This record as markdown: /tools/eda-agent/proj-open.md
What proj_open does on Eda Agent
AI agents invoke proj_open to trigger actions in Eda Agent. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why proj_open is rated High
Opening a project triggers an external application operation in Altium Designer via the persistent DelphiScript bridge. It is not a pure read (it changes application state by loading a project into the IDE), nor does it destroy data, but it executes an action in an external environment whose effects depend on the file path argument.
From the tool's definition Open an existing Altium project
Attacks that exploit this kind of access
The rule that runs proj_open safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Eda Agent, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For proj_open, this is the rule to start with:
proj_open stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Eda Agent, apply this rule, and every proj_open call is checked against it from then on.
Questions about proj_open
Open an existing Altium project. It is categorised as a Execute tool in the Eda Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Eda Agent MCP server in PolicyLayer and add a rule for proj_open: 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 Eda Agent. Nothing to install.
proj_open is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the proj_open 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 proj_open. 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.
proj_open is provided by the Eda Agent MCP server (salitronic/eda-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Eda Agent, and thousands of servers like it.
Across the catalogue