Count <ref> tags in a wikitext string.
AI agents call get_ref_count to retrieve information from Wikicitation without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a passive analysis operation—counting XML-like tags in a string—with no side effects, no state modification, and no external operations triggered. It is a straightforward data retrieval/analysis function typical of Read category tools.
From the tool's definition Tool name 'get_ref_count' and description 'Count <ref> tags in a wikitext string' indicate a retrieval/query operation that counts occurrences of reference tags without modifying data.
Attacks that exploit this kind of access
Count <ref> tags in a wikitext string. It is categorised as a Read tool in the Wikicitation MCP Server, which means it retrieves data without modifying state.
Register the Wikicitation MCP server in PolicyLayer and add a rule for get_ref_count: 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 Wikicitation. Nothing to install.
get_ref_count 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 get_ref_count 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 get_ref_count. 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.
get_ref_count is provided by the Wikicitation MCP server (jsobel1/wikicitation-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 →