AI agents use generate_project_doc to create or update resources in Mcp Flow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Flow environment.
The tool creates or modifies a project documentation file (project.md), which is a reversible write operation. It does not execute arbitrary code, delete data, move money, or read sensitive information—it simply generates documentation based on project structure analysis.
From the tool's definition Tool description states 'write a compact project.md' and 'Scan a project and write', indicating file creation/modification. The tool name includes 'generate' which creates new artifacts.
Attacks that exploit this kind of access
Scan a project and write a compact project.md (structure, stack,. It is categorised as a Write tool in the Mcp Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Flow MCP server in PolicyLayer and add a rule for generate_project_doc: 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 Mcp Flow. Nothing to install.
generate_project_doc is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_project_doc 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 generate_project_doc. 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.
generate_project_doc is provided by the Mcp Flow MCP server (remimenguy/mcp-flow). 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 →