project_doc_append · ProjectDoc MCP: Risk & Policy

WHAT IT DOES

What project_doc_append does on ProjectDoc

AI agents use project_doc_append 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.

WHY IT NEEDS A POLICY

Why project_doc_append needs a policy

This tool appends content to an existing document entry without overwriting or deleting anything. It is a non-destructive write operation — it only adds data to the end of an entry. Severity is low because the blast radius is limited to appending unwanted text to a documentation entry, which is easily reversible via update.

From the tool's definition 追加内容到已有条目的末尾，自动添加分隔线。不覆盖已有内容。 (Appends content to the end of an existing entry, automatically adds a separator line. Does not overwrite existing content.)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

project_doc_append Rate-limited

project_doc_append stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "project_doc_append": {
      "limits": [
        {
          "counter": "project_doc_append_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches ProjectDoc, so you can run agents against it safely.

FAQ

Questions about project_doc_append

What does the project_doc_append tool do? +

追加内容到已有条目的末尾，自动添加分隔线。不覆盖已有内容。. 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.

How do I enforce a policy on project_doc_append? +

Register the ProjectDoc MCP server in PolicyLayer and add a rule for project_doc_append: 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.

What risk level is project_doc_append? +

project_doc_append is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit project_doc_append? +

Yes. Add a rate_limit block to the project_doc_append 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.

How do I block project_doc_append completely? +

Set action: deny in the PolicyLayer policy for project_doc_append. 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.

What MCP server provides project_doc_append? +

project_doc_append 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.