OllamaCAUTION
An MCP Server for Ollama
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Supercharge your AI assistant with local LLM access
[](https://www.gnu.org/licenses/agpl-3.0) [](https://www.typescriptlang.org/) [](https://github.com/anthropics/model-context-protocol) [](https://github.com/rawveg/ollama-mcp)
An MCP (Model Context Protocol) server that exposes the complete Ollama SDK as MCP tools, enabling seamless integration between your local LLM models and MCP-compatible applications like Claude Desktop and Cline.
Features • Installation • Available Tools • Configuration • Retry Behavior • Development
✨ Features
- ☁️ Ollama Cloud Support - Full integration with Ollama's cloud platform
- 🔧 14 Comprehensive Tools - Full access to Ollama's SDK functionality
- 🔄 Hot-Swap Architecture - Automatic tool discovery with zero-config
- 🎯 Type-Safe - Built with TypeScript and Zod validation
- 📊 High Test Coverage - 96%+ coverage with comprehensive test suite
- 🚀 Zero Dependencies - Minimal footprint, maximum performance
- 🔌 Drop-in Integration - Works with Claude Desktop, Cline, and other MCP clients
- 🌐 Web Search & Fetch - Real-time web search and content extraction via Ollama Cloud
- 🔀 Hybrid Mode - Use local and cloud models seamlessly in one server
💡 Level Up Your Ollama Experience with Claude Code and Desktop
The Complete Package: Tools + Knowledge
This MCP server gives Claude the tools to interact with Ollama - but you'll get even more value by also installing the Ollama Skill from the Skillsforge Marketplace:
- 🚗
78471f5c7f0eOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add ollama-mcp --env OLLAMA_API_KEY=${OLLAMA_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"ollama-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"OLLAMA_API_KEY": "${OLLAMA_API_KEY}"
}
}
}
}Exposed tools (14)
11 read · 2 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
get_weather | read | Get weather |
ollama_chat | read | Chat with a model using conversation messages. Supports system messages, multi-turn conversations, tool calling, and generation options. |
ollama_copy | read | Copy a model. Creates a duplicate of an existing model with a new name. |
ollama_create | write | Create a new model with structured parameters. Allows customization of model behavior, system prompts, and templates. |
ollama_delete | destructive | Delete a model from local storage. Removes the model and frees up disk space. |
ollama_embed | read | Generate embeddings for text input. Returns numerical vector representations. |
ollama_generate | read | Generate completion from a prompt. Simpler than chat, useful for single-turn completions. |
ollama_list | read | List all available Ollama models installed locally. Returns model names, sizes, and modification dates. |
ollama_ps | read | List running models. Shows which models are currently loaded in memory. |
ollama_pull | read | Pull a model from the Ollama registry. Downloads the model to make it available locally. |
ollama_push | write | Push a model to the Ollama registry. Uploads a local model to make it available remotely. |
ollama_show | read | Show detailed information about a specific model including modelfile, parameters, and architecture details. |
ollama_web_fetch | read | Fetch a web page by URL using Ollama\ |
ollama_web_search | read | Perform a web search using Ollama\ |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (11)
host: process.env.OLLAMA_HOST || 'http://127.0.0.1:11434',
ollama_delete
const { createServer } = await import('../../src/server.js');import { ChatInputSchema } from '../../src/schemas.js';import { chatWithModel, toolDefinition } from '../../src/tools/chat.js';import { ResponseFormat } from '../../src/types.js';import { copyModel, toolDefinition } from '../../src/tools/copy.js';| `OLLAMA_HOST` | `http://127.0.0.1:11434` | Ollama server endpoint (use `https://ollama.com` for cloud) |
"OLLAMA_HOST": "http://127.0.0.1:11434",
@modelcontextprotocol/sdk, json2md, markdown-table, ollama, zod, @types/node, @vitest/coverage-v8, typescript
- 🔧 **14 Comprehensive Tools** - Full access to Ollama's SDK functionality
Gates applied: no_behavioural_pass.
78471f5c7f0efull audit observations/trust-audit/mcp-server/rawveg__ollama.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 78471f5c7f0e | CAUTION | B | 89 | first audit |
Questions
What is the Ollama MCP server?
An MCP Server for Ollama
What tools does Ollama expose?
14 in total: 11 read-only, 2 that write, and 1 that can delete or overwrite (ollama_delete). Every one is listed on this page with its risk.
Is Ollama safe to connect to an agent?
With care. The audit graded it B (89/100) and found 11 things worth knowing before you trust this server, listed below with the exact line each was found on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Ollama need?
It reads OLLAMA_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Ollama run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as ollama-mcp at 2.1.0.
How current is this page?
The grade is for one exact copy of the source (78471f5c7f0e), read on 2026-10-06. The repository is watched and re-audited when it changes.