AI agents invoke reindex_document to trigger actions in Ai Brain. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Reindexing queues a background operation that rebuilds the document's index entry. This is an Execute-category action because it triggers an external process whose effects depend on the document argument. It is not purely a read (it causes side effects) nor a write (it doesn't create/modify document content directly).
From the tool's definition 'Queue a rebuild of a document' — triggers an external operation (reindexing/rebuild process) rather than simply reading or writing document content
Attacks that exploit this kind of access
Queue a rebuild of a document. It is categorised as a Execute tool in the Ai Brain MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ai Brain MCP server in PolicyLayer and add a rule for reindex_document: 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 Ai Brain. Nothing to install.
reindex_document is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the reindex_document 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 reindex_document. 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.
reindex_document is provided by the Ai Brain MCP server (thejoshgriffith/ai-brain). 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 →