Vercel AI
This OpenAI and Mistral MCP server implementation leverages the Vercel AI SDK to provide a unified interface for interacting with multiple AI models. It supports OpenAI's GPT-4 and GPT-3.5 series, as well as Mistral's large and small models, offering features like structured output, system prompts, and safe prompts. Built with TypeScript and designed for Node.js environments, this server stands out by combining two leading AI providers in a single, easy-to-use package. It's particularly useful for developers looking to integrate advanced language models into their applications, enabling seamless switching between providers and models to suit different use cases, from content generation to complex reasoning tasks.
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/opencnid/mcp-vercel-ai
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Vercel AI 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.