Llama.cpp Bridge
This MCP server provides a bridge between Claude Desktop and local LibreModel (Gigi) instances running via llama-server, built by Jerry using TypeScript with the Model Context Protocol SDK and Zod validation. The implementation offers three core tools: a main chat interface with full parameter control (temperature, max tokens, top-p, top-k sampling), quick predefined tests for capability verification, and health checks with server diagnostics including props endpoint querying. Features configurable defaults, graceful error handling with timeout protection, and comprehensive usage documentation through built-in resources, making it valuable for users who want to integrate their local llama.cpp models with Claude Desktop while maintaining full control over generation parameters and server connectivity.
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
- file-system
- Source
- PulseMCP
- Repository
- github.com/openconstruct/llama-mcp-server
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Llama.cpp Bridge 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.