update_source · Llm Wiki MCP: Risk & Policy

WHAT IT DOES

What update_source does on Llm Wiki

AI agents use update_source to create or update resources in Llm Wiki — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Llm Wiki environment.

WHY IT NEEDS A POLICY

Why update_source needs a policy

This tool modifies existing data (updates a source file and rebuilds wiki pages) but does not irreversibly delete data nor execute arbitrary code—it performs a bounded write operation within the wiki system. The partial rebuild scope and reversibility of updates classify it as Write rather than Execute or Destructive.

From the tool's definition Tool name 'update_source' and description indicate it updates an ingested raw file and partially rebuilds related wiki pages.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_source Rate-limited

update_source 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": {
    "update_source": {
      "limits": [
        {
          "counter": "update_source_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 Llm Wiki, so you can run agents against it safely.

FAQ

Questions about update_source

What does the update_source tool do? +

更新一个已 ingest 的原始文件，并局部重建相关 wiki 页面。. It is categorised as a Write tool in the Llm Wiki MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_source? +

Register the Llm Wiki MCP server in PolicyLayer and add a rule for update_source: 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 Llm Wiki. Nothing to install.

What risk level is update_source? +

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

Can I rate-limit update_source? +

Yes. Add a rate_limit block to the update_source 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 update_source completely? +

Set action: deny in the PolicyLayer policy for update_source. 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 update_source? +

update_source is provided by the Llm Wiki MCP server (quick-sort/llm-wiki-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.