Thinking Agent MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SILICONFLOW_MODEL | No | Model name to use | deepseek-ai/DeepSeek-V4-Flash |
| SILICONFLOW_API_KEY | Yes | Your SiliconFlow API key | |
| SILICONFLOW_BASE_URL | No | Base URL for SiliconFlow API | https://api.siliconflow.cn/v1 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| chat_agentA | 调用独立、非思考模式的模型生成文本，用于延伸当前思维链。你可以传入任何需要独立完成且不受对话历史影响的子任务，包括但不限于：逻辑推理、发散联想、创意生成、优缺点分析、情景假设、步骤拆解、知识类比与迁移等。请确保 input_text 是一个完整、自包含的任务描述，明确任务类型与目标。通过调整 temperature（0 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion between tools. The tool's purpose is clearly described.
With a single tool, naming consistency is trivially maintained. The snake_case format is acceptable.
The server has only one tool, which is at the lower end of reasonable scope. While a single general-purpose tool can be useful, it feels thin for a server named 'Thinking Agent MCP'.
The tool surface is severely incomplete for a thinking agent server. It only provides text generation without any supporting tools for memory, planning, or verification.