Detect project state, stack, package manager, tests, auth, database, deployment, CI, and risk notes.
AI agents call detect_project to retrieve information from CodeAudit MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports information about a project's configuration, dependencies, and infrastructure without modifying, executing against, or deleting any data. It is a passive inspection/audit capability aligned with the 'Read' category. The low severity reflects minimal blast radius—misuse would at worst expose information the agent already has access to, not cause side effects or data loss.
From the tool's definition Tool description explicitly states it 'Detect[s] project state' and related metadata (stack, package manager, tests, auth, database, deployment, CI, risk notes). The verb 'detect' indicates inspection/querying of existing project configuration and state.
Attacks that exploit this kind of access
Detect project state, stack, package manager, tests, auth, database, deployment, CI, and risk notes. It is categorised as a Read tool in the CodeAudit MCP MCP Server, which means it retrieves data without modifying state.
Register the CodeAudit MCP server in PolicyLayer and add a rule for detect_project: 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 CodeAudit MCP. Nothing to install.
detect_project 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 detect_project 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 detect_project. 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.
detect_project is provided by the CodeAudit MCP server (priyanshuchawda/codeaudit). 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 →