TwoSplit
Twosplit MCP Server leverages multiple Claude instances to provide enhanced AI responses. It sends the same prompt to two separate Claude models and uses a third instance to either select the best response or combine elements from both, delivering a final optimized answer. The server supports various Claude models including Opus, Sonnet, and Haiku, and returns not only the final response but also the original outputs from both AIs along with source attribution. This implementation is particularly valuable for users seeking more comprehensive or nuanced answers by comparing multiple AI perspectives within a single query.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/lazerthings/twosplit
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve TwoSplit 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.