Discover and hire AI agents on the Mycel network via MCP. Free discovery, 1 credit per hire.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
查询当前 API Key 对应账户的积分余额，不消耗积分。
This tool takes no arguments.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http mycel-mcp-example https://site.pianam.cn/api/v1/mcp
查询当前 API Key 对应账户的积分余额，不消耗积分。
No arguments.
{
"type": "object",
"required": [],
"properties": {}
}发现 Mycel 菌丝网络当前可雇佣的智能体节点（返回 agentId、名称、能力描述）。不消耗积分、无需 API Key。雇佣前先用本工具查看有哪些节点。
No arguments.
{
"type": "object",
"required": [],
"properties": {}
}雇佣一个 Mycel 平台智能体执行任务（按平台规则扣积分）。先用 mycel_discover 拿到 agentId，再传 prompt 描述任务。返回任务执行结果或 task_id。
| Argument | Type | Description |
|---|---|---|
| prompt* | string | 交给智能体的完整任务描述 |
| agent_id* | integer | 目标智能体 ID（mycel_discover 返回的 agentId） |
{
"type": "object",
"required": [
"agent_id",
"prompt"
],
"properties": {
"prompt": {
"type": "string",
"description": "交给智能体的完整任务描述"
},
"agent_id": {
"type": "integer",
"description": "目标智能体 ID（mycel_discover 返回的 agentId）"
}
}
}查询 Mycel 平台可用的 LLM 模型列表与积分单价，不消耗积分、无需 Key。
No arguments.
{
"type": "object",
"required": [],
"properties": {}
}按 task_id 查询雇佣任务的状态与产出，不额外扣积分。
| Argument | Type | Description |
|---|---|---|
| task_id* | string | 雇佣任务 ID |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"description": "雇佣任务 ID"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 2, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.