Log inSubmit server
Offline MCP logo

Offline MCP

Runs local Ollama inference and provides model, offline architecture, open-weights, and deployment guidance.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Offline MCP

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "offline-mcp": {
      "command": "uvx",
      "args": [
        "offline-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 6 tools correctly (Today).

Overview

The offline-mcp MCP server connects agents to local Ollama inference and open-weight model guidance for offline deployments. It can check Ollama, run prompts through an installed local model, recommend models, and explain four levels of degraded operation. Additional tools cover Africa-focused model directories and deployment on laptops, servers, Raspberry Pi, and Android. Reach for it when connectivity, cloud access, or data residency are constraints, especially in East African deployments.

Use cases

  • Run prompts through a local Ollama model
  • Check available local models before inference
  • Select open-weight models for East African language use cases
  • Plan AI deployments for Raspberry Pi or Android
  • Design fallback behavior for intermittent connectivity

Key features

  • Local Ollama status and model discovery
  • Prompt execution through local Ollama models
  • East Africa-focused open-weight model recommendations
  • Four-level degraded-mode guidance
  • Africa language model directory
  • Deployment guidance for laptops, servers, Raspberry Pi, and Android

Tools6

What Offline MCP lets your agent do. Expand a tool for its parameters.

Verified live~1.1k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

5/5 checks healthy over the last 42d

What it can do

From the 6 tools this server returned when we ran it; 6 declare their own safety hints.

Handles credentials · 1Makes network requests · 2Read-only tools · 6
Network at startup2 connections
Files written at startup11

Observed 2026-10-24 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 4h ago via OSV.dev · offline-mcp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

Last commit3d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed6Callable tools this server registers over MCP.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Offline MCP works

What offline-mcp does

The offline-mcp MCP server provides an MCP interface for local AI infrastructure built around Ollama. It combines two kinds of capability: operational access to a locally running inference service, and reference material for selecting models and planning offline deployments.

The server is aimed at environments where internet access is intermittent or unavailable. The README identifies Kenya, Tanzania, and Uganda as primary deployment contexts and describes use in clinics, schools, community offices, and other local settings. Its stated design keeps inference and community data on the device rather than sending prompts to a hosted model provider.

The package is also positioned as part of an East Africa coordination stack.

How it works

The operational path uses Ollama running locally. check_ollama_status reports whether Ollama is available and returns the models it can access. run_local_inference sends a prompt to a selected local Ollama model. The README names Llama 3.2 and Qwen 2.5 as examples of models that can run on the device, but the available choices depend on what has been installed locally.

The offline-mcp MCP server follows a local-first approach: core operations are intended to work without internet connectivity. Its reference material also describes graceful degradation, hardware-aware model selection, and a four-level degraded-mode architecture. A JSONL queue is listed among the design principles for accumulating events offline and synchronizing when connectivity returns, although no queue-specific MCP tool appears in the six-tool list.

The project describes a Raspberry Pi 4 deployment powered by a 50W solar panel and using a 256GB SD card as an example context. That example indicates the intended operating range, not a guarantee that every model or workload will run on that hardware.

Setup and configuration

Install the Python package with:

Terminal
pip install offline-mcp

Before using inference, an Ollama installation must be running locally and must have at least one usable model. The server documentation does not specify environment variables, additional configuration files, authentication settings, or a required model name.

Hardware and model selection remain deployment decisions; the included guides are intended to help compare laptop, server, Raspberry Pi, and Android options.

Tools and capabilities

Six MCP tools are documented:

  • check_ollama_status: Checks local Ollama availability and lists available models.
  • run_local_inference: Runs a prompt through a local Ollama model.
  • list_recommended_models: Recommends open-weight models for East Africa use cases.
  • degraded_mode_guide: Explains a four-level architecture for operating with reduced connectivity or capability.
  • open_weights_directory: Provides a directory of open-weight models with Africa language support.
  • local_deployment_guide: Covers deployment considerations for laptops, servers, Raspberry Pi, and Android.

Together, these tools support both immediate local inference and planning work. For example, an agent can inspect the local Ollama installation, identify suitable models, and consult deployment guidance before running a prompt.

Limitations and notes

The offline-mcp MCP server depends on Ollama for its inference tool, so local inference is unavailable if Ollama is not running or no suitable model is installed. Model performance and language coverage will depend on the selected open-weight model and the available hardware.

The README presents the project for offline and East African use cases, but it does not provide benchmarks, resource requirements for each model, or a complete hardware compatibility matrix. It also labels demo data as unsuitable for operational decisions. Treat the guides as deployment reference material and validate models, hardware, and outputs for the intended workload.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Offline MCP

offline-mcp is an MCP server that connects AI agents to a locally running Ollama installation and open-weight model guidance. Its main tools check Ollama status, list available models, run local inference, recommend models for East Africa, explain degraded operation, and provide model and deployment directories for offline environments.

Install it with `pip install offline-mcp`. After installation, run Ollama locally and make sure at least one usable model is available before using the inference tool.

No, the documented local inference path does not require an API key. It uses Ollama running on the local machine, so cloud access is not required for that path. Ollama and a suitable local model must still be installed and available.

It runs prompts through models available in the local Ollama installation. The README specifically mentions Llama 3.2 and Qwen 2.5 as examples, while separate tools recommend open-weight models and list models with Africa language support.

Yes, Raspberry Pi is an explicitly documented deployment target. The README gives a Raspberry Pi 4 with a 50W solar panel and 256GB SD card as an example, while noting deployment guidance also covers laptops, servers, and Android.

Related MCP servers

All in Conversational AI All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewOffline MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/offline-mcp?style=directory)](https://allmcps.com/mcp/offline-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/offline-mcp"><img src="https://allmcps.com/api/badge/offline-mcp?style=directory" alt="Offline MCP on AllMCPs" /></a>