AI agents call failed_chunks 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.
This tool aggregates and retrieves diagnostic information about chunking errors that occurred during code indexing. It is a read-only query operation with no side effects—it simply surfaces historical error data for analysis and debugging.
From the tool's definition Tool name 'failed_chunks' and description 'Aggregated chunking errors during indexing' indicate retrieval of error logs or metadata about indexing failures. No modification, deletion, execution, or financial operations are implied.
Attacks that exploit this kind of access
Aggregated chunking errors during indexing (AST failures, regex fallbacks, binary files). 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 failed_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 Paparats. Nothing to install.
failed_chunks 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 failed_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.
Set action: deny in the PolicyLayer policy for failed_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.
failed_chunks 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 →