fetch_results
AI agents call fetch_results to retrieve information from Tacc Mcp Bio without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name 'fetch_results' and the broader server functionality for reading job outputs and logs on an HPC cluster, this tool most likely retrieves completed job results or output data without modification. No destructive, financial, or state-changing operations are suggested.
From the tool's definition Tool name 'fetch_results' and sibling tools like 'check_outputs', 'fetch_file', and 'check_connection' suggest data retrieval operations. The server context involves job management and log reading on HPC clusters, indicating read-only data access patterns.
Attacks that exploit this kind of access
fetch_results. It is categorised as a Read tool in the Tacc Mcp Bio MCP Server, which means it retrieves data without modifying state.
Register the Tacc Mcp Bio MCP server in PolicyLayer and add a rule for fetch_results: 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 Tacc Mcp Bio. Nothing to install.
fetch_results 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_results 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_results. 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_results is provided by the Tacc Mcp Bio MCP server (narasimhan-lab/tacc-mcp-bio). 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 →