AI agents call DatasetFullTextSearch to retrieve information from OpenBudget MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Full-text search is a read-only operation that retrieves data without modifying it. The empty description lowers confidence slightly, but the tool name and server context (OpenBudget API for querying governmental datasets) strongly suggest this is a search/retrieval function consistent with the Read category. No evidence of side effects, deletions, code execution, or financial transactions.
From the tool's definition Tool name 'DatasetFullTextSearch' indicates a search operation on budget datasets; server description emphasizes 'query and search' capabilities with no write or destructive operations mentioned.
Documented attack patterns abuse exactly the kind of access DatasetFullTextSearch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenBudget MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for DatasetFullTextSearch:
{
"version": "1",
"default": "deny",
"tools": {
"DatasetFullTextSearch": {}
}
}DatasetFullTextSearch is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
DatasetFullTextSearch. It is categorised as a Read tool in the OpenBudget MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenBudget MCP Server MCP server in PolicyLayer and add a rule for DatasetFullTextSearch: 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 OpenBudget MCP Server. Nothing to install.
DatasetFullTextSearch 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 DatasetFullTextSearch 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 DatasetFullTextSearch. 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.
DatasetFullTextSearch is provided by the OpenBudget MCP Server MCP server (openbudget/budgetkey-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenBudget MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 OpenBudget MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.