Deepseek MCP Server

Unclaimed

by arikusi

MCP server for DeepSeek V4 (v4-flash, v4-pro, 1M context): chat, reasoning, function calling, thinking mode, cost tracking. deepseek-chat/reasoner aliases supported.

Install

$claude mcp add -s user deepseek npx @arikusi/deepseek-mcp-server -e DEEPSEEK_API_KEY=your-key-here

Unclaimed listing

Is this your MCP server?

This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.

Claim this server

Tools (25)

action

(required): "list" "clear" "delete"

content

Message text

deepseek_chat

Chat with DeepSeek AI models with automatic cost tracking and function calling support.

deepseek_fim

Fill-in-the-Middle completion. You give a prompt (the prefix) and an optional suffix, and the model completes the text in between. It is built for code completion and content infilling rather than conversation. FIM runs on DeepSeek's Beta endpoint in non-thinking mode, and the API caps output at 409

deepseek_sessions

Manage conversation sessions.

json_mode

(optional): Enable JSON output mode (supported by both models)

max_tokens

(optional): Maximum tokens to generate (V4 models support up to 384000)

messages

(required): Array of conversation messages

model

(optional): "deepseek-v4-flash" (default) or "deepseek-v4-pro". The deprecated "deepseek-chat" and "deepseek-reasoner" aliases are still accepted and resolve to v4-flash (non-thinking / thinking); prefer the V4 names.

prompt

(required): The prefix text before the gap. For code completion, this is the code up to the cursor.

reasoning_effort

(optional): "high" (default) or "max", applies only while thinking mode is active

response_schema

(optional): A JSON Schema to validate the model output against. Implies JSON output. The server validates the parsed result and, on failure, issues up to RESPONSESCHEMAMAXRETRIES repair retries (default 2, set 0 to disable) that feed the validation error back to the model. Schema regex patterns are

role

"system" "user" "assistant" "tool"

session_id

(optional): Session ID for multi-turn conversations. Previous context is automatically prepended.

stop

(optional): A stop string or an array of up to 16 stop strings.

stream

(optional): Enable streaming mode (default: false)

structuredContent.effective

and fallback: what was actually sent after alias/thinking resolution, and any silent model fallback that fired

structuredContent.request

a self-contained per-request usage and cost summary (token counts, cache hit/miss, costusd), aggregated across any repair retries

structuredContent.schema

when responseschema is used, {valid, attempts, error?}; jsonparseerror when JSON output could not be recovered

suffix

(optional): The text after the gap. The model fills the space between prompt and suffix.

temperature

(optional): 0-2, controls randomness (default: 1.0). Ignored when thinking mode is enabled.

thinking

(optional): Toggle thinking mode, {type: "enabled"} to reason or {type: "disabled"} for a fast answer (non-thinking is the default)

tool_call_id

(optional): Required for tool role messages

tool_choice

(optional): "auto" "none" "required" {type: "function", function: {name: "..."}}

tools

(optional): Array of tool definitions for function calling (max 128)