Model Context Protocol server for DeepSeek V4 API endpoints with stdio and Streamable HTTP transports.
If you already use Deepseek, the deepseek mcp server is the piece that lets your assistant work with it directly. Model Context Protocol server for DeepSeek V4 API endpoints with stdio and Streamable HTTP transports.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
chat_completion — DeepSeek V4 chat. Defaults to deepseek-v4-flash. Supports thinking: { "type": "enabled" | "disabled" }, reasoning_effort: "high" | "max", JSONcompletion — DeepSeek V4 Pro FIM completion. Defaults to deepseek-v4-prolist_models — Reads the live DeepSeek model listget_user_balance — Reads account balance and availabilityreset_conversation — Clears an in-memory conversationlist_conversations — Lists in-memory conversation IDsConfiguration is passed through the environment: DEEPSEEK_MCP_AUTH_TOKEN, REPLACE_WITH_TOKEN, DEEPSEEK_API_KEY, REPLACE_WITH_DEEPSEEK_KEY, DEEPSEEK_BASE_URL, MCP_HTTP_HOST, MCP_HTTP_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Deepseek's toolset — chat_completion, completion, list_models and 3 more — is a fair guide to whether it matches your workflow. It is maintained by DMontgomery40; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| chat_completion | DeepSeek V4 chat. Defaults to deepseek-v4-flash. Supports thinking: { "type": "enabled" | "disabled" }, reasoning_effort: "high" | "max", JSON output, function tools, logprobs, streaming, and conversation memory. |
| completion | DeepSeek V4 Pro FIM completion. Defaults to deepseek-v4-pro. |
| list_models | Reads the live DeepSeek model list. |
| get_user_balance | Reads account balance and availability. |
| reset_conversation | Clears an in-memory conversation. |
| list_conversations | Lists in-memory conversation IDs. |
{
"mcpServers": {
"deepseek": {
"command": "npx",
"args": ["-y", "deepseek-mcp-server"],
"env": {
"DEEPSEEK_MCP_AUTH_TOKEN": "your-value",
"REPLACE_WITH_TOKEN": "your-value",
"DEEPSEEK_API_KEY": "your-value",
"REPLACE_WITH_DEEPSEEK_KEY": "your-value",
"DEEPSEEK_BASE_URL": "your-value",
"MCP_HTTP_HOST": "your-value",
"MCP_HTTP_PATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| DEEPSEEK_MCP_AUTH_TOKEN | Credential the server authenticates with. | Yes |
| REPLACE_WITH_TOKEN | Credential the server authenticates with. | Yes |
| DEEPSEEK_API_KEY | Credential the server authenticates with. | Yes |
| REPLACE_WITH_DEEPSEEK_KEY | Credential the server authenticates with. | Yes |
| DEEPSEEK_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| MCP_HTTP_HOST | Endpoint or connection string the server talks to. | Optional |
| MCP_HTTP_PATH | Filesystem location the server is allowed to use. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.