Low Risk

list_chunks

list_chunks

How to control list_chunks ↓

What list_chunks does on Diffchunk

AI agents call list_chunks to retrieve information from Diffchunk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why list_chunks needs a policy

list_chunks appears to enumerate or list available chunks within diff files, which is a retrieval operation with no side effects. No modification, execution, deletion, or financial operations are implied. The empty tool description slightly reduces confidence, but the server's stated purpose and sibling tools strongly suggest read-only chunk listing functionality.

From the tool's definition Tool name 'list_chunks' and server description indicate this retrieves or lists chunk metadata from diff files.

Documented attack patterns abuse exactly the kind of access list_chunks gives an agent:

How to control list_chunks

PolicyLayer is an MCP gateway — it sits between your AI agents and Diffchunk, and nothing reaches the server without passing your rules. This is the rule we recommend for list_chunks:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "list_chunks": {}
  }
}

list_chunks is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Diffchunk — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about list_chunks

What does the list_chunks tool do? +

list_chunks. It is categorised as a Read tool in the Diffchunk MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list_chunks? +

Register the Diffchunk MCP server in PolicyLayer and add a rule for list_chunks: 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 Diffchunk. Nothing to install.

What risk level is list_chunks? +

list_chunks is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit list_chunks? +

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

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

list_chunks is provided by the Diffchunk MCP server (peteretelej/diffchunk). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Diffchunk tool call.

Start from Diffchunk, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

5 Diffchunk tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.