Offload coding and text tasks to a local Ollama LLM to save API tokens. Use for code generation, refactoring, formatting, and more.
Apache 2.0
675,409 tools. Updated 2026-10-19 05:13
"Connecting Claude and Ollama" matching MCP tools:
- Switch the AI provider used for file renaming. Supports Claude, OpenAI, Gemini, Ollama, and Apple providers.MIT
- Send a prompt to any AI provider, including ChatGPT, Gemini, Claude, and Ollama. Use active provider/model by default or specify a different one.MIT
- Send simple questions to a local Ollama model for quick answers, saving Claude tokens for complex tasks.-
- Generate simple text locally with Ollama for error messages, placeholder content, boilerplate code, and routine documentation, saving Claude tokens for complex reasoning.-
- List all locally available Ollama models to identify options for offloading simpler tasks and conserving Claude tokens.-
Matching MCP Servers
- AlicenseAqualityBmaintenanceLets Claude query and manage a local Ollama server — list models, inspect them, run generate/chat completions, pull or delete models.8MIT
- AlicenseAqualityBmaintenanceDelegates tasks from an Anthropic-backed Claude Code session to Ollama-backed Claude Code sessions, allowing them to run side-by-side without sharing environment variables.710 npmMIT
Matching MCP Connectors
Written fix-and-flip term sheets for 1–4 unit investment purchases, by email. Business-purpose only.
On 11 Sept 2026, Claude's best model rates 40 points above OpenAI's and 16 above Gemini's..
- Downloads and installs an Ollama model locally, enabling Claude to offload simpler tasks and cut token usage.-
- Generate MCP client configuration snippets for connecting Codex, Claude Desktop, or other stdio MCP clients.-
- Check the LLMxRay server's status: observe port, forwarded Ollama version, retained turns, disk text setting, and start time. Use when diagnostics see no turns or to confirm the Ollama target.Apache 2.0
- Report the current setup and environment: model availability, login statuses, CLI installations, council composition, subscription tiers, concurrency, and quota warnings.Apache 2.0
- Create a self-contained prompt-to-response LLM chain inside TouchDesigner as a baseCOMP. Choose webclient or dropped TOX mode for OpenAI, Anthropic, Ollama, or custom endpoints.MIT
- Get connection commands for a deployed gateway group endpoint, including HTTP endpoint, Bearer header, claude mcp add line, mcp-proxy stdio bridge, and JSON-RPC curl.MIT
- List all AI models available across configured providers (Ollama, OpenAI, Anthropic, X.AI, vLLM, TRT-LLM, SGLang, CLI) to get model IDs for council configuration.Apache 2.0
- Count installed Claude Code skills, agents, and commands in your ~/.claude directory to assess your ecosystem setup.MIT
- List Supabase instances on Aliyun RDS to discover instance names, status, and connection URLs for connecting.MIT
- List free-seat status and requestable local runtimes such as Ollama, llama.cpp, LM Studio, OpenAI-compatible servers, and vLLM.MIT
- Set subscription tiers for ChatGPT, Claude, Grok, and Ollama to control cloud availability and per-provider concurrency, then auto-populate the council with usable models.Apache 2.0
- List local Ollama models and retrieve queryable paid route labels for accessing AI models with payment options.MIT
- Retrieve a snapshot of a Claude session, including current todos and reported problems, by providing the session ID.MIT
- Initiates a Claude Agent SDK session in the background and returns a session handle for monitoring and control.MIT
- Send messages to a local Ollama model acting as a sovereign digital twin. Responses are WORM-sealed for immutable record keeping.Apache 2.0