AI agents call fetch_rows to retrieve information from AACT Clinical Trials MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from the AACT database without modifying, deleting, or executing arbitrary code. It is a standard data retrieval operation with no side effects. The sibling tools and server context all indicate read-only database access. Even if an AI agent misuses this tool, the blast radius is limited to viewing already-public clinical trial data.
From the tool's definition Tool name is 'fetch_rows' and is listed as a sibling to 'read_query', 'search_columns', 'describe_table', and 'list_tables'—all clearly Read operations. The server provides 'direct query access' for 'structured retrieval and analysis' of clinical trial data.
Documented attack patterns abuse exactly the kind of access fetch_rows gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AACT Clinical Trials MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for fetch_rows:
{
"version": "1",
"default": "deny",
"tools": {
"fetch_rows": {}
}
}fetch_rows 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.
fetch_rows. It is categorised as a Read tool in the AACT Clinical Trials MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AACT Clinical Trials MCP Server MCP server in PolicyLayer and add a rule for fetch_rows: 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 AACT Clinical Trials MCP Server. Nothing to install.
fetch_rows 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 fetch_rows 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 fetch_rows. 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.
fetch_rows is provided by the AACT Clinical Trials MCP Server MCP server (navisbio/aact_clinicaltrials_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AACT Clinical Trials 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.
7 AACT Clinical Trials MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.