AI agents call aio_citation_check to retrieve information from Geoseo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve or analyze citation information for SEO purposes, consistent with the 'Read' category. However, the empty description significantly limits confidence. The naming convention and context within a SEO analysis server suggest it queries existing citation data without modifying it. Severity is low because reads on public SEO/citation data pose minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'aio_citation_check' suggests checking or querying citation data. The 'check' verb indicates retrieval/inspection rather than modification. The 'citation' component aligns with the server's stated capability of 'citation tracking'.
Attacks that exploit this kind of access
aio_citation_check. It is categorised as a Read tool in the Geoseo MCP Server, which means it retrieves data without modifying state.
Register the Geoseo MCP server in PolicyLayer and add a rule for aio_citation_check: 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 Geoseo. Nothing to install.
aio_citation_check 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 aio_citation_check 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 aio_citation_check. 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.
aio_citation_check is provided by the Geoseo MCP server (rachit8484/geoseo-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 →