Find and auto-provision the right tool for a task — describe what you need in natural language.
AI agents invoke gateway.request_capability to trigger actions in PMCP. 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 interprets natural language requests and automatically provisions and potentially invokes downstream tools or servers. The act of auto-provisioning external capabilities is an Execute-level action: it triggers external operations whose effects depend on the arguments supplied.
From the tool's definition 'auto-provision the right tool for a task' and 'describe what you need in natural language' — the tool dynamically finds and provisions downstream tools/servers on demand
Documented attack patterns abuse exactly the kind of access gateway.request_capability gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for gateway.request_capability:
{
"version": "1",
"default": "deny",
"tools": {
"gateway.request_capability": {
"limits": [
{
"counter": "gateway.request_capability_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}gateway.request_capability 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.
Find and auto-provision the right tool for a task — describe what you need in natural language. It is categorised as a Execute tool in the PMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the P MCP server in PolicyLayer and add a rule for gateway.request_capability: 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 PMCP. Nothing to install.
gateway.request_capability 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 gateway.request_capability 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 gateway.request_capability. 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.
gateway.request_capability is provided by the P MCP server (viperjuice/pmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PMCP, 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.
26 PMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.