openroad_eval
Evaluates a Tcl snippet in a fresh stateless OpenROAD session and returns capped stdout. Include any read_lef/read_liberty/read_def setup the query needs; no state persists between calls.
This record as markdown: /tools/zesun33-mcp-openroad/openroad-eval.md
What openroad_eval does on Mcp Openroad
AI agents call openroad_eval to retrieve information from Mcp Openroad without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
cwd | string | — | Optional working directory. |
tcl | string | Yes | Tcl snippet to evaluate (max 8000 chars). |
timeout_ms | number | — | Timeout in milliseconds. |
Parameters from the server's own tool schema.
Why openroad_eval is rated Low
Even though openroad_eval only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsAccepts file system path (cwd)
Attacks that exploit this kind of access
The rule that runs openroad_eval safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Openroad, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For openroad_eval, this is the rule to start with:
openroad_eval is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Openroad, apply this rule, and every openroad_eval call is checked against it from then on.
Questions about openroad_eval
Evaluates a Tcl snippet in a fresh stateless OpenROAD session and returns capped stdout. Include any read_lef/read_liberty/read_def setup the query needs; no state persists between calls. It is categorised as a Read tool in the Mcp Openroad MCP Server, which means it retrieves data without modifying state.
openroad_eval accepts 3 parameters: cwd, tcl, timeout_ms. Required: tcl. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Openroad MCP server in PolicyLayer and add a rule for openroad_eval: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Openroad. Nothing to install.
openroad_eval is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the openroad_eval rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for openroad_eval. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
openroad_eval is provided by the Mcp Openroad MCP server (@zesun33/mcp-openroad). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcp Openroad, and thousands of servers like it.
This server
Across the catalogue