mcp-server-deepseek
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Log level for the server | DEBUG |
| MCP_SERVER_DEEPSEEK_API_KEY | Yes | Your DeepSeek API key | |
| MCP_SERVER_DEEPSEEK_MODEL_NAME | No | The DeepSeek model name to use | deepseek-reasoner |
| MCP_SERVER_DEEPSEEK_API_BASE_URL | No | The base URL for the DeepSeek API | https://api.deepseek.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| think-with-deepseek-r1C | Ask deepseek-R1 for user's prompt Arg: prompt: user's full prompt (full text) Return: Enhanced thinking |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| ask_deepseek |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
Only one tool exists, so there is no ambiguity about which tool to use for the task.
The single tool name 'think-with-deepseek-r1' uses hyphens rather than the common snake_case or camelCase, but consistency within the set is perfect.
A single tool for a model interaction server feels insufficient; typically such servers offer multiple tools for different operations.
The tool covers one specific thinking enhancement, but lacks complementary operations like chat or raw output, leaving potential gaps.