AI agents invoke reindex to trigger actions in Rawthink. 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 triggers a background operation that reads existing content and rebuilds the search database index. It does not delete or overwrite source data, but it does execute a potentially expensive and side-effectful operation (modifying the search index state).
From the tool's definition Re-index vault content into the search database
Attacks that exploit this kind of access
Re-index vault content into the search database. It is categorised as a Execute tool in the Rawthink MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Rawthink MCP server in PolicyLayer and add a rule for reindex: 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 Rawthink. Nothing to install.
reindex 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 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. 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 is provided by the Rawthink MCP server (ygtalp/rawthink-mcp). 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 →