Built-in Tools
Zeus’s tool system is organized into four layers, each serving a different capability domain:Tool Injection & Mode Filtering
Tools are loaded sequentially during_init_context(), with different tool sets available per mode:
| Tool Category | Agent Mode | Ask Mode | Plan Mode |
|---|---|---|---|
| Filesystem (read/write) | All | Read-only | Read-only |
| TodoList | All | All | All |
| Memory | Read/write | Disabled | Read-only |
| RAG | All | Read-only (search/list) | All |
| Sandbox | All | Disabled | Disabled |
| Web Search | All | All | All |
| MCP/OAuth | All | Read-only | Read-only |
| Browser/Desktop | All | Disabled | Disabled |
MultiServerMCPClient, with each server having a 1800s (30min) timeout.
TODO State Flow
Overview
TodoList is a built-in middleware tool from the DeepAgents framework, managing task state throughwrite_todos and read_todos.
Background
In real-time chat and history replay, thetodo.md state needs to be correctly updated. Previously, there was a bug where sandbox tool calls would overwrite the todo.md content.
Data Flow
Key Fix
The file list returned bysandbox calls would overwrite the todo.md content previously set by write_todos. The solution is to check during state updates whether the existing todo.md content should be preserved. If the newly returned file list does not contain an updated version of todo.md, the content previously set by write_todos is retained, preventing it from being overwritten.
MCP Prompts
Overview
Zeus supports MCP (Model Context Protocol) Prompts functionality. In addition to@mcp.tools, MCP server-provided prompt templates can be accessed via @mcp.prompts.
What are MCP Prompts
MCP Prompts are reusable prompt templates provided by MCP servers, similar to preset conversation scenarios or workflows. Tools vs Prompts:| Feature | Tools | Prompts |
|---|---|---|
| Purpose | Execute specific operations | Provide preset prompts |
| Examples | Search, file reading | Code review template |
| Invocation | Agent calls automatically | User selects to use |
Architecture
The system initializes MCP Prompts via BaseService, iterating through all configured MCP servers to retrieve each server’s prompt list (including name, description, and parameter information). The API validation endpoint/validate returns both tool and prompt information. MCP server records in the database contain tools and prompts JSON fields.
Usage
Method 1: As Prompt Template Resources
Users can select a prompt in the UI and fill in parameters. The system will retrieve the corresponding prompt content based on the selected prompt and parameters.Method 2: Dynamic Invocation
The AI can identify when a prompt template is needed and dynamically retrieve prompt content by specifying the server name, prompt name, and parameters.Official Tools
Overview
Zeus AI provides a set of pre-configured official tools that can be directly enabled and used in the MCP tab.Available Tools
Tavily Search
AI-powered web search engine- Function: Search the internet using AI technology
- Use Cases: Find real-time information, news, research materials
- Requires API Key: Yes
- Get API Key: https://tavily.com
- Default Enabled: Yes
GitHub
GitHub repository and code search- Function: Search GitHub repositories, view code, get user information
- Use Cases: Find open-source projects, research code implementations
- Requires API Key: Yes (recommended)
- Get API Key: GitHub Personal Access Token
- Default Enabled: No
Usage Guide
Enabling Official Tools
- Open the tool configuration panel
- Select the “MCP” tab
- Find the tool you need in the “Official Tools” area
- Click the toggle switch on the tool card to enable it
Configuring API Keys
- Click the “Configure API Key” button on the tool card
- Enter the API Key
- The API Key will be securely encrypted and stored
- The tool will be automatically enabled
API Endpoints
GET /api/official-tools/list- Get list of all available official toolsPOST /api/official-tools/test- Test if tool connection is working