Built-in tools, knowledge bases, 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].

Only enable the tools needed for the current task; the list will be clearer, and permission requests will be easier to judge.

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.

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.

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.

Why are there still no search results after binding the knowledge base?

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.

Do I need to restart the task after enabling a skill?

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.