dstools
by lijiatuk
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Logging verbosity | INFO |
| VISION_MODEL | No | e.g. gpt-4o, qwen-vl-max, glm-4v, a local qwen2.5-vl via Ollama | |
| DEEPSEEK_MODEL | No | Synthesis / heavy model | deepseek-v4-pro |
| RESEARCH_DEPTH | No | Research rounds | 2 |
| TAVILY_API_KEY | No | Required if SEARCH_PROVIDER=tavily | |
| VISION_API_KEY | No | Key for the vision endpoint | |
| SEARCH_PROVIDER | No | duckduckgo (keyless) / tavily | duckduckgo |
| VISION_BASE_URL | No | OpenAI-compatible vision endpoint (any multimodal model) | |
| DEEPSEEK_API_KEY | No | DeepSeek API key (required for deep_research) | |
| RESEARCH_BREADTH | No | Sub-queries generated per round | 3 |
| DEEPSEEK_BASE_URL | No | OpenAI-compatible endpoint | https://api.deepseek.com |
| DEEPSEEK_THINKING | No | auto/on/off — V4 thinking mode for hard steps | auto |
| DEEPSEEK_FAST_MODEL | No | Cheap sub-step model | deepseek-v4-flash |
| RESEARCH_MAX_SOURCES | No | Pages fetched & synthesised | 8 |
| DEEPSEEK_REASONING_EFFORT | No | low/medium/high | high |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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/lijiatuk/dstools'
If you have feedback or need assistance with the MCP directory API, please join our Discord server