"ollama" matching MCP servers:

MCP server for delegating coding tasks to local Ollama models. Supports listing models and executing tasks with file writing capabilities.

A VRAM-aware MCP server that offloads token-heavy development tasks to local Ollama models, saving API tokens for complex reasoning.

MCP server that lets Claude Code offload simple tasks like code explanation, writing tests, and adding comments to a local Ollama model, saving Claude API tokens.

Enables natural language queries to PostgreSQL through an Ollama-powered agent, using MCP protocol to connect the backend to the database and a web interface.

Hardened MCP bridge to the full Ollama ecosystem — local and cloud models. 6 tools covering health, model management, chat, and generation with SSRF mitigation, singleton HTTP client, and structured error handling. Two deps, one file.

Enables Claude Code to leverage local Ollama models for tasks like summarizing large files, reviewing diffs, semantic code search, and generating boilerplate or tests, while also supporting a fully offline mode.

Enables AI agents to offload mechanical, high-token work to local Ollama models through MCP, with role-based model discovery, batch processing, and file-aware inputs.

Offloads cheap work from cloud LLM agents to a local Ollama model, reducing costs and keeping frontier models focused on complex tasks.

Integrates Ollama's local AI models with MCP clients, enabling listing models, viewing model details, and asking questions to models.

MCP server wrapping local Ollama models for offload from API-priced orchestrators. Nine stdio tools - generation, summarisation, analysis, drafting, code tasks (docstring/test/explain/review/types/refactor-suggest), diff-driven tasks (commit-message/pr-description/changelog/summary/impact), mechanical transforms, and model management (list/pull). Apache-2.0.

Enables locally running an Ollama-powered MCP server to chat with a tool-capable model, retrieve bundled demo documents, and execute /security+ or /format commands through MCP, an authenticated HTTP API, or an interactive CLI.

An MCP server that lets Claude Code delegate coding tasks such as code generation, review, refactoring, and test writing to a local Ollama instance running a Qwen3 model.

A minimal local vision bridge for text-only VS Code Copilot, enabling it to see images by sending them to a local Ollama vision model and returning text descriptions. It provides MCP tools for image description, listing, OCR, and status checks.

Lets Claude query and manage a local Ollama server — list models, inspect them, run generate/chat completions, pull or delete models.

Exposes a local Ollama fleet as MCP tools for Claude Code, enabling model listing, generation, fleet health checks, parallel comparisons, smart host routing, and model pulling across hosts.

A Python MCP server that gives vision capabilities to text-only LLMs by exposing an analyze_image tool that sends local images to a vision-capable Ollama model and returns textual descriptions.

Gives AI agents a persistent vector memory by embedding text with Ollama and storing it in Qdrant, so they can save, batch-save, semantically search with payload filters, and delete memories across collections.

MCP server enabling LLM clients without vision capability to process images by delegating to local Ollama vision models. Supports describing images, OCR, asking questions, and processing clipboard images.

Enables AI agents to interact with local Ollama models for text generation and tool calling with prompt injection protection.

Enables Google Antigravity CLI to offload token-heavy workloads to local Ollama models through MCP tools for code drafting, summarization, chunked map-reduce, and JSON extraction, reducing cloud token usage.