Check if a local file exists (restricted to workspace directory)
AI agents call check_file_exists to retrieve information from AI Development Pipeline MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves information about file existence; it does not create, modify, delete, or execute anything. It is a simple existence check that returns a boolean result without altering state. Severity is low because even if an AI misuses it, the impact is limited to information disclosure within a restricted directory.
From the tool's definition Tool description states 'Check if a local file exists' — a pure query operation with no modification or side effects. The restriction to the workspace directory further limits scope.
Attacks that exploit this kind of access
Check if a local file exists (restricted to workspace directory). It is categorised as a Read tool in the AI Development Pipeline MCP MCP Server, which means it retrieves data without modifying state.
Register the AI Development Pipeline MCP server in PolicyLayer and add a rule for check_file_exists: 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 AI Development Pipeline MCP. Nothing to install.
check_file_exists 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 check_file_exists 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 check_file_exists. 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.
check_file_exists is provided by the AI Development Pipeline MCP server (theburgerllc/ai-development-pipeline-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 →