pulsemcp Safe content atomic mcp-remote

DeepSeek Reasoner

DeepSeek-Claude integrates DeepSeek's R1 reasoning engine with Claude, enabling sophisticated reasoning capabilities through a simple API interface. The server exposes a single tool that processes queries by sending them to the DeepSeek API and formatting the reasoning output within <ant_thinking> tags for seamless integration with Claude's thought process framework. This implementation allows Claude to leverage DeepSeek's advanced reasoning capabilities that evolved from large-scale reinforcement learning, making it particularly valuable for complex problem-solving tasks that benefit from multiple reasoning approaches.

Cognium trust score
50%
Tier
Unverified

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
productivity
Source
PulseMCP
Author type
human
Updated
2026-04-25
View source Find related skills

Use via MCP

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
Swap --scope user for --scope project to commit it to .mcp.json.

Search SkillsRegistry