AI agents call hubs 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 computes and returns graph analytics (degree centrality) on existing wiki pages. It performs no data modification, deletion, or external execution—purely a read/query operation analyzing link topology. Severity is low because misuse would only affect visibility/ranking of results, not data integrity or external operations.
From the tool's definition Tool name 'hubs' and description 'Most-connected pages by degree centrality (in+out distinct neighbours)' indicate a query operation that retrieves and analyzes graph connectivity metrics from the wiki without modifying data.
Attacks that exploit this kind of access
Most-connected pages by degree centrality (in+out distinct neighbours). 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 hubs: 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.
hubs 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 hubs 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 hubs. 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.
hubs 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.
hubs is one line of Wiki's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →