This record as markdown: /tools/mcp-anything/build-run.md
What build_run does on Mcp Anything
AI agents invoke build_run to trigger actions in Mcp Anything. 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 build_run is rated High
The tool executes a build system command with side effects that depend on the build configuration and project state. While the description says 'Generate,' build commands in Unity inherently execute compilation and asset processing. This falls under Execute (runs code/commands with external operations) rather than Write, as builds are not simple data modification.
From the tool's definition Tool name is 'build_run' and description states 'Generate the Unity build command' — this generates and triggers a build process, which is code execution with external effects (compilation, asset processing, potential output generation).
Attacks that exploit this kind of access
The rule that runs build_run safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Anything, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For build_run, this is the rule to start with:
build_run 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 Mcp Anything, apply this rule, and every build_run call is checked against it from then on.
Questions about build_run
Generate the Unity build command. It is categorised as a Execute tool in the Mcp Anything MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Anything MCP server in PolicyLayer and add a rule for build_run: 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 Anything. Nothing to install.
build_run 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 build_run 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 build_run. 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.
build_run is provided by the Mcp Anything MCP server (Zaymadkid/mcp-anything). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcp Anything, and thousands of servers like it.
Across the catalogue