AI agents call search_alphafold to retrieve information from Gwas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query against a public biological database (AlphaFold) to retrieve pre-computed protein structure predictions. There is no creation, modification, deletion, code execution, or financial impact. The worst-case misuse would be excessive queries or information gathering, both low-risk outcomes. This is a straightforward Read operation.
From the tool's definition The tool description states it 'Search[es] AlphaFold database for predicted structures by gene name or protein name.' The verb 'search' and the action of querying a database to retrieve structure predictions are purely informational with no side effects or…
Attacks that exploit this kind of access
Search AlphaFold database for predicted structures by gene name or protein name. It is categorised as a Read tool in the Gwas MCP Server, which means it retrieves data without modifying state.
Register the Gwas MCP server in PolicyLayer and add a rule for search_alphafold: 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 Gwas. Nothing to install.
search_alphafold 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 search_alphafold 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 search_alphafold. 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.
search_alphafold is provided by the Gwas MCP server (muslus/gwas-mcp). 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 →