assembly
AI agents call assembly 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.
The assembly tool appears to retrieve protein structure assembly data from a public scientific database. This is a read-only operation that queries existing data without creating, modifying, deleting, or executing code. The context of RCSB PDB—a read-only scientific data repository—and the nature of sibling tools all indicate retrieval functionality.
From the tool's definition Tool named 'assembly' on RCSB PDB server described as enabling retrieval of protein structures; sibling tools (ligand, polymer_entity, search, structure, summary) are all query/retrieval operations with no side effects.
Attacks that exploit this kind of access
assembly. 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 assembly: 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.
assembly 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 assembly 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 assembly. 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.
assembly 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 →