mutate_residue
AI agents invoke mutate_residue to trigger actions in ChimeraX MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
'mutate_residue' implies modifying a residue in a protein structure, which is a write/execute operation on structural data. Given the server's editing context and sibling tools like 'delete_atoms' (Destructive) and 'add_hydrogen' (Write), mutating a residue likely alters the model in a way that may or may not be reversible depending on session state.
From the tool's definition Tool name 'mutate_residue' on a server for protein structure 'editing' — the server description explicitly mentions 'editing' as a capability.
Attacks that exploit this kind of access
mutate_residue. It is categorised as a Execute tool in the ChimeraX MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ChimeraX MCP Server MCP server in PolicyLayer and add a rule for mutate_residue: 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 ChimeraX MCP Server. Nothing to install.
mutate_residue is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the mutate_residue 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 mutate_residue. 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.
mutate_residue is provided by the ChimeraX MCP Server MCP server (mahynotch/chimerax-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 →