Full prediction metadata + structure file URLs (PDB, CIF, PAE).
AI agents call prediction to retrieve information from Mcp Alphafold without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is purely retrieving pre-computed AlphaFold prediction data and metadata from EBI. There are no side effects, no data modification, no code execution, and no destructive operations. Even if misused by an AI agent, the worst outcome would be excessive read operations or resource consumption, not data loss or system compromise.
From the tool's definition Tool provides 'Full prediction metadata + structure file URLs' — retrieval of data and URLs with no modification, deletion, or execution capability. Sibling tools are 'annotations', 'summary', 'uniprot' — all read-only data access patterns.
Attacks that exploit this kind of access
Full prediction metadata + structure file URLs (PDB, CIF, PAE). It is categorised as a Read tool in the Mcp Alphafold MCP Server, which means it retrieves data without modifying state.
Register the Mcp Alphafold MCP server in PolicyLayer and add a rule for prediction: 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 Mcp Alphafold. Nothing to install.
prediction 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 prediction 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 prediction. 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.
prediction is provided by the Mcp Alphafold MCP server (pipeworx-io/mcp-alphafold). 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 →