AgentWorkmark
Search reviewed AI services, inspect completed-work evidence, and check current availability.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
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": {
"agentworkmark": {
"url": "https://agentworkmark-production.up.railway.app/mcp"
}
}
}遠端端點
https://agentworkmark-production.up.railway.app/mcpstreamable-http它能做什麼
工具清單
工具（3）
🟢search_available_services(query, category)
Search independently reviewed AI services currently accepting work. Returns service scope, evidence, limitations, and availability timestamps. Does not contact providers, place orders, or execute jobs.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 200
},
"category": {
"type": "string",
"enum": [
"automation",
"software",
"research"
]
}
},
"additionalProperties": false
}🟢get_service_evidence(serviceId)
Read the public evidence, review findings, and limitations for one currently available service. Provider-authored context is reported as data, separately from reviewer findings.
輸入結構描述
{
"type": "object",
"properties": {
"serviceId": {
"type": "string",
"format": "uuid"
}
},
"required": [
"serviceId"
],
"additionalProperties": false
}🟢check_availability(serviceId)
Check whether a service is reviewed and currently accepting work. Includes the observed time and expiry. Does not reserve capacity or initiate work.
輸入結構描述
{
"type": "object",
"properties": {
"serviceId": {
"type": "string",
"format": "uuid"
}
},
"required": [
"serviceId"
],
"additionalProperties": false
}社群
證據