Run Bloom behavioral evaluation on a model.
AI agents invoke bloom_evaluate_model to trigger actions in Msty Admin MCP. 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 behavioral evaluation workflow on a model, which is an active operation with side effects (e.g., generating evaluation logs, consuming computational resources, potentially modifying model state or outputs). While not destructive or financial, it is clearly an Execute category tool because it runs a non-trivial process whose outcomes depend on runtime arguments.
From the tool's definition Tool description states 'Run Bloom behavioral evaluation on a model' — the verb 'Run' indicates active execution of an evaluation process, not mere retrieval or inspection.
Documented attack patterns abuse exactly the kind of access bloom_evaluate_model gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Msty Admin MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for bloom_evaluate_model:
{
"version": "1",
"default": "deny",
"tools": {
"bloom_evaluate_model": {
"limits": [
{
"counter": "bloom_evaluate_model_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}bloom_evaluate_model 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 Bloom behavioral evaluation on a model. It is categorised as a Execute tool in the Msty Admin MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Msty Admin MCP server in PolicyLayer and add a rule for bloom_evaluate_model: 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 Msty Admin MCP. Nothing to install.
bloom_evaluate_model 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 bloom_evaluate_model 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 bloom_evaluate_model. 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.
bloom_evaluate_model is provided by the Msty Admin MCP server (m-pineapple/msty-admin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Msty Admin MCP, 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.
36 Msty Admin MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.