get-signal: Provide all changes of the specified signal name to the model's context. This is useful for large waveform files with many signals where you cannot fit the entire VCD file into the model's context window.
Can optionally specify a start and end timestamp range for the model to look at.
uv pip install --system mcp-vcd
And add the following to your claude_desktop_config.json:
"mcpServers": {
"mcp-vcd": {
"command": "uv",
"args": [
"run",
"mcp-vcd"
]
}
}See Anthropic's MCP documentation for more info.
Get all instances of a specified signal in a VCD file
| Name | Required | Description | Default |
|---|---|---|---|
| file_name | Yes | Name of the VCD file to analyze | |
| signal_name | Yes | Name of the signal to search for | |
| start_time | No | Start timestamp (optional) | |
| end_time | No | End timestamp (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only indicates a read operation ('Get') without mentioning side effects, error conditions, or performance implications. The description is insufficiently transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 11 words, highly concise and front-loaded with the core action. No extraneous information is present.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, and the description does not explain what an 'instance' constitutes (e.g., time, value). For a tool with 4 parameters and no output schema, the description is inadequate for complete understanding of the return format.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, meaning all parameters are described in the input schema. The tool description does not add any additional semantic value beyond what the schema already provides, meeting the baseline for this dimension.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'all instances of a specified signal in a VCD file', making the tool's purpose specific and unambiguous. No siblings exist, so differentiation is unnecessary.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
With no sibling tools, usage guidelines are less critical, but the description provides no explicit context, prerequisites, or when-to-use advice. It implicitly suggests analyzing VCD files but lacks definitive guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get-signalScored across 1 tool
With only one tool, there is no possibility of confusion between tools, so disambiguation is perfect.
A single tool trivially maintains consistency. The name 'get-signal' follows a clear verb_noun pattern.
A single tool is far too few for a VCD file server. Typical operations like loading files, listing signals, or querying multiple signals are missing.
The tool surface is severely incomplete. It only provides one operation (get-signal), lacking essential lifecycle or exploration capabilities for VCD files.
Save and query market signals from your AI conversations.
Stop re-explaining yourself to Agents. Give it the right context, right when needed.
Codebase graphs, caller impact analysis, and recorded project context for AI coding agents.
Your portable context layer — load it into any AI.
