MCP server for running Ollama models with async support
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"iflow-mcp-angrysky56-ollama-mcp-server","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Ollama MCP Server A comprehensive Model Context Protocol (MCP) server for Ollama integration with advanced features including script management, multi-agent workflows, and process leak prevention. ## 🌟 Features - **🔄 Async Job Management**: Execute long-running tasks in the background - **📝 Script Templates**: Create reusable prompt templates with variable substitution - **🤖 Fast-Agent Integration**: Multi-agent workflows (chain, parallel, router, evaluator) - **🛡️ Process Leak Prevention**: Proper cleanup and resource management - **📊 Comprehensive Monitoring**: Job tracking, status monitoring, and output management - **🎯 Built-in Prompts**: Interactive guidance templates for common tasks - **⚡ Multiple Model Support**: Work with any locally installed Ollama model ## 🚀 Quick Start ### Prerequisites - Python 3.8+ with [uv](https://docs.astral.sh/uv/) package manager - [Ollama](https://ollama.ai/) installed and running - [Claude Desktop](https://claude.ai/download) for MCP integration ### Installation 1. **Setup Environment**: Be advised- This readme was revised by a less than concientious AI. ```bash cd /path/to/ollama-mcp-server uv venv --python 3.12 --seed source .venv/bin/activate uv add mcp[cli] python-dotenv ``` 2. **Configure Claude Desktop**: Copy configuration from `example_of_bad_ai_gen_mcp_config_do_not_use.json` (Don't lol. Use the example_claude_desktop_config.json)to your Claude Desktop config file: - **Linux**: `~/.config/Claude/claude_desktop_config.json` - **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json` - **Windows**: `%APPDATA%\Claude\claude_desktop_config.json` 3. **Update paths** in the config to match your system 4. **Restart Claude Desktop** ## 🛠️ Available Tools ### Core Operations - `list_ollama_models` - Show all available Ollama models - `run_ollama_prompt` - Execute prompts with any model (sync/async) - `get_job_status` - Check job completion status - `list_jobs` - View all running and c…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.