Count DOIs in a wikitext string.
AI agents call get_doi_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 retrieves and counts metadata (DOIs) from provided wikitext input without modifying, creating, deleting, or executing any operations. It is a pure read operation analogous to search or list functions. The blast radius of misuse is minimal—an agent could only waste resources on repeated counting queries.
From the tool's definition Tool name 'get_doi_count' and description 'Count DOIs in a wikitext string' indicate a counting/query operation with no side effects.
Attacks that exploit this kind of access
Count DOIs 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_doi_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_doi_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_doi_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_doi_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_doi_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.
get_doi_count is one line of Wikicitation'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 →