AI agents call metadata_diff to retrieve information from Asc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays differences between two versions of app metadata (descriptions, keywords, release notes). It performs a read-only comparison operation with no side effects. The data queried already exists (live vs. pending versions), and the tool only presents the delta. There is no capability to modify, delete, or execute operations.
From the tool's definition Tool description explicitly states it 'Compare[s] metadata' and 'Shows what changed' — purely retrieval and comparison of existing data with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Compare metadata between your live and pending app versions. Shows what changed in descriptions, keywords, and release notes across locales. It is categorised as a Read tool in the Asc MCP Server, which means it retrieves data without modifying state.
Register the Asc MCP server in PolicyLayer and add a rule for metadata_diff: 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 Asc. Nothing to install.
metadata_diff 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 metadata_diff 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 metadata_diff. 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.
metadata_diff is provided by the Asc MCP server (pofky/asc-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 →