Ollama
This Ollama MCP server implementation provides a bridge between the Model Context Protocol and Ollama, a local large language model runner. Developed as an open-source project, it enables seamless interaction with Ollama-hosted models through a standardized MCP interface. The server supports key operations such as chat completions, with real-time streaming capabilities using Server-Sent Events (SSE). Built with TypeScript and leveraging the @modelcontextprotocol/sdk, it offers robust error handling and configuration options. This implementation is particularly useful for developers and researchers looking to integrate locally-hosted AI models into their MCP-compatible applications, enabling low-latency access to powerful language models while maintaining data privacy and control.
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
- search
- Source
- PulseMCP
- Repository
- github.com/nighttrek/ollama-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Ollama 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.