This record as markdown: /tools/delimit/delimit-security-audit.md
What delimit_security_audit does on Delimit
AI agents call delimit_security_audit to retrieve information from Delimit without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why delimit_security_audit is rated Low
Audit tools typically retrieve and report on existing state without modifying data. The name indicates passive security review rather than active intervention. However, the empty description prevents higher confidence assessment. Classified as Read with low severity since even if misused, audit queries have minimal blast radius compared to write/execute/destructive actions.
From the tool's definition Tool name 'delimit_security_audit' strongly suggests inspection or review of security logs/status, consistent with audit functions which are typically read-only queries. The description is empty, which lowers confidence.
Attacks that exploit this kind of access
The rule that runs delimit_security_audit safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Delimit, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For delimit_security_audit, this is the rule to start with:
delimit_security_audit is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Delimit, apply this rule, and every delimit_security_audit call is checked against it from then on.
Questions about delimit_security_audit
delimit_security_audit is a read tool on the Delimit MCP server. It is categorised as a Read tool in the Delimit MCP Server, which means it retrieves data without modifying state.
Register the Delimit MCP server in PolicyLayer and add a rule for delimit_security_audit: 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 Delimit. Nothing to install.
delimit_security_audit 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 delimit_security_audit 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 delimit_security_audit. 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.
delimit_security_audit is provided by the Delimit MCP server (delimit-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Delimit, and thousands of servers like it.
This server
Across the catalogue