Unichat (TS)
This TypeScript MCP server, developed by Stefan, integrates the Unichat library to enable AI assistants to interact with multiple language models including OpenAI, MistralAI, Anthropic, xAI, and Google AI. It provides a unified interface for sending requests to these models via a single 'unichat' tool, abstracting away the complexities of individual APIs. The server supports both STDIO and SSE transport mechanisms and includes predefined prompts for common tasks like code review, documentation, and explanation. By offering a consistent way to leverage multiple AI models, this implementation is particularly useful for developers building flexible chatbots, multi-model AI assistants, or applications that require seamless switching between different language models.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · 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/amidabuddha/unichat-ts-mcp-server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Unichat (TS) 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.