Bring Self Hosted
to Cursor
Learn how to connect LocalAI to Cursor and start using 19 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the LocalAI MCP Server?
Connect your LocalAI instance to any AI agent and leverage powerful multimodal capabilities directly from your own infrastructure.
What you can do
- Text Generation — Use
chat_completionsoranthropic_messagesto generate text using local models with full OpenAI or Anthropic compatibility. - Image Synthesis — Create visual content from text prompts using the
generate_imagetool, supporting custom sizes and negative prompts. - Audio Processing — Convert speech to text with
transcribe_audioor generate natural-sounding speech from text usingtext_to_speech. - Advanced Search & RAG — Generate vector embeddings with
create_embeddingsand improve search relevance using thererank_documentstool. - Computer Vision — Analyze images and identify elements using the
detect_objectstool. - System Management — Monitor your instance with
list_models,get_system, andgetVersionto ensure optimal performance.
How it works
- Subscribe to this server
- Provide your LocalAI Base URL (e.g.,
http://localhost:8080) and optional API Key - Start interacting with your local models through Claude, Cursor, or any MCP client
Who is this for?
- Privacy-Conscious Developers — Run powerful AI workflows without sending sensitive data to third-party cloud providers.
- AI Researchers — Easily test and swap different local models for chat, vision, and audio tasks.
- DevOps Engineers — Integrate local AI capabilities into internal tools and automated pipelines.
Built-in capabilities (19)
Generate messages (Anthropic compatible)
Install a model from the gallery
Generate chat completions (OpenAI compatible)
Create text embeddings
Detect objects in an image
Analyze face demographics
Identify faces (1:N)
Enroll a face into the store
Verify faces (1:1)
Supports negative prompts using | separator. Generate images from text prompts
Check authentication state and providers
View personal token usage
View system and backend info
Get LocalAI version
List available models
Generate open responses
Rerank documents based on a query
Convert text to audio (TTS)
Pass the file data or path as required by your LocalAI setup. Transcribe audio to text
Why Cursor?
Cursor's Agent mode turns LocalAI into an in-editor superpower. Ask Cursor to generate code using live data from LocalAI and it fetches, processes, and writes. all in a single agentic loop. 19 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.
- —
Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context
- —
Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards
- —
MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment
- —
VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools
LocalAI in Cursor
LocalAI and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect LocalAI to Cursor through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for LocalAI in Cursor
The LocalAI MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 19 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Cursor only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
LocalAI for Cursor
Every tool call from Cursor to the LocalAI MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I see which AI models are currently installed on my LocalAI server?
You can use the list_models tool. It will return a complete list of all available models on your instance, including their IDs and capabilities.
Does this server support generating images locally?
Yes! By using the generate_image tool, you can provide a prompt and optional size to generate images directly on your hardware using supported models like Stable Diffusion.
Can I use this to transcribe audio files into text?
Absolutely. The transcribe_audio tool allows you to send audio data or file paths to your LocalAI instance for high-quality transcription using models like Whisper.
What is Agent mode and why does it matter for MCP?
Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
Where does Cursor store MCP configuration?
Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
Can Cursor use MCP tools in inline edits?
No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
How do I verify MCP tools are loaded?
Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.
Tools not appearing in Cursor
Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
Server shows as disconnected
Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.
Explore More MCP Servers
View all →
HubSpot Operations Hub
6 toolsManage workflows, CRM properties, pipelines, owners, and property groups through natural conversation.
DeepSource
14 toolsAutomate code quality monitoring via DeepSource — analyze issues, vulnerabilities, metrics, and report cards directly from any AI agent.
JotForm
10 toolsManage forms, submissions, and reports via JotForm API.
Eurostat Demographics — EU Population & Labor
6 toolsEU demographics and labor market: population by age and sex, monthly unemployment rates, employment data, immigration by citizenship, life expectancy, and minimum wages for all 27 EU member states.