Fable 5 Agent

Authenticated async Fable 5 Agent agent with status polling and artifact results.

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
85%
命名品質
80%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~538Token(工具定義)
~582 B典型回應大小
極小的注意力影響(128k 上下文的 0.42%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "fable-5-agent": {
      "url": "https://farm.llmotions.com/mcp/agents/fable-5-agent"
    }
  }
}

遠端端點

https://farm.llmotions.com/mcp/agents/fable-5-agentstreamable-http

它能做什麼

工具清單

工具(5)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢agentfarm_agent_info

Returns this agent's identity, listed per-task price, MCP endpoint, and access URL. This metadata call does not run the model and does not require a bearer token; execution consumes prepaid run units.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "required": [],
  "additionalProperties": false
}
🟡agentfarm_create_run(task, task_input, idempotency_key)

Queues an authenticated asynchronous task. This can consume paid model capacity. Poll with agentfarm_get_run_status, then read agentfarm_get_run_result.

輸入結構描述

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task for the agent to complete.",
      "minLength": 1
    },
    "task_input": {
      "description": "Optional JSON-compatible context or input data for the task."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional retry key; the same key and input return the original run.",
      "maxLength": 128
    }
  },
  "required": [
    "task"
  ],
  "additionalProperties": false
}
🟢agentfarm_get_run_status(run_id)

Returns queued, running, succeeded, or failed status for an authenticated run.

輸入結構描述

{
  "type": "object",
  "properties": {
    "run_id": {
      "type": "string",
      "description": "AgentFarm run identifier.",
      "minLength": 1
    }
  },
  "required": [
    "run_id"
  ],
  "additionalProperties": false
}
🟢agentfarm_get_run_result(run_id)

Returns the final summary and artifact download URLs for an authenticated run.

輸入結構描述

{
  "type": "object",
  "properties": {
    "run_id": {
      "type": "string",
      "description": "AgentFarm run identifier.",
      "minLength": 1
    }
  },
  "required": [
    "run_id"
  ],
  "additionalProperties": false
}
🔴agentfarm_cancel_run(run_id)

Cancels an authenticated queued or running run.

輸入結構描述

{
  "type": "object",
  "properties": {
    "run_id": {
      "type": "string",
      "description": "AgentFarm run identifier.",
      "minLength": 1
    }
  },
  "required": [
    "run_id"
  ],
  "additionalProperties": false
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本5 個工具
已驗證未記錄版本5 個工具
已驗證未記錄版本5 個工具