deepseek-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEEPSEEK_API_KEY | Yes | Required. DeepSeek API key. Can also be set as the apiKey key in ~/.deepseek-mcp/config.json. | |
| DEEPSEEK_ALLOW_FS | No | Whether local file reads are allowed. Set to 0 to block all local file reads. | true |
| DEEPSEEK_BASE_URL | No | Base URL for the DeepSeek or any OpenAI-compatible API. | https://api.deepseek.com |
| DEEPSEEK_FS_ROOTS | No | Directories to confine file reads to. Empty means unrestricted. | |
| DEEPSEEK_LOG_FILE | No | Log file path. Rotates at 5 MB. | ~/.deepseek-mcp/deepseek-mcp.log |
| DEEPSEEK_LOG_LEVEL | No | Log level: silent, error, warn, info, debug, or trace. | info |
| DEEPSEEK_CHAT_MODEL | No | Model used for chat completions. | deepseek-chat |
| DEEPSEEK_MAX_TOKENS | No | Default max_tokens value. 0 means send no max_tokens and let the API use its own maximum. | 0 |
| DEEPSEEK_TIMEOUT_MS | No | Request timeout in milliseconds. Default is 15 minutes for long reasoning runs. | 900000 |
| DEEPSEEK_LOG_TO_FILE | No | Whether logging to a file is enabled. | true |
| DEEPSEEK_MAX_RETRIES | No | Maximum number of retries with exponential backoff. Honours Retry-After. | 4 |
| DEEPSEEK_BETA_BASE_URL | No | Beta base URL used by fill-in-the-middle and prefix completion. | <baseUrl>/beta |
| DEEPSEEK_REASONER_MODEL | No | Model used for reasoning completions. | deepseek-reasoner |
| DEEPSEEK_MAX_BYTES_TOTAL | No | Maximum total bytes read. 0 means unlimited. | 8000000 |
| DEEPSEEK_MAX_OUTPUT_CHARS | No | Maximum output characters for tool results. 0 means never truncate. | 0 |
| DEEPSEEK_PERSIST_SESSIONS | No | Whether multi-turn sessions are persisted to disk. | true |
| DEEPSEEK_MAX_BYTES_PER_FILE | No | Maximum bytes read per file. 0 means unlimited. | 2000000 |
| DEEPSEEK_SESSION_MAX_MESSAGES | No | Maximum messages retained in a session. Oldest turns are dropped past this. | 200 |
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
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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues