DeepSeek Reasoner
This MCP server, developed by Based_H-10, integrates the DeepSeek API's reasoning capabilities with Claude. Built with Python and leveraging the FastMCP framework, it provides a tool for enhancing Claude's responses with DeepSeek's R1 reasoning engine. The implementation focuses on seamlessly combining DeepSeek's advanced reasoning, which evolved from large-scale reinforcement learning, with Claude's existing capabilities. It's particularly useful for applications requiring more sophisticated reasoning and analysis, enabling use cases such as complex problem-solving, in-depth research assistance, and nuanced decision support without directly exposing users to the intricacies of the DeepSeek API.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- search
- Source
- PulseMCP
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve DeepSeek Reasoner from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.