AI agents call get_chunk to retrieve information from Paparats without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the name 'get_chunk' and the server's stated purpose as a semantic code search engine indicate this tool retrieves or queries data (code chunks) without side effects. This aligns with the Read category. Confidence is slightly reduced due to the missing description, but sibling tools like 'arch_list' and 'explain_feature' support this being a retrieval-focused server.
From the tool's definition Tool name 'get_chunk' suggests retrieval of code/data segments from the semantic search index. The server is described as a code search tool for retrieving information from local Qdrant storage, indicating query/retrieval operations.
Attacks that exploit this kind of access
get_chunk. It is categorised as a Read tool in the Paparats MCP Server, which means it retrieves data without modifying state.
Register the Paparats MCP server in PolicyLayer and add a rule for get_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 Paparats. Nothing to install.
get_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 get_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 get_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.
get_chunk is provided by the Paparats MCP server (@paparats/cli). 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 →