polymer_entity
AI agents call polymer_entity to retrieve information from Mcp Rcsb Pdb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves polymer entity information from a public scientific database. It performs a query and returns structural data without modifying anything. The context confirms the server is read-only for data retrieval purposes. Low severity because misuse only exposes existing public scientific data.
From the tool's definition Tool name 'polymer_entity' is part of a server explicitly described as 'querying and retrieving' data from RCSB Protein Data Bank. Sibling tools ('assembly', 'ligand', 'search', 'structure', 'summary') are all retrieval operations.
Attacks that exploit this kind of access
polymer_entity. It is categorised as a Read tool in the Mcp Rcsb Pdb MCP Server, which means it retrieves data without modifying state.
Register the Mcp Rcsb Pdb MCP server in PolicyLayer and add a rule for polymer_entity: 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 Rcsb Pdb. Nothing to install.
polymer_entity 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 polymer_entity 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 polymer_entity. 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.
polymer_entity is provided by the Mcp Rcsb Pdb MCP server (pipeworx-io/mcp-rcsb-pdb). 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 →