Compare secrets between two environments to find differences.
AI agents call keyway_diff to retrieve information from Keyway MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Diffing secrets is fundamentally a read operation: it retrieves and compares data without side effects. However, severity is high rather than low because the tool operates on sensitive credentials; unauthorized diffing could expose which secrets differ between environments, revealing infrastructure or deployment patterns. An AI agent misusing this to compare production vs.
From the tool's definition Tool name is 'keyway_diff' and description states 'Compare secrets between two environments to find differences' — this is a query/comparison operation with no modification or deletion.
Attacks that exploit this kind of access
Compare secrets between two environments to find differences. It is categorised as a Read tool in the Keyway MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Keyway MCP Server MCP server in PolicyLayer and add a rule for keyway_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 Keyway MCP Server. Nothing to install.
keyway_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 keyway_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 keyway_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.
keyway_diff is provided by the Keyway MCP Server MCP server (keywaysh/keyway-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 →