Grok
Grok MCP Server provides AI assistants with access to the Grok API, enabling chat completions, text completions, embeddings, and model operations. Developed by BrewMyTech, this TypeScript implementation uses Zod for robust request/response validation and offers comprehensive error handling for common API issues. The server exposes five core tools: listing models, retrieving model details, creating chat completions with optional streaming support, generating text completions, and creating text embeddings. It authenticates via environment variables and is designed for seamless integration with Visual Studio Code, making it ideal for developers building applications that require Grok's AI capabilities.
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/brewmytech/grok-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Grok 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.