MCP Research Router
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_LLM_MODEL | No | LLM model name | Qwen/Qwen2.5-7B-Instruct |
| MCP_SERVER_URL | No | MCP server URL | |
| MCP_LLM_API_KEY | No | LLM API key | |
| MCP_LLM_ENABLED | No | Whether to enable LLM recommendation (true/false) | false |
| MCP_LLM_TIMEOUT | No | LLM timeout in milliseconds | 90000 |
| MCP_SERVER_NAME | No | MCP server name (prefix for tool names) | default |
| MCP_LLM_BASE_URL | No | LLM base URL | https://api.siliconflow.cn/v1 |
| MCP_PROMPTS_PATH | No | Custom prompts directory path | package internal prompts directory |
| MCP_MAX_ITERATIONS | No | Maximum number of iterations | 3 |
| MCP_MIN_CONFIDENCE | No | Minimum confidence | 0.7 |
| MCP_SERVER_ENABLED | No | Whether to enable MCP server (true/false) | false |
| MCP_SERVER_HEADERS | No | MCP server request headers in JSON format, e.g. {"Authorization": "Bearer token"} | {} |
| MCP_MAX_RECOMMENDATIONS | No | Maximum number of recommendations | 5 |
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 |
|---|---|
| get_tool_listA | 获取研究可用的所有工具列表,或根据用户查询智能推荐最合适的工具并提供研究策略指导。 两种使用模式: 模式1:获取所有工具
模式2:智能工具推荐(推荐)
参数说明:
返回内容: 模式1(获取所有工具):
模式2(智能推荐):
重要说明:
智能推荐约束:
示例: 获取所有工具:{"name": "get_tool_list"} 智能推荐:{"user_query": "搜索人工智能的最新新闻"} 深度研究:{"user_query": "分析人工智能在医疗领域的最新进展", "prompt_mode": "deep_research", "max_tools": 5} 自定义模式:{"user_query": "搜索新闻", "prompt_mode": "news_mode"} |
| execute_toolsA | 执行从远程MCP服务器获取的工具(支持单个或批量并行执行)。 重要约束:
如何区分:
使用方式: 方式1:执行单个工具 {"tool_name": "server_name-tool_name", "arguments": {"参数名": "参数值"}} 方式2:批量并行执行多个工具(推荐,3-5倍速度提升){"tools": [{"tool_name": "server_name-tool_name", "arguments": {...}}, {"tool_name": "server_name-tool_name", "arguments": {...}}]} 性能优势: 当需要执行多个工具时,使用批量模式可以并行执行,提供3-5倍速度提升。所有工具同时执行,无需等待。 适用场景:
注意事项:
|
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 2 tools
The two tools have completely distinct purposes: one lists/discover tools, the other executes them. No overlap or ambiguity.
Both tool names follow a consistent verb_noun snake_case pattern: execute_tools and get_tool_list.
Only two tools, which is minimal but functional for a meta-server that primarily discovers and executes tools from other servers.
Covers the essential functionalities of a research router: tool discovery and execution. No obvious gaps.