growsurf_agent_program_creation_eval

Generate one-shot GrowSurf program-creation eval prompts and acceptance checks for agent steering: starter content review, conservative rewards, configuration review, and frontend install proof.

SERVERGrowSurf SOURCE@growsurfteam/growsurf-mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/com-growsurf-growsurf/growsurf-agent-program-creation-eval.md

WHAT IT DOES

What growsurf_agent_program_creation_eval does on GrowSurf

AI agents use growsurf_agent_program_creation_eval to create or update resources in GrowSurf, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GrowSurf environment.

RISK

Why growsurf_agent_program_creation_eval is rated Medium

An AI agent can call growsurf_agent_program_creation_eval faster than any human can review: one bad instruction and it creates or modifies resources in GrowSurf by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs growsurf_agent_program_creation_eval safely

PolicyLayer is an MCP gateway: it sits between your AI agents and GrowSurf, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For growsurf_agent_program_creation_eval, this is the rule to start with:

growsurf_agent_program_creation_eval Rate-limited

growsurf_agent_program_creation_eval stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "growsurf_agent_program_creation_eval": {
      "limits": [
        {
          "counter": "growsurf_agent_program_creation_eval_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect GrowSurf, apply this rule, and every growsurf_agent_program_creation_eval call is checked against it from then on.

FAQ

Questions about growsurf_agent_program_creation_eval

What does the growsurf_agent_program_creation_eval tool do? +

Generate one-shot GrowSurf program-creation eval prompts and acceptance checks for agent steering: starter content review, conservative rewards, configuration review, and frontend install proof. It is categorised as a Write tool in the GrowSurf MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on growsurf_agent_program_creation_eval? +

Register the GrowSurf MCP server in PolicyLayer and add a rule for growsurf_agent_program_creation_eval: 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 GrowSurf. Nothing to install.

What risk level is growsurf_agent_program_creation_eval? +

growsurf_agent_program_creation_eval is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit growsurf_agent_program_creation_eval? +

Yes. Add a rate_limit block to the growsurf_agent_program_creation_eval 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.

How do I block growsurf_agent_program_creation_eval completely? +

Set action: deny in the PolicyLayer policy for growsurf_agent_program_creation_eval. 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.

What MCP server provides growsurf_agent_program_creation_eval? +

growsurf_agent_program_creation_eval is provided by the GrowSurf MCP server (@growsurfteam/growsurf-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on GrowSurf, and thousands of servers like it.

This server

All 52 GrowSurf tools →

Across the catalogue

team_manager_kill_agent on Team Manager MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →