AI agents invoke wiki.reindex to trigger actions in WikiMCP. 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.
This tool triggers a system-level operation (reindexing/rescanning all pages) rather than simply reading, writing, or deleting data. It initiates a potentially resource-intensive background process affecting the entire wiki. It is not destructive (no data is deleted) nor does it create/modify content directly, but it executes an operational action with side effects on the index state.
From the tool's definition 'Refresh the wiki index by rescanning all pages' — triggers an external operation (full rescan/reindex of all pages)
Attacks that exploit this kind of access
Refresh the wiki index by rescanning all pages. Use after wiki content has been updated. It is categorised as a Execute tool in the WikiMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Wiki MCP server in PolicyLayer and add a rule for wiki.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 WikiMCP. Nothing to install.
wiki.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 wiki.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 wiki.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.
wiki.reindex is provided by the Wiki MCP server (raydestar/wikimcp). 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 →