Ollama
This MCP server provides integration with Ollama for local LLM inference, built by KingJhonRi using FastMCP and the Ollama Python client. The implementation offers direct access to locally hosted language models through Ollama's API, enabling AI assistants to leverage self-hosted models for text generation, conversation, and other language tasks without relying on external cloud services. Features include model management capabilities and streaming response support, making it ideal for developers and organizations requiring privacy-focused AI workflows, offline language model access, or custom model deployment scenarios where data sovereignty and local processing are priorities.
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
- devops-ci
- Source
- PulseMCP
- Repository
- github.com/kingjhonri/mcp-ollama
- 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.