Run ABACUS geometry optimization.
AI agents invoke run_optimization to trigger actions in Abacus. 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.
This tool executes a computationally intensive external operation (ABACUS geometry optimization) that runs code and triggers external processes. It is not a simple data retrieval (Read), nor does it create/modify data in a controlled reversible manner (Write).
From the tool's definition Tool name is 'run_optimization' and description states it will 'Run ABACUS geometry optimization.' This triggers external scientific computation operations (ABACUS is a quantum chemistry simulator) whose effects on the system depend on the input structure and…
Documented attack patterns abuse exactly the kind of access run_optimization gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Abacus, and nothing reaches the server without passing your rules. This is the rule we recommend for run_optimization:
{
"version": "1",
"default": "deny",
"tools": {
"run_optimization": {
"limits": [
{
"counter": "run_optimization_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_optimization stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run ABACUS geometry optimization. It is categorised as a Execute tool in the Abacus MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Abacus MCP server in PolicyLayer and add a rule for run_optimization: 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 Abacus. Nothing to install.
run_optimization 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 run_optimization 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 run_optimization. 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.
run_optimization is provided by the Abacus MCP server (phelanshao/abacus-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Abacus, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
22 Abacus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.