This server provides offline/local AI inference infrastructure via Ollama, open-weight model recommendations, and deployment/degraded-mode guidance for low-connectivity East Africa contexts.
Check whether Ollama is running locally and list available models.
Run prompts through a local Ollama model, optionally choosing the model.
List recommended open-weight models for East Africa use cases, with optional use-case and RAM filters.
Get a guide for operating AI systems when cloud connectivity fails.
Browse a directory of open-weight models suitable for East Africa civic use cases.
Get local deployment guidance for devices such as laptops, servers, Raspberry Pi, and Android.
Allows running local inference using Ollama models, checking Ollama status, and listing available models on the local machine.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@offline-mcp run local inference: 'hello in Swahili?'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Install: pip install offline-mcp · Use with any MCP client.
Local AI inference infrastructure — Ollama wrapper, open weights directory, degraded-mode guide for East Africa.
Why: Never assume OpenAI survives, Anthropic stays accessible, or export controls disappear. This matters more in Africa than anywhere else.
1st world equivalent: Ollama, LLaMA, Mistral local deployment
"If you take the deal, you're going to be exploited. If you don't take it, you're going to die."
— Frank Ssekamwa, Ugandan digital rights expert
Across the Global South, AI and health data from communities is being extracted, processed abroad, and used to build models whose value flows away from the communities that generated it.
offline-mcp is the sovereignty floor of the East Africa coordination stack.
When this runs on a Raspberry Pi 4 with a 50W solar panel and a 256GB SD card:
Health data stays in the clinic. Health guidance comes from local models.
Land records stay in the land office. Queries don't touch foreign servers.
Civic data stays in the county. AI assistance runs without internet.
No API key. No cloud dependency. No data leaving the community.
The models available via offline-mcp (Llama 3.2, Qwen 2.5) run entirely on device.
Community data used to generate AI outputs creates no dataset sent back to model providers.
This is not a privacy feature. It is the architectural foundation of digital independence.
Related MCP server: Ollama MCP Wrapper
This server implements patterns validated by peer-reviewed research on offline-first AI for bandwidth-constrained environments:
arXiv:2603.03339 (2026) — Offline-First LLM Architecture for Adaptive Learning in Low-Connectivity Environments — confirms that meaningful AI support is achievable with hardware-aware model selection when designed for infrastructure-limited deployment. Key finding: offline-first is a complementary paradigm, not a compromise.
Design principles applied:
Local-first: all core operations execute without internet connectivity
Graceful degradation: reduced functionality beats no functionality
JSONL queue: events accumulated offline sync when connectivity returns
Hardware-aware: tool selection adapts to available compute
East Africa context: Kenya, Tanzania, Uganda — rural areas with intermittent connectivity represent the primary deployment target. This server is not designed for ideal conditions. It is designed for real ones.
pip install offline-mcpTool | Description |
| Check if Ollama is running locally and list available models |
| Run a prompt through a local Ollama model |
| Best open-weight models for East Africa use cases |
| 4-level degraded mode architecture for offline operation |
| Directory of open-weight models with Africa language support |
| Deployment guide for laptop, server, Raspberry Pi, Android |
Runs on a 50W solar panel + Raspberry Pi 4. Viable for rural Kenya clinics, schools, and community offices.
MIT © Gabriel Mahia | contact@aikungfu.dev
This MCP server is part of the Kenya coordination infrastructure.
Connect it to africa-coord-bus —
the coordination event bus that routes signals between domains automatically.
pip install africa-coord-busAll servers: pypi.org/user/gmahia Live demo: coord-cascade-demo
MIT licensed. Feedback via GitHub Issues only — pull requests are not accepted. Demo data is labeled DEMO and is not suitable for operational decisions. Full policy: docs/architecture/IP_POLICY.md. Security reports: see SECURITY.md.
Install & run: pip install reli-cli && reli list — the MCP servers on the official MCP Registry under io.github.gabrielmahia
Evaluate any model on Swahili agent tasks: kipimo · dataset · leaderboard
Coordinate across servers: africa-coord-bus — offline-first event bus with a built-in Kenya routing table
Datasets: huggingface.co/gmahia · Docs hub: nairobi-stack
Model-agnostic by design: closed APIs, open-weight models, and small distilled models are all first-class citizens.
Check if Ollama is running locally and list available models.
Inputs: no named parameters. Returns: object
Guide for operating AI systems when cloud connectivity fails.
Inputs: no named parameters. Returns: object
List recommended open-weight models for East Africa AI use cases.
Inputs: use_case, max_ram_gb. Returns: object
Guide to deploying local AI inference on modest hardware in Kenya/East Africa.
Inputs: device_type. Returns: object
Directory of open-weight AI models suitable for East Africa civic use cases.
Inputs: use_case. Returns: object
Run a prompt through a local Ollama model.
Inputs: prompt (required), model. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Each tool has a clearly distinct purpose: status checking, running inference, listing recommended models, providing a directory, and offering guides. No overlap in functionality.
All names use snake_case and follow a verb_noun or adjective_noun pattern, with minor variation between imperative verbs and descriptive nouns. Consistent enough for clear identification.
Six tools is well-scoped for an offline AI inference and guidance server, covering core operations and supplementary resources without bloat.
The tool set covers the full expected workflow: status check, inference, model recommendations, directory, and guides for deployment and degraded mode. No obvious gaps.
Open-model LLM inference for agents. Pay per call in USDC via x402 or API key. First call free.
AI LLM with Gemini, MiniMax, Replicate, OpenRouter. Vision, search, code review. USDC on Base.
150+ vertical AI expert bots as agent tools. $1 bots run on YOUR machine - your data stays yours.
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
