Skip to main content
Glama
Prism-Future

Cherry Studio Knowledge Base MCP Server

by Prism-Future
OverviewSchemaRelated ServersScoreDiscussions
Remote

Cherry Studio Knowledge Base MCP Server

一行配置，即刻使用。 让 Claude、Cursor 等 AI 助手直接读取你的 Cherry Studio 知识库。

One-line config, ready to use. Let Claude, Cursor, and other AI assistants read your Cherry Studio knowledge bases directly.

客户端兼容性 / Client Compatibility

客户端 / Client

状态 / Status

备注 / Notes

✅ Codex

已验证可用

—

✅ WorkBuddy

已验证可用

—

⚠️ LobeHub

可能无法使用

已知兼容性问题 / Known compatibility issues

你的客户端不在这个列表？欢迎提交 Issue 反馈使用体验！
Your client not listed? Feel free to open an issue with your experience!

Related MCP server: Open WebUI Knowledge Base MCP Server

使用方法 / Usage

方式一：npx 直接运行（推荐，无需安装）/ Method 1: npx (Recommended, No Installation)

打开你的 AI 客户端配置（Claude Desktop / Cursor 等），粘贴以下 JSON：

Open your AI client config (Claude Desktop / Cursor, etc.), paste this JSON:

{
  "mcpServers": {
    "cherrystudio-knowledgebase": {
      "command": "npx",
      "args": ["-y", "cherrystudio-knowledgebase-mcp"],
      "env": {
        "CHERRYSTUDIO_API_BASE_URL": "http://127.0.0.1:23333",
        "CHERRYSTUDIO_API_KEY": "cs-sk-your-api-key-here"
      }
    }
  }
}

只需替换 cs-sk-your-api-key-here 为你的真实 API Key，保存后重启客户端即可。

Just replace cs-sk-your-api-key-here with your real API Key, save and restart your client.

获取 API Key：在 Cherry Studio 中打开设置，找到 API 密钥并复制。 Get API Key: Open Cherry Studio settings, find and copy the API key.

方式二：本地克隆运行 / Method 2: Clone and Run Locally

git clone https://github.com/Prism-Future/cherrystudio-knowledgebase-mcp.git
cd cherrystudio-knowledgebase-mcp
npm install
npm run build

然后使用本地路径配置：/ Then configure with local path:

{
  "mcpServers": {
    "cherrystudio-knowledgebase": {
      "command": "node",
      "args": ["path/to/cherrystudio-knowledgebase-mcp/dist/index.js"],
      "env": {
        "CHERRYSTUDIO_API_BASE_URL": "http://127.0.0.1:23333",
        "CHERRYSTUDIO_API_KEY": "cs-sk-your-api-key-here"
      }
    }
  }
}

方式三：JSON 配置文件 / Method 3: JSON Config File

如果你不想把 API Key 写在客户端配置里，可以创建一个独立的 JSON 配置文件：

If you don't want to put the API Key in the client config, create a standalone JSON config file:

# 创建配置文件 / Create config file
echo '{"cherryStudioApiKey":"cs-sk-your-api-key-here"}' > config.json

然后客户端配置里不需要写 env：/ Then the client config doesn't need env:

{
  "mcpServers": {
    "cherrystudio-knowledgebase": {
      "command": "npx",
      "args": ["-y", "cherrystudio-knowledgebase-mcp"]
    }
  }
}

配置文件支持放在以下位置（优先级由高到低）：/ Config file can be placed at (priority from high to low):

  1. config.json in project root

  2. ~/.config/cherrystudio-kb-mcp/config.json

完整配置示例见 config.example.json。/ See config.example.json for full example.

前置要求 / Prerequisites

  • Node.js 18+

  • Cherry Studio（已启动并运行 / Running）

  • Cherry Studio API 已启用且知道 API Key / API enabled and you have the API Key

功能 / Features

工具 / Tool

功能 / Function

listKnowledgeBases

列出所有知识库 / List all knowledge bases

searchKnowledgeBases

搜索知识库内容 / Search knowledge bases

getKnowledgeBase

获取知识库详情 / Get knowledge base details

getMcpServers

列出已配置的 MCP 服务器 / List configured MCP servers

常见问题 / FAQ

Q: API Key 在哪里获取？/ Where to get the API Key?

A: 在 Cherry Studio 设置中找到 API 密钥并复制。/ Find and copy the API key in Cherry Studio settings.

Q: Cherry Studio API 地址是什么？/ What is the API address?

A: 默认是 http://127.0.0.1:23333，请确保 Cherry Studio 正在运行。/ Default is http://127.0.0.1:23333, make sure Cherry Studio is running.

Q: 支持哪些客户端？/ Which clients are supported?

A: 任何支持 MCP 协议的客户端，如 Claude Desktop、Cursor、Codex 等。/ Any MCP-compatible client: Claude Desktop, Cursor, Codex, etc.

开发 / Development

npm install      # 安装依赖
npm run dev      # 开发模式
npm run build    # 构建
npm run test     # 测试

项目信息 / Project Info

  • 作者 / Author: Prism-Future

  • 许可证 / License: MIT

  • 技术栈 / Tech Stack: TypeScript, Node.js, MCP SDK, Zod, Axios

相关链接 / Links

Available Tools

4 tools
getKnowledgeBaseA

Get details of a specific knowledge base by ID

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesThe ID of the knowledge base to retrieve

TDQS

A3.8/5.0
Behavior3/5

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

No annotations are provided, so the description must convey behavior. 'Get details' clearly indicates a read operation, but it does not mention error behavior, authentication, or any other side effects. For a simple retrieval, this is minimally adequate, but lacks depth.

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

Conciseness5/5

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

The description is a single, front-loaded sentence that immediately conveys the action and scope. Every word earns its place, with no fluff or repetition.

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 simplicity of the tool (one parameter, no output schema), the description is sufficient for an agent to know what it does and how to invoke it. However, it lacks explicit guidance on when to use this tool versus its siblings, which is a minor gap.

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

Parameters3/5

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

The input schema covers 100% of the parameter with a clear description ('The ID of the knowledge base to retrieve'). The tool description only repeats 'by ID', adding no additional meaning beyond the schema, so the baseline of 3 applies.

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 uses a specific verb 'Get details' with a clear resource 'knowledge base' and a qualifier 'by ID'. It clearly distinguishes from siblings like listKnowledgeBases (list all) and searchKnowledgeBases (search), and directly states the primary action and target.

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

Usage Guidelines3/5

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

The description implies usage when you know the specific ID, but it does not explicitly mention alternatives or contrast with siblings. There is no 'use this instead of X' guidance, so the agent must infer from context.

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

getMcpServersA

List all MCP servers configured in Cherry Studio

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.2/5.0
Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. The verb 'List' implies a read-only operation, but the description does not explicitly state safety, side effects, or what the output contains. It is not misleading, but it adds minimal behavioral context beyond the name.

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

Conciseness5/5

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

The description is a single concise sentence, front-loaded with the action verb 'List' and the target resource. There is no unnecessary information, making it highly efficient and appropriately structured.

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?

For a simple zero-parameter listing tool, the description is sufficiently complete. There is no output schema, so the description could potentially mention what fields are returned per server, but given the simplicity and clarity of the purpose, this is not a major gap. The tool's domain is clearly established.

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?

The tool has zero parameters, so the description does not need to explain any. Per the rubric, 0 parameters earns a baseline score of 4. The description provides no parameter information, which is appropriate.

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 uses the specific verb 'List' and clearly identifies the resource as 'all MCP servers configured in Cherry Studio'. This distinguishes it from sibling tools, which focus on knowledge bases. The purpose is unambiguous.

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

Usage Guidelines4/5

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

The description clearly implies this tool is for listing MCP servers, and sibling tools are entirely different resources (knowledge bases), so there is no conflict. However, it does not explicitly state when to use this tool over alternatives or provide any exclusions, though none seem necessary here.

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

listKnowledgeBasesA

List all available knowledge bases in Cherry Studio

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.1/5.0
Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It implies a read-only operation by using 'List', but does not explicitly state safety, authentication needs, or return format. For a simple list operation this is minimally adequate, but it adds no context beyond the literal action.

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

Conciseness5/5

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

The description is a single, clear sentence that front-loads the verb and resource. Every word is necessary, with no filler or repetition, achieving optimal conciseness.

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?

This is a simple list tool with no parameters, no output schema, and no annotations. The description fully captures the essential behavior—listing all knowledge bases. Given the low complexity, nothing important is missing; siblings are not required to be mentioned here.

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?

The tool has zero parameters, so the description correctly needs to explain none. The empty input schema is fully covered, and the description adds no parameter-specific details, which is appropriate given there are no parameters. Baseline of 4 applies.

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 uses a specific verb ('List'), a specific resource ('knowledge bases'), and the scope ('all available'), clearly distinguishing it from sibling tools like getKnowledgeBase (singular) and searchKnowledgeBases (filtered). It unambiguously states what the tool does.

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

Usage Guidelines3/5

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

The description provides no explicit guidance on when to use this tool versus alternatives. Usage is implied by the name and sibling tool names, but the description itself does not mention when to choose it over getKnowledgeBase or searchKnowledgeBases, nor does it note any exclusions or prerequisites.

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

searchKnowledgeBasesA

Search across one or more knowledge bases for relevant content

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesThe search query string
documentCountNoMaximum number of documents to return (default: 10, max: 100)
knowledgeBaseIdsNoOptional array of knowledge base IDs to search within

TDQS

A3.6/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action of searching and offers no details about result types, relevance ordering, what happens when no knowledgeBaseIds are given, or any side effects. This is minimal transparency for a tool expected to return content.

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

Conciseness5/5

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

The description is a single, well-formed sentence that communicates the core purpose without any redundancy or filler. It earns its place with zero waste.

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

Completeness2/5

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

With no output schema and no annotations, the description must explain enough about behavior to allow correct usage, but it omits what the returned 'relevant content' looks like, whether the search defaults to all knowledge bases, and any pagination or filtering nuances. This leaves significant gaps for a non-trivial tool.

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

Parameters3/5

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

The input schema has 100% coverage with clear descriptions for all three parameters (query, documentCount, knowledgeBaseIds). The tool description adds no extra meaning beyond what the schema already provides, so the baseline score of 3 is appropriate.

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 uses the specific verb 'search' with the resource 'knowledge bases' and clarifies scope as 'one or more'. This clearly distinguishes it from sibling tools like listKnowledgeBases and getKnowledgeBase, which perform listing and retrieval respectively.

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

Usage Guidelines4/5

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

The description implies this tool is for finding relevant content across one or more knowledge bases, which naturally contrasts with list/get siblings. However, it does not explicitly state when to use it over alternatives or mention possible exclusions, so it falls short of the highest bar.

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. 4 tool updatesv1.0.0
    • First observedgetKnowledgeBase
    • First observedgetMcpServers
    • First observedlistKnowledgeBases
    • First observedsearchKnowledgeBases
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.8/5.0
Disambiguation4/5

Each knowledge base tool is clearly distinct: list, get, and search. However, getMcpServers is an unrelated tool that could confuse the server's purpose, making it slightly less coherent as a set.

Naming Consistency5/5

All tools follow a consistent verb + noun pattern in camelCase (list, get, search), with no mixed conventions or vague verbs.

Tool Count4/5

With 4 tools, the count is within the ideal range, but it feels slightly thin for a knowledge base server that might be expected to support more operations.

Completeness2/5

The knowledge base tools only cover list, get, and search, with no create, update, or delete operations, leaving obvious lifecycle gaps. The inclusion of getMcpServers also distracts from the domain.

Maintenance

ActivitySlowing
ResponsivenessSyncing

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

  • Dify Doc MCP Server

    shellus
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that integrates Dify knowledge bases, enabling AI assistants to retrieve and search content from Dify via tools like list datasets, get dataset details, and knowledge retrieval.
    21
    4
    MIT

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/Prism-Future/CherryStudio-KnowledgeBase-MCP'

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