mcpHosted AI, explicit consent

Dry run skill

tools/call

Simulate what an agent would do without executing any side effects. Returns the LLM's plan, intended tool calls, model used, and token usage. No DB writes, no LinkedIn sends. Use to vet a skill before turning autonomy up.

Parameters

workspaceId

string

Optional workspace ID or slug. Required when this credential can access multiple workspaces and no workspace was configured on the client.

agentRolerequired

string

No description.

skillIds

string[]

Optional. Skill IDs to consider; omit to let the agent pick.

userMessage

string

Optional free-text instruction for the agent.

allowHostedAi

boolean

Must be true when this operation uses Pipeline hosted inference.

Example

MCP tools/calljson

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "dry-run-skill",
    "arguments": {
      "agentRole": "scout",
      "allowHostedAi": true
    }
  }
}

Response

The operation is available, but its typed response schema has not been published yet.

JSON-RPC errors

-32602: Invalid parameters. Field-level details are returned in the JSON-RPC error data.
-32001: Authentication or hosted AI consent is required.
-32003: Workspace access is denied.
-32029: The request was rate limited.