AI agents call orphans to retrieve information from Wikimcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and reports the structure of the wiki graph to identify pages without connections. It performs no writes, deletions, or side effects—merely returns data about existing page relationships. This is a standard Read operation (retrieve, inspect, analyze) with minimal blast radius if misused by an agent.
From the tool's definition Tool returns analytic information about orphaned pages and dead-ends—'pages with no edges' and 'pages with inbound but no outbound'. The description uses passive language ('with no edges') indicating retrieval/inspection, not modification.
Attacks that exploit this kind of access
Pages with no edges (orphans) and pages with inbound but no outbound (dead-ends). It is categorised as a Read tool in the Wikimcp MCP Server, which means it retrieves data without modifying state.
Register the Wiki MCP server in PolicyLayer and add a rule for orphans: 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.
orphans 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 orphans 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 orphans. 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.
orphans is provided by the Wiki MCP server (mohith-das/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 →