Compact code operations. Actions: compact_file|edit|compact_all|beautify|expand_file|expand_project|validate_pipeline|get_mode|set_mode
AI agents use compact to create or update resources in Project Graph — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Project Graph environment.
The tool performs reversible modifications to code (edit, compact, beautify operations). While 'compact' and 'beautify' are non-destructive transformations, the inclusion of 'edit' as an explicit action confirms write capability. The blast radius is high because an agent with unrestricted access could modify arbitrary source files in a codebase, potentially injecting malicious code or breaking functionality.
From the tool's definition Tool description explicitly lists 'edit' and 'compact_file' among its actions, indicating the ability to modify code files. The server description emphasizes 'code reading and editing' capabilities.
Attacks that exploit this kind of access
Compact code operations. Actions: compact_file|edit|compact_all|beautify|expand_file|expand_project|validate_pipeline|get_mode|set_mode. It is categorised as a Write tool in the Project Graph MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Project Graph MCP server in PolicyLayer and add a rule for compact: 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 Project Graph. Nothing to install.
compact is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the compact 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 compact. 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.
compact is provided by the Project Graph MCP server (rnd-pro/project-graph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →