Skip to main content
Glama
SpiritHerb

MCP Research Router

by SpiritHerb
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
JavaScript
Hybrid

MCP Research Router

📖 引言

你是否遇到过这些问题？

  • 有多个 MCP 服务器，每次都要逐个添加到客户端，很麻烦？

  • 工具太多，不知道该用哪个？

  • 需要同时调用多个工具，但只能一个一个来？

MCP Research Router 就是为你准备的。

它是一个 MCP 聚合器和智能路由器，帮你：

  • ✅ 一次连接，访问所有 MCP 服务器

  • ✅ 自动推荐最适合的工具

  • ✅ 批量并行执行，性能提升 3-5 倍

Related MCP server: MCP Gateway

🎯 这个工具适合你吗？

✅ 适合使用

  • 有多个 MCP 服务器需要统一管理

  • 工具数量多，不知道该用哪个

  • 需要批量调用多个工具

  • 想通过 LLM 智能推荐工具

❌ 不适合使用

  • 只有一个 MCP 服务器

  • 工具数量少，能直接选择

  • 不需要智能推荐功能

如果你的客户端已经支持添加多个 MCP，并且你只有少量工具，那么你不需要这个工具。

⚡ 特点

1. 统一管理多个 MCP 服务器

聚合多个 MCP 服务器，一次连接即可访问所有工具。无需在每个客户端中逐个添加。

2. 智能工具推荐

根据你的需求，通过 LLM 自动推荐最合适的工具。不用再翻阅长长的工具列表。

3. 批量并行执行

同时调用多个相关工具，性能提升 3-5 倍。适合需要综合多个工具结果的场景。

🚀 快速开始

1. 安装

npm install -g mcp-research-router
# 或直接运行
npx mcp-research-router

2. 配置

推荐：使用环境变量

在 MCP 客户端中添加环境变量：

MCP_LLM_ENABLED=true
MCP_LLM_API_KEY=your-api-key-here
MCP_LLM_BASE_URL=https://open.bigmodel.cn/api/paas/v4
MCP_LLM_MODEL=glm-4.7-flash
MCP_SERVER_URL=http://127.0.0.1:3000/mcp/your-group-id

3. 连接到客户端

编辑配置文件（适用于 Claude Desktop、Cursor 等支持 MCP 的客户端）：

  • Claude Desktop:

    • Windows: %APPDATA%\Claude\claude_desktop_config.json

    • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Cursor:

    • Windows: %APPDATA%\Cursor\User\globalStorage\mcp_settings.json

    • Mac: ~/Library/Application Support/Cursor/User/globalStorage/mcp_settings.json

最小配置（仅连接服务）：

{
  "mcpServers": {
    "mcp-research-router": {
      "command": "npx",
      "args": ["mcp-research-router"]
    }
  }
}

包含环境变量：

{
  "mcpServers": {
    "mcp-research-router": {
      "command": "npx",
      "args": ["mcp-research-router"],
      "env": {
        "MCP_LLM_ENABLED": "true",
        "MCP_LLM_BASE_URL": "https://ark.cn-beijing.volces.com/api/coding/v3",
        "MCP_LLM_API_KEY": "your-api-key-here",
        "MCP_LLM_MODEL": "ark-code-latest",
        "MCP_SERVER_ENABLED": "true",
        "MCP_SERVER_URL": "http://your-server-url/mcp/endpoint",
        "MCP_SERVER_NAME": "my-server",
        "MCP_SERVER_HEADERS": "{\"Authorization\": \"Bearer your-token\"}"
      }
    }
  }
}

📖 使用方法

获取工具列表

{
  "name": "get_tool_list"
}

智能工具推荐

{
  "name": "get_tool_list",
  "arguments": {
    "user_query": "搜索关于人工智能的最新新闻",
    "max_tools": 3
  }
}

系统会根据你的需求推荐最合适的工具。

批量执行工具

{
  "name": "execute_tools",
  "arguments": {
    "tools": [
      {
        "tool_name": "server-name-metaso-metaso_web_search",
        "arguments": {"q": "人工智能最新发展"}
      }
    ]
  }
}

⚙️ 配置说明

环境变量（推荐）

环境变量

说明

默认值

MCP_LLM_ENABLED

是否启用 LLM 推荐

false

MCP_LLM_API_KEY

LLM API 密钥

-

MCP_LLM_BASE_URL

LLM 基础 URL

https://api.siliconflow.cn/v1

MCP_LLM_MODEL

LLM 模型名称

Qwen/Qwen2.5-7B-Instruct

MCP_LLM_TIMEOUT

LLM 调用超时时间（毫秒）

90000

MCP_SERVER_ENABLED

是否启用 MCP 服务器

false

MCP_SERVER_URL

MCP 服务器 URL

-

MCP_SERVER_NAME

MCP 服务器名称（工具名前缀）

default

MCP_SERVER_HEADERS

MCP 服务器请求头（JSON 格式）

{}

MCP_PROMPTS_PATH

自定义提示词目录路径

包内 prompts 目录

MCP_MAX_RECOMMENDATIONS

最大推荐数

5

MCP_MAX_ITERATIONS

最大迭代次数

3

MCP_MIN_CONFIDENCE

最小置信度

0.7

MCP_SERVER_HEADERS 使用方法

需要填写 JSON 格式的字符串：

MCP_SERVER_HEADERS={"Authorization": "Bearer your-token"}

示例：

  • Bearer Token 认证：{"Authorization": "Bearer your-token"}

  • API Key 认证：{"X-API-Key": "your-api-key"}

  • 多个请求头：{"Authorization": "Bearer your-token", "X-Custom-Header": "value"}

配置文件方式

如果需要使用配置文件，编辑 config.json：

{
  "subAgent": {
    "enabled": true,
    "type": "openai",
    "baseUrl": "https://open.bigmodel.cn/api/paas/v4",
    "apiKey": "your-api-key-here",
    "model": "glm-4.7-flash",
    "timeout": 90000
  },
  "mcpServers": {
    "enabled": true,
    "servers": [
      {
        "name": "my-favorites",
        "type": "streamable-http",
        "url": "http://127.0.0.1:3000/mcp/your-group-id"
      }
    ]
  }
}

完整配置示例请参考 config.full.example.json。

🎨 提示词模式

系统支持多种提示词模式，你可以根据需求选择：

预定义模式

  • tool_recommendation（默认）：快速工具推荐

  • deep_research：深度研究模式，适合复杂任务

自定义模式

在 prompts/ 文件夹中创建新文件夹：

prompts/
└── my_mode/
    ├── system.txt
    └── user.txt

使用时传入 prompt_mode: "my_mode"。

详细说明请查看 prompts/README.md。

❓ 常见问题

Q: 如何配置 MCPHub 分组？

  1. 在 MCPHub 网页端创建分组

  2. 添加常用的 MCP 服务器到分组

  3. 复制分组 ID

  4. 配置环境变量：MCP_SERVER_URL=http://127.0.0.1:3000/mcp/分组ID

⚠️ 不要把 MCP Research Router 自己添加到分组里，否则会无限套娃。

Q: 不配置 LLM 能使用吗？

可以，但功能受限：

  • ✅ 可以获取工具列表

  • ✅ 可以执行工具

  • ❌ 无法使用智能推荐功能

🛠️ 开发

# 安装依赖
pnpm install

# 开发模式（支持热重载）
pnpm dev

# 构建
pnpm build

# 运行
pnpm start

📄 许可证

MIT

🙏 赞赏

如果你觉得这个项目对你有帮助，欢迎通过微信赞赏支持我的开发工作：

🔗 相关链接

Available Tools

2 tools
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：

  • 此工具只能执行从远程MCP服务器获取的工具，工具名称格式为"server_name-tool_name"

  • 不能执行用户直接添加到MCP客户端的其他工具

  • 如果工具名称不是"server_name-tool_name"格式，说明该工具应该直接调用，不要通过此工具执行

如何区分：

  • 工具名称包含 "-" 且格式为 "server_name-tool_name" 则通过此工具执行

  • 工具名称不包含 "-" 或不是 "server_name-tool_name" 格式则直接调用

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：

  • 单个工具执行：使用方式1

  • 多个工具（无依赖）：使用方式2批量并行执行

  • 多个工具（有依赖）：使用方式1顺序执行

注意事项：

  • 只能执行格式为 "server_name-tool_name" 的工具

  • 批量执行时，所有工具并行执行，互不等待

  • 如果工具之间有依赖关系，请使用方式1逐个执行

ParametersJSON Schema
NameRequiredDescriptionDefault
tool_nameNo单个工具的名称，格式为"server_name-tool_name"（与tools参数二选一）
argumentsNo传递给单个工具的参数
toolsNo批量执行的工具数组（与tool_name参数二选一）

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so description carries full burden. It discloses key behaviors: only for remote tools, batch is parallel with 3-5x speedup, sequential for dependent tools. Does not cover error handling or synchronization details, but sufficiently explains core traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-organized with headers, bullet points, and clear sections. It is thorough but each sentence contributes useful information. A slight reduction due to length, but efficient for the content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description provides complete context: purpose, constraints, usage methods, performance benefits, and scenario recommendations. It distinguishes from the sibling and covers critical usage aspects comprehensively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and descriptions are already good. The description adds value by explaining the naming format 'server_name-tool_name' and clarifying mutual exclusivity between 'tool_name' and 'tools' parameters, beyond what schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Execute tools obtained from remote MCP servers' with a specific verb and resource. It distinguishes from sibling tool 'get_tool_list' by focusing on execution rather than listing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance on when to use this tool vs. direct invocation, based on the naming convention 'server_name-tool_name'. Also details usage modes for single, batch parallel, or sequential execution with clear applicability to dependency scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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

  • 直接调用，不传任何参数

  • 返回所有可用工具的完整列表

  • 用于了解系统中有哪些工具可用

模式2：智能工具推荐（推荐）

  • 传入 user_query 参数

  • 系统会根据查询内容智能推荐最合适的工具

  • 返回推荐工具列表、参数建议和研究策略

  • 适用于需要搜索、研究或查询的场景

参数说明：

  • user_query（可选，推荐模式必需）：用户的研究查询或问题

  • max_tools（可选）：推荐的最大工具数量，默认 5

  • max_iterations（可选）：最大搜索迭代次数，默认 3

  • prompt_mode（可选）：提示词模式，接受任何字符串值。预定义模式包括 tool_recommendation（默认，快速推荐）和 deep_research（深度研究）。用户也可以在 prompts/ 文件夹中创建自定义提示词模式，文件夹名称即为模式名称

返回内容： 模式1（获取所有工具）：

  • tools：所有工具的完整列表

  • total：工具总数

模式2（智能推荐）：

  • selected_tools：推荐的工具列表，包含工具名、参数建议和使用理由

  • research_strategy 或 research_plan：研究策略和执行计划

  • 执行指南：如何使用推荐的工具

重要说明：

  • 推荐的工具必须通过 execute_tools 工具执行

  • 推荐多个工具时，使用 execute_tools 的批量模式（tools 参数）并行执行以获得 3-5倍加速

  • 仅在工具之间存在依赖关系时使用单个模式（tool_name 参数）顺序执行

智能推荐约束：

  • LLM 必须返回有效的 JSON 格式

  • tool_name 必须是工具列表中存在的完整工具名（格式为 server_name-tool_name）

  • suggested_params 中的参数名必须严格匹配工具的 input_schema 定义

  • 必须包含 selection_reason 说明选择理由

  • 参数值必须符合 input_schema 中定义的类型和约束

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"}

ParametersJSON Schema
NameRequiredDescriptionDefault
user_queryNo用户的研究查询或问题（可选，传入则启用智能推荐）
max_toolsNo推荐的最大工具数量（默认：5）
max_iterationsNo最大搜索迭代次数（默认：3）
prompt_modeNo提示词模式：tool_recommendation（默认，快速推荐）、deep_research（深度研究）或用户自定义模式名称。用户可以在 prompts/ 文件夹中创建自定义提示词模式，文件夹名称即为模式名称tool_recommendation

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the tool's behavior: it returns lists or recommendations, includes constraints on JSON format, exact tool names, and parameter matching. It also mentions performance benefits of batch execution. However, it does not explicitly state side effects (none expected for a read tool) or authentication needs, but that is acceptable for an informational tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-organized with headings, bullet points, and examples. Every section adds necessary information. It could be slightly more concise by merging some redundant explanations, but the structure aids readability and completeness. The front-loaded summary of modes is effective.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (two modes, four parameters, custom prompt modes) and lack of output schema, the description adequately covers return values for both modes, usage constraints, and integration with 'execute_tools'. It is thorough enough for an agent to use the tool correctly without additional context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description adds substantial value beyond the schema. It explains optionality, default values, and the custom prompt mode feature (e.g., creating prompt files in 'prompts/' folder). It also provides concrete examples demonstrating different parameter combinations, which helps the agent understand usage patterns.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's dual purpose: listing all available tools or intelligently recommending tools based on a query. It distinguishes two modes and specifies the resource ('工具列表'). The verb 'get' and resource are explicit, and it differentiates from the sibling tool 'execute_tools' by stating that execution should be done via that tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use each mode: mode 1 for simply listing tools, mode 2 for research/query scenarios. It also instructs to use 'execute_tools' for execution, recommends batch mode for multiple tools, and warns against sequential execution without dependencies. This leaves no ambiguity about when to invoke this tool versus alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updatesv1.0.14
    • First observedexecute_tools
    • First observedget_tool_list
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.6/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have completely distinct purposes: one lists/discover tools, the other executes them. No overlap or ambiguity.

Naming Consistency5/5

Both tool names follow a consistent verb_noun snake_case pattern: execute_tools and get_tool_list.

Tool Count3/5

Only two tools, which is minimal but functional for a meta-server that primarily discovers and executes tools from other servers.

Completeness5/5

Covers the essential functionalities of a research router: tool discovery and execution. No obvious gaps.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Master MCP Server

    Jakedismo
    F
    license
    Not graded
    quality
    Not graded
    maintenance
    Aggregates multiple MCP servers behind a single, secure endpoint with unified tool/resource discovery, OAuth authentication, and resilient request routing. Enables users to manage and interact with multiple MCP backends through one centralized interface with load balancing and circuit breakers.
    2
    -

  • MCP Gateway

    abdullah1854
    A
    license
    Not graded
    quality
    C
    maintenance
    A universal gateway that aggregates multiple MCP servers into a single interface while providing advanced token optimization, result filtering, and automated summarization. It enables efficient management of large tool catalogs and reduces context usage by up to 95% for major AI clients.
    19
    15
    MIT

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SpiritHerb/mcp-research-router'

If you have feedback or need assistance with the MCP directory API, please join our Discord server