mcp-server-deepseek

Created By
tizeea year ago
A MCP server provides access to DeepSeek-R1's reasoning capabilities for LLMs
Overview

What is mcp-server-deepseek?

The mcp-server-deepseek is a Model Context Protocol (MCP) server that provides access to DeepSeek-R1's reasoning capabilities, enabling non-reasoning models to generate improved responses through enhanced thinking.

How to use mcp-server-deepseek?

To use the mcp-server-deepseek, clone the repository, set up a virtual environment, install the package, and configure your DeepSeek API credentials in a .env file. You can then run the server and use the think_with_deepseek_r1 tool to send prompts and receive reasoning content.

Key features of mcp-server-deepseek?

  • Access to DeepSeek-R1's reasoning model via API.
  • Structured reasoning output in a <thinking> format.
  • Full compatibility with the Model Context Protocol.
  • Robust error handling and detailed logging.

Use cases of mcp-server-deepseek?

  1. Enhancing responses from models lacking native reasoning capabilities.
  2. Accessing DeepSeek-R1's reasoning for complex problem-solving tasks.
  3. Integrating structured reasoning into LLMs like Claude that support MCP.

FAQ from mcp-server-deepseek?

  • What is required to run the server?

    You need Python 3.13 or higher and a valid DeepSeek API key.

  • How do I run the server?

    You can run the server directly using the command mcp-server-deepseek or in development mode with make dev.

  • What should I do if I encounter API key issues?

    Ensure your DeepSeek API key is correctly set in the .env file.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
tizee
Star
0
Language
Python
License
MIT license

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

37 minutes ago