创建新的文档条目。
AI agents use project_doc_create to create or update resources in ProjectDoc — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ProjectDoc environment.
This tool creates new documentation entries, which is a reversible modification of project data. It does not execute arbitrary code, delete data permanently, or move money. The severity is medium because erroneous or malicious document creation could clutter the project documentation system and potentially mislead collaborators, but entries can be edited or removed.
From the tool's definition Tool name 'project_doc_create' and description '创建新的文档条目' (creates new document entries) indicate data creation.
Attacks that exploit this kind of access
创建新的文档条目。. It is categorised as a Write tool in the ProjectDoc MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ProjectDoc MCP server in PolicyLayer and add a rule for project_doc_create: 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 ProjectDoc. Nothing to install.
project_doc_create 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 project_doc_create 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 project_doc_create. 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.
project_doc_create is provided by the ProjectDoc MCP server (yarrow-cai/project-doc). 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 →