Attach every registered tool to *mcp* via mcp.tool(). Calling :meth:apply multiple times with the same server is a no-op on subsequent calls; calling it with a different server registers everything against that server too (useful for tests that spin up isolated :class:FastMCP instances). *middlew...
AI agents invoke apply to trigger actions in Repowise. 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 registers/attaches tools to an MCP server instance, triggering external registration operations with side effects on the server state. It's not a simple read, and it modifies runtime behavior by binding tool functions. The description is somewhat meta/infrastructural but describes an operation that executes registrations against a live server.
From the tool's definition 'Attach every registered tool to *mcp* via mcp.tool()' and 'registers everything against that server'
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access apply gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Repowise, and nothing reaches the server without passing your rules. This is the rule we recommend for apply:
{
"version": "1",
"default": "deny",
"tools": {
"apply": {
"limits": [
{
"counter": "apply_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}apply 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.
Attach every registered tool to *mcp* via mcp.tool(). Calling :meth:apply multiple times with the same server is a no-op on subsequent calls; calling it with a different server registers everything against that server too (useful for tests that spin up isolated :class:FastMCP instances). *middleware*, when given, wraps each tool function before registration — the server passes its savings instrumentation in this way so the registry stays decoupled from it. A signature- preserving wrapper is the caller's responsibility (FastMCP reads each tool's signature to build its schema). Defaults to identity. It is categorised as a Execute tool in the Repowise MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Repowise MCP server in PolicyLayer and add a rule for apply: 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 Repowise. Nothing to install.
apply 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 apply 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 apply. 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.
apply is provided by the Repowise MCP server (repowise-dev/repowise). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 19 Repowise tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
19 Repowise tools catalogued and risk-classified — across an index of 42,500+ MCP servers.