AI agents call sch.search to retrieve information from TOOL4LM without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries academic databases and Wikipedia for information retrieval only. It performs searches across arXiv, Crossref, and Wikipedia—all read-only operations that return data without creating, modifying, deleting, or executing any operations. No financial transactions, code execution, or destructive actions are possible. The lowest-severity category applies.
From the tool's definition Tool name 'sch.search' and description 'Academic-first search (arXiv + Crossref + Wikipedia)' indicate retrieval of publicly available academic and reference data with no modification or side effects.
Attacks that exploit this kind of access
Academic-first search (arXiv + Crossref + Wikipedia). It is categorised as a Read tool in the TOOL4LM MCP Server, which means it retrieves data without modifying state.
Register the TOOL4LM MCP server in PolicyLayer and add a rule for sch.search: 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 TOOL4LM. Nothing to install.
sch.search 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 sch.search 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 sch.search. 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.
sch.search is provided by the TOOL4LM MCP server (khanhs-234/tool4lm). 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 →