AI agents use add_batch to create or update resources in Nesift — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nesift environment.
This tool adds new data (web pages) to the system's index. While it does not delete or overwrite existing data (which would be Destructive), and does not execute arbitrary code (which would be Execute), it does perform a Write operation — ingesting and indexing URLs modifies the state of the semantic search index.
From the tool's definition 'Ingest multiple URLs in parallel' — the tool writes/indexes new web content into the local semantic search system, creating persistent records that modify the indexed data store.
Attacks that exploit this kind of access
Ingest multiple URLs in parallel. It is categorised as a Write tool in the Nesift MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nesift MCP server in PolicyLayer and add a rule for add_batch: 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 Nesift. Nothing to install.
add_batch is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_batch 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 add_batch. 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.
add_batch is provided by the Nesift MCP server (scottgl9/nesift). 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 →