{"data":{"slug":"jonigl-mcp-client-for-ollama","name":"mcp-client-for-ollama","tagline":"TUI MCP Client for Ollama enables local LLM interaction with extensive features.","github_url":"https://github.com/jonigl/mcp-client-for-ollama","owner":"jonigl","repo":"mcp-client-for-ollama","owner_avatar_url":"https://avatars.githubusercontent.com/u/4612832?v=4","primary_language":"Python","stars":783,"forks":114,"topics":["agentic-ai","ai","command-line-tool","harness","linux","local-llm","macos","mcp","mcp-client","mcp-prompts","mcp-resouces","mcp-server","mcp-tools","model-context-protocol","ollama","open-source","sse","stdio","streamable-http","windows"],"archived":false,"github_pushed_at":"2026-07-27T08:34:02+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/jonigl-mcp-client-for-ollama","markdown_url":"https://www.graphcanon.com/tools/jonigl-mcp-client-for-ollama.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jonigl-mcp-client-for-ollama","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jonigl-mcp-client-for-ollama","description":"Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved preferences.","homepage_url":null,"license":"MIT","open_issues":19,"watchers":8,"ai_summary":"jonigl/mcp-client-for-ollama offers a TUI client that supports local large language model (LLM) interaction through the Model Context Protocol (MCP). It includes tools, prompts, resources, and an agent mode among other functionalities like model switching, streaming responses, human-in-the-loop support.","readme_excerpt":"## Requirements\n\n- **Python 3.11+** ([Installation guide](https://www.python.org/downloads/))\n- **Ollama** running locally ([Installation guide](https://ollama.com/download))\n  - After installation, run `ollama list` to see available models. If no models are installed, you can pull one using `ollama pull <model_name>`. For example, `ollama pull gemma4:latest`.\n- **UV package manager** ([Installation guide](https://github.com/astral-sh/uv))\n\n---\n\n## Quick Start\n\nInstall `ollmcp` via pip, add an MCP server, and run the client:\n\n```bash\n\n---\n\n# Install ollmcp via uv\nuv tool install --upgrade ollmcp\n\n---\n\n## Installation Options\n\n**Option 1:** Install with uv and run (recommended)\n\n```bash\nuv tool install --upgrade ollmcp\nollmcp\n```\n\n**Option 2:** Install with pip and run\n\n```bash\npip install --upgrade ollmcp\nollmcp\n```\n\n**Option 3:** Only run without installing (requires `uv` package manager)\n\n```bash\nuvx ollmcp\n```\n\n**Option 4:** Install from source and run using virtual environment\n\n```bash\ngit clone https://github.com/jonigl/mcp-client-for-ollama.git\ncd mcp-client-for-ollama\nuv run -m mcp_client_for_ollama\n```\n\n---\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.","github_created_at":"2025-04-23T21:05:02+00:00","created_at":"2026-07-11T11:54:30.559149+00:00","updated_at":"2026-08-02T04:00:33.619581+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"agentic-ai","name":"agentic-ai"},{"slug":"ai","name":"ai"},{"slug":"command-line-tool","name":"command-line-tool"},{"slug":"linux","name":"linux"},{"slug":"local-llm","name":"local-llm"},{"slug":"macos","name":"macos"},{"slug":"mcp-client","name":"mcp-client"},{"slug":"ollama","name":"ollama"}],"trust":{"provenance":{"is_fork":false,"github_id":971649509,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-27T12:00:39.778Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":10,"days_since_push":0,"last_release_at":"2026-07-25T16:07:15Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-08-02T04:00:33.246Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-27T12:00:40.269Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-07-27T12:00:40.269Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-07-27T12:00:40.269Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-27T12:00:40.269Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["If your project requires extensive interactions with locally-hosted large language models, offering agents and tools for automation directly from a text-based user interface.","When you need to switch between multiple LLMs easily and control settings like model parameters or system prompts, enhancing flexibility for varied workflows."],"when_not_to_use":["If your setup is more about integrating with distant servers in the cloud rather than engaging local models, as this tool focuses on interfacing with locally available resources.","For environments that need purely graphical user interfaces (GUI) since mcp-client-for-ollama provides a text-based user interface which might be a limitation if advanced visualization is required."],"source":"enrich:decision_facts","observed_at":"2026-07-15T08:23:09.835Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"For developers focused on local LLM interaction with robust features such as streaming responses and human-in-the-loop collaboration through a TUI interface"}]}}