OBTO
MCP-native · Glass Box

The Glass Box AI Platform.
Stop renting black boxes — start owning your intelligence.

Build with Claude Code, Codex, Cursor or any MCP client. OBTO is the MCP-native platform where the AI client you already use builds, deploys and verifies full-stack applications: a receipt on every run, restore points on every change, your code exportable to GitHub, one flat price per app.

No seat taxes, no token metering. One flat price per plan, billed per deployed application. Your AI client or API key carries the model spend.

Any LLM — Claude, GPT, Codex, Qwen
Your code, exportable to GitHub
MCP-Native from day one
Full-Stack — not just React frontends

Not locked to one model. Not locked to one AI client. Your code is yours.

How it works

The Glass Box Architecture

1. Observe

Trace every tool call, change and outcome in real time — and the token cost when the run uses your API key. No hidden operations.

2. Connect via MCP

Standardize how your models talk to your data using the open Model Context Protocol (MCP).

3. Verify

Validate the app, call the real routes, and restore any change from its restore point.

4. Own your code

Push your application's source to GitHub any time. Self-hosted runtimes are an Enterprise engagement.

Use cases

What can you build with transparent AI?

IT Helpdesk That Resolves Itself

Deploy an agent that reads tickets, queries your CMDB, and resolves common ITSM requests — without human intervention.

MCP Servers Your Whole Team Uses

Build, host, and version observable MCP tools that Claude, GPT, or Codex can call — all from one deployment target.

Spreadsheets That Clean Themselves

Extract, normalize, and load messy data using LLMs as the transformation layer. No brittle ETL scripts.

Customer Portal With AI Assistants

Role-based access portals where each user gets a tailored AI assistant scoped to their data and permissions.

Run Receipts & Audit Trail

Every agent run leaves a receipt: tool calls, changes, outcomes, and token spend when the run uses your API key — no hidden operations.

Multi-LLM Collaborative Workflows

Claude architects the backend, Codex extends the frontend — in the same app, on the same platform. Try that anywhere else.

The OBTO difference

Cure your SaaS fatigue

The Hybrid-Native Flex

Start fast on our managed cloud. When compliance or cost demands it, shift your workloads to your own Kubernetes infrastructure with zero code changes.

Open Standard Integrations

Connect to ServiceNow, databases, and internal APIs using the Model Context Protocol. No more brittle, proprietary vendor connectors.

No Data Hostages

You built the workflow, it belongs to you. We provide the engine and the built-in storage, but you retain full ownership of your IP and logic.

Open where it matters

The OBTO plugin, its skills and the MCP bootstrap server are Apache-2.0 on GitHub, and the protocol is open MCP. The hosted platform is ours to run for you. Either way, OBTO makes AI show its work: every run leaves a receipt you can read.

300M+
Monthly requests served in production
150+
Institutions onboarded on OBTO
7+
Years of production-grade infrastructure

The OBTO Ecosystem

SOFOS
Education

Transparent, AI-assisted learning and tutoring flows for universities.

Pelatis
ITSM

Agentic copilot for ServiceOps. Resolve IT tickets with fully audited actions.

MCP Tool Builder
Developers

Design, publish, and observe MCP tools for any LLM. Version-controlled.

OBTO Platform
PaaS

The core runtime to build, monitor, and scale transparent AI apps.

Platform

Platform Highlights

Multi-Model Agnostic

Run OpenAI, Anthropic, Ollama, and open-weight models side-by-side.

Agentic Orchestration

Compose tool-using agents with strict, auditable guardrails.

MCP Native

Built from the ground up to support the Model Context Protocol.

Observable Runtime

Secure execution environments with built-in logging and per-run receipts.

Deploy Agents You Can Actually Trust

Design purpose-built agents for research, automation, and ETL. Deploy them with versioned releases, enforce strict policy guardrails, and track every action with the Glass Box dashboard.

The Infrastructure of Intelligence

A complete, opinionated runtime for Agentic apps. Designed for the enterprise that wants speed today, and total architectural ownership tomorrow.

AI Workflow Builder
Orchestrate tools, models, and logic explicitly.
Glass Box Auditing
Granular telemetry, traces, and rate limits built-in.
MCP Tool Hosting
Design, host, and version MCP servers effortlessly.
Hybrid Deployment
Run in our cloud or self-host on your K8s clusters.
Enterprise Security
Secrets vault, RBAC, and strict policy engines.
Transparent Pricing
Billed per app, never per token. See exactly what every agent does.
Look inside the Glass Box

Sign in and get your personal MCP endpoint in under a minute. Connect your AI client and start building immediately.

Get your MCP endpoint →

No seat licenses. No setup. Pay only for what your agents use.

Why OBTO?

Visibility

The "Glass Receipt" ensures you never wonder why an agent made a decision or what it cost.

Standardization

Embrace MCP to break free from proprietary tool-calling silos.

Portability

Containerized architecture means your workflows can migrate in-house seamlessly.

Reliability

Policy sandboxing and deep audit trails protect your enterprise data.

Radical Price Transparency

Zero surprises. One flat price per plan, billed per deployed application — never per token, never metered. Bring your own AI client (Claude, ChatGPT, Cursor) or your own API key, and you keep your LLM spend.

Bring your own AI

Connect Claude Desktop, Cursor, or ChatGPT to OBTO's MCP endpoint — or bring your own key on OpenRouter, Anthropic, or OpenAI. You bring the model; we host the application. Billed per app, not per token.

Free

Start free — 1 application, MCP access included, basic Glass Box tracing. No card required.

Start free
Starter
Most popular
$19/mo
Your first paid step
  • 2 applications
  • ✓ Fair-use API rate limits
  • ✓ MCP access included
  • ✓ Basic Glass Box tracing
  • ✓ Community support
Get Starter
Team
$49/mo
Scale your agents
  • 5 applications
  • ✓ Higher API rate limits
  • ✓ Standard Glass Box tracing
  • ✓ Roles & audit trails
  • ✓ Email support
Get Team
Business
$149/mo
Production at scale
  • 20 applications
  • ✓ Unlimited API calls (fair use)
  • ✓ Advanced Glass Box tracing
  • ✓ Roles & audit trails
  • ✓ Priority support + SLA
Get Business
Enterprise

Beyond 20 apps? Self-hosted on your K8s, bring your own models (BYOM), custom MCP integrations, dedicated support + SLA.

Contact sales

Bring your own AI — your client or your key on OpenRouter, Anthropic, or OpenAI. See full pricing details →

Frequently asked

How is pricing calculated?

One flat price per plan, billed per deployed application — never per token. You bring your own AI, so your model spend stays with your provider, and Glass Box tracing still shows you exactly what every agent did.

Can I self-host OBTO?

Not as a self-serve option today. Self-hosting is an Enterprise engagement, scoped and supported under a separate agreement. Your application code is exportable to GitHub on every plan.

Which models and tools are supported?

Bring your own client — Claude, ChatGPT, Cursor, or any MCP client — or your own key on OpenRouter, Anthropic, or OpenAI. We use the Model Context Protocol (MCP) to standardize tool connections.

Is the "Glass Box" secure?

Visibility doesn't mean vulnerability. We never train on your data, all connections are encrypted, and we enforce strict Role-Based Access Controls.

Insights

From the OBTO blog

ARTICLE

How OBTO is Defining the AI Workforce of the Future

How transparent, observable agents are reshaping the way teams build and deploy an AI workforce.

Read article →
ARTICLE

Radical Price Transparency: Why We Bill Per App, Not Per Token

Bring your own AI and keep your model spend. OBTO charges a flat price per deployed application — see exactly how it works.

See pricing →

Stop renting. Start owning.

Deploy your first observable Agentic workflow today. Scale transparently tomorrow.