Model Context Protocol-Server für die aktuelle DeepSeek V4 API.
Stand 24. April 2026 dokumentiert die öffentliche API-Referenz von DeepSeek:
POST /chat/completions mit deepseek-v4-flash und deepseek-v4-pro
POST /beta/completions für V4 Pro FIM-Vervollständigung
GET /models
GET /user/balance
Dieser Server stellt nur diese dokumentierten API-Oberflächen bereit. Er enthält keinen V4-Monitor, keine spekulativen Bild-/Video-/Upload-Tools und keine automatische Modellersetzung.
chat_completion: DeepSeek V4 Chat. Standardmäßig deepseek-v4-flash. Unterstützt thinking: { "type": "enabled" | "disabled" }, reasoning_effort: "high" | "max", JSON-Ausgabe, Funktions-Tools, Logprobs, Streaming und Konversationsspeicher.
completion: DeepSeek V4 Pro FIM-Vervollständigung. Standardmäßig deepseek-v4-pro.
list_models: Liest die Live-Modellliste von DeepSeek.
get_user_balance: Liest Kontostand und Verfügbarkeit.
reset_conversation: Löscht eine im Arbeitsspeicher befindliche Konversation.
list_conversations: Listet IDs von Konversationen im Arbeitsspeicher auf.
Related MCP server: Deepseek MCP Server
URL: https://deepseek-mcp.ragweld.com/mcp
Auth: Authorization: Bearer <token>
Codex CLI:
export DEEPSEEK_MCP_AUTH_TOKEN="REPLACE_WITH_TOKEN"
codex mcp add deepseek --url https://deepseek-mcp.ragweld.com/mcp --bearer-token-env-var DEEPSEEK_MCP_AUTH_TOKENClaude Code:
export DEEPSEEK_MCP_AUTH_TOKEN="REPLACE_WITH_TOKEN"
claude mcp add --transport http deepseek https://deepseek-mcp.ragweld.com/mcp --header "Authorization: Bearer $DEEPSEEK_MCP_AUTH_TOKEN"Cursor:
node -e 'const fs=require("fs"),p=process.env.HOME+"/.cursor/mcp.json";let j={mcpServers:{}};try{j=JSON.parse(fs.readFileSync(p,"utf8"))}catch{};j.mcpServers={...(j.mcpServers||{}),deepseek:{url:"https://deepseek-mcp.ragweld.com/mcp",headers:{Authorization:"Bearer ${env:DEEPSEEK_MCP_AUTH_TOKEN}"}}};fs.mkdirSync(process.env.HOME+"/.cursor",{recursive:true});fs.writeFileSync(p,JSON.stringify(j,null,2));'DEEPSEEK_API_KEY="REPLACE_WITH_DEEPSEEK_KEY" npx -y deepseek-mcp-serverDocker:
docker pull docker.io/dmontgomery40/deepseek-mcp-server:0.5.0
docker run --rm -i -e DEEPSEEK_API_KEY="REPLACE_WITH_DEEPSEEK_KEY" docker.io/dmontgomery40/deepseek-mcp-server:0.5.0Erforderlich:
DEEPSEEK_API_KEY=your-api-keyOptional:
DEEPSEEK_BASE_URL=https://api.deepseek.com
DEEPSEEK_REQUEST_TIMEOUT_MS=120000
DEEPSEEK_DEFAULT_MODEL=deepseek-v4-flash
MCP_TRANSPORT=stdio
MCP_HTTP_HOST=127.0.0.1
MCP_HTTP_PORT=3001
MCP_HTTP_PATH=/mcp
MCP_HTTP_STATEFUL_SESSION=false
CONVERSATION_MAX_MESSAGES=200npm run build
npm test
DEEPSEEK_API_KEY="REPLACE_WITH_DEEPSEEK_KEY" npm run test:live
DEEPSEEK_MCP_AUTH_TOKEN="REPLACE_WITH_TOKEN" npm run test:remoteDer Live-Rauchtest führt echte DeepSeek-Anfragen für Modellauflistung, Kontostand, Chat ohne Thinking, Streaming-Chat mit Thinking inklusive reasoning_content, FIM-Vervollständigung und MCP-Tool-Aufrufe durch.
MCP Registry-Name: io.github.DMontgomery40/deepseek
npm-Paket: deepseek-mcp-server
OCI-Paket: docker.io/dmontgomery40/deepseek-mcp-server:0.5.0
DeepSeek Chat-Vervollständigungen: https://api-docs.deepseek.com/api/create-chat-completion
DeepSeek FIM-Vervollständigungen: https://api-docs.deepseek.com/api/create-completion
DeepSeek-Modelle: https://api-docs.deepseek.com/api/list-models
DeepSeek-Kontostand: https://api-docs.deepseek.com/api/get-user-balance
MCP-Spezifikation: https://modelcontextprotocol.io/specification/2025-11-25
MIT
Primary DeepSeek V4.1 chat tool for text, images, and multi-turn generation. Defaults to deepseek-flash. Provide either message (a text string or text/image/file content parts) or messages (full chat history); if both are provided, messages is used. Images may use an HTTP(S) URL, supported base64 data URL, or Files API file_id. Thinking is enabled by default; use reasoning_effort for current effort controls. Use conversation_id for explicit in-memory context. Set include_raw_response=true only for provider-payload debugging.
Inputs: stop, model, tools, top_p, +19 more. Returns: model, usage, status, message, +10 more
DeepSeek FIM completion tool for prompt/suffix fill-in-the-middle workflows. Defaults to deepseek-flash in non-thinking mode. Use this when you need raw completion text instead of chat message formatting. Set include_raw_response=true only when you need the full provider payload for debugging.
Inputs: prompt (required), echo, stop, model, +10 more. Returns: text, model, usage, status, +7 more
Create a stateless DeepSeek V4.1 response using the OpenAI-compatible Responses API. Defaults to deepseek-flash and accepts text, image URLs, base64 images, and Files API file_id inputs. Use reasoning.effort for thinking control, tools for function or server-side web-search tools, and stream=true for semantic SSE aggregation. Send full input history for multi-turn work. Set include_raw_response=true only for provider-payload debugging.
Inputs: text, user, input, model, +11 more. Returns: error, model, usage, status, +10 more
Delete one uploaded DeepSeek image by file_id. This permanently removes that provider-side file reference.
Inputs: file_id (required). Returns: id, object, status, deleted, +4 more
Return the current DeepSeek account balance and availability status. This tool takes no parameters and is read-only. Use it for account health checks when diagnosing provider-side failures.
Inputs: no named parameters. Returns: status, message, retryable, error_type, +3 more
List all conversation IDs currently stored in this MCP process memory. This tool takes no parameters and does not call the DeepSeek API. Useful for debugging conversation persistence behavior.
Inputs: no named parameters. Returns: count, status, message, retryable, +3 more
List images uploaded to the DeepSeek Files API. Supports cursor pagination, creation-time order, and the user_data purpose filter.
Inputs: after, limit, order, purpose. Returns: data, object, status, last_id, +6 more
List available DeepSeek models for model selection and validation. This tool takes no parameters. Use it before passing an explicit model ID to generation tools.
Inputs: no named parameters. Returns: data, object, status, message, +3 more
Delete stored in-memory chat history for a conversation_id. Use this when you want to keep the same ID but start a fresh thread. This only affects server-side memory in the current MCP process.
Inputs: conversation_id (required). Returns: status, message, removed, retryable, +3 more
Retrieve metadata for one DeepSeek Files API image by file_id.
Inputs: file_id (required). Returns: id, bytes, object, status, +8 more
Upload a JPEG, PNG, GIF, or WebP image to DeepSeek and return a reusable file_id. Supply base64 image data directly; server-local file paths are intentionally not accepted. Optional expiry is 3,600 to 2,592,000 seconds.
Inputs: filename (required), file_data (required), expires_after_seconds. Returns: id, bytes, object, status, +8 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 11 tools
The three generation tools (chat_completion, completion, create_response) have overlapping capabilities like text/image input and multi-turn support, which could cause confusion. However, their descriptions clearly differentiate use cases (chat vs FIM vs stateless Responses API), and all other tools target distinct resources or actions.
Nine of eleven tools follow a consistent verb_noun pattern (e.g., list_models, upload_file, delete_file). The two exceptions (chat_completion and completion) are noun-only names, but they are conventional and readable, making the set mostly predictable.
The server provides 11 tools, which is well within the ideal 3–15 range. Each tool covers a distinct aspect of the DeepSeek API (generation, file management, account info, conversation memory), with no obvious redundancy or bloat.
The surface covers core generation, file CRUD (upload/list/retrieve/delete), model listing, balance check, and conversation memory management. Minor gaps include no explicit update or detailed inspection of conversations, but these are not critical for typical workflows.
Chat, image, video, and audio models from many vendors behind one remote MCP server and one key.
Connect MCP clients to 2,000+ AI models without managing provider API keys.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
MCP server for AI dialogue using various LLM models via AceDataCloud