> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/docs/en-us/advanced-basic/agent-workspace/tools-knowledge-skills-mcp.md).

# Built-in Tools, Knowledge Base, Skills, and MCP

These four types of capabilities can all enhance an Agent, but they solve different problems: built-in tools handle common operations, the knowledge base limits retrievable materials, skills provide working methods, and MCP connects external tools and data.

## Differences and combinations

| Capability     | Problems solved                                             | Example                                                                                   |
| -------------- | ----------------------------------------------------------- | ----------------------------------------------------------------------------------------- |
| Built-in tools | What an Agent can do directly in Cherry Studio              | Read and write files, web search, generate images, memory, notifications, scheduled tasks |
| Knowledge base | What private materials can the Agent retrieve               | Product specifications, contract templates, team handbooks                                |
| skills         | What workflow and standards should the Agent follow         | Weekly report format, code review checklist, writing guidelines                           |
| MCP            | Which external tools and resources can the Agent connect to | Databases, browsers, third-party business systems                                         |

Configuration path: left navigation \[Work] → open the Agent menu → \[Edit] → \[Built-in tools].

<figure><img src="/files/15188d6f3f58d161ea98bb083b959eb8aa6b83e6" alt="Agent 编辑窗口中的内置工具分类与开关"><figcaption><p>Only enable the tools needed for the current task; the list will be clearer, and permission requests will be easier to judge.</p></figcaption></figure>

## Built-in tools

Built-in tools are grouped by context, files, multimedia, orchestration, search, and terminal. Common capabilities include:

* \[Generate images]: use the configured image-generation model;
* \[Knowledge base search] and \[Knowledge base management]: appear only after a knowledge base is bound;
* \[Web search] and \[Web scraping]: use the network access capabilities already configured in Cherry Studio;
* \[Memory]: save and retrieve stable information across tasks;
* \[Scheduled tasks] and \[Notifications]: let the Agent manage schedules and send results to a channel;
* \[Task] and \[Workflow]: handle complex tasks with sub-agents or orchestration;
* File and Bash tools: read, create, modify files, and execute commands.

## Knowledge base scope

The knowledge bases selected in \[Knowledge Base] define the Agent's retrieval scope. If none are selected, knowledge base tools will not load; if multiple are selected, the Agent will still work only within those knowledge bases and will not automatically read other repositories.

## skills

Enable already installed skills in \[Skills]. The skill content will enter the Agent's working environment to constrain the process and output. When you need a new skill, you can directly ask the Agent to help find and install it in \[Work]; the manual management path is \[Settings] → \[Skills].

## MCP

First connect to and start the server in \[Settings] → \[MCP], then return to the \[MCP] binding in the Agent edit window. A server that isn't running cannot be enabled; after connecting, the tools it provides will enter the Agent's tool directory and remain subject to the permission mode.

{% hint style="danger" %}
Enabling a tool does not mean approval should be skipped. For file writes, terminal use, external data modifications, and image generation that may incur charges, prefer to keep \[confirm each time]; use looser permissions only for tools with trusted sources and clearly defined risks.
{% endhint %}

## Recommended combination

| Task requires                       | Recommended combination                  | When to add more                                           | Notes                                                            |
| ----------------------------------- | ---------------------------------------- | ---------------------------------------------------------- | ---------------------------------------------------------------- |
| Process local files                 | File tools + dedicated working directory | Add skills when a fixed format is needed                   | Keep \[confirm each time] for now                                |
| Answer based on internal materials  | Knowledge base + knowledge base search   | Hand it over to the channel after retrieval becomes stable | First test questions that have no answers                        |
| Repeatedly execute a fixed workflow | Skills + necessary built-in tools        | Add MCP only when external data is needed                  | Skills should not store account keys                             |
| Call external systems               | MCP + least-privilege credentials        | Relax approval only after the task becomes stable          | Writes, deletions, and chargeable operations should be confirmed |

## User case: market research Agent

Bind the product materials knowledge base to the Agent, enable the 'Research Report' skill, connect a trusted web search MCP, and keep the built-in web scraping and file write tools. The Agent first determines the product scope from internal materials, then searches external information, and finally writes to the working directory according to the structure defined by the skill. Internal materials, external sources, and output format each have a clear role, making later maintenance easier.

<details>

<summary>Why are there still no search results after binding the knowledge base?</summary>

Make sure the knowledge base has finished processing and contains searchable content, then check whether the binding in the Agent edit window still exists. After a knowledge base is deleted, the related binding will be removed automatically.

</details>

<details>

<summary>Do I need to restart the task after enabling a skill?</summary>

There is no need to close the task. After editing the Agent, the new skill configuration will be loaded starting with the next message; the reply currently being generated will not be interrupted.

</details>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.cherryai.com.cn/docs/en-us/advanced-basic/agent-workspace/tools-knowledge-skills-mcp.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.