Execute a capability call against a chosen provider with typed inputs. WRITE tool when the capability's category ends in '.write' (creates state, sends notifications, charges money, etc.) — confirm with the user before calling for any non-reversible capability. Read capabilities (category ending ...
Risk signalsBulk/mass operation — affects multiple targets
Part of the Whatcanido — MCP Server for Service Businesses server.
Free to start. No card required.
AI agents invoke invoke_capability to trigger processes or run actions in Whatcanido — MCP Server for Service Businesses. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
invoke_capability can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"invoke_capability": {
"limits": [
{
"counter": "invoke_capability_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Whatcanido — MCP Server for Service Businesses policy for all 10 tools.
These attack patterns abuse exactly the kind of access invoke_capability gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Execute a capability call against a chosen provider with typed inputs. WRITE tool when the capability's category ends in '.write' (creates state, sends notifications, charges money, etc.) — confirm with the user before calling for any non-reversible capability. Read capabilities (category ending '.read') are safe to call without confirmation. Validates inputs against the capability's JSON Schema. On failure, returns a structured error with 'missing_fields' or schema violation detail so you can repair without round-tripping. Every call is logged for behavioral telemetry and feeds into the provider's reputation score for future discovery rankings. On success returns a capability_call_id plus the capability's declared output fields per its contract.. It is categorised as a Execute tool in the Whatcanido — MCP Server for Service Businesses MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Whatcanido — MCP Server for Service Businesses MCP server in PolicyLayer and add a rule for invoke_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 Whatcanido — MCP Server for Service Businesses. Nothing to install.
invoke_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 invoke_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 invoke_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.
invoke_capability is provided by the Whatcanido — MCP Server for Service Businesses MCP server (https://whatcanido.dev/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 Whatcanido — MCP Server for Service Businesses tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.