Retrieves cached chunks from a changeMode response. Use this to get subsequent chunks after receiving a partial changeMode response.
AI agents call fetch-chunk to retrieve information from Gemini CLI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches cached data that has already been generated and stored. It performs a simple retrieval operation with no ability to modify, delete, or execute operations. The blast radius of misuse is minimal—an agent could only read chunks it shouldn't have access to, not alter or destroy data.
From the tool's definition Tool name 'fetch-chunk' and description 'Retrieves cached chunks from a changeMode response' indicates data retrieval with no modification or side effects. The verb 'retrieves' confirms read-only access.
Documented attack patterns abuse exactly the kind of access fetch-chunk gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gemini CLI MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for fetch-chunk:
{
"version": "1",
"default": "deny",
"tools": {
"fetch-chunk": {}
}
}fetch-chunk is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieves cached chunks from a changeMode response. Use this to get subsequent chunks after receiving a partial changeMode response. It is categorised as a Read tool in the Gemini CLI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Gemini CLI MCP Server MCP server in PolicyLayer and add a rule for fetch-chunk: 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 Gemini CLI MCP Server. Nothing to install.
fetch-chunk is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the fetch-chunk 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 fetch-chunk. 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.
fetch-chunk is provided by the Gemini CLI MCP Server MCP server (orzcls/gemini-mcp-tool-windows-fixed). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gemini CLI MCP Server, 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.
6 Gemini CLI MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.