Vurb.ts is a TypeScript framework for the Model Context Protocol (MCP) that introduces the MVA (Model-View-Agent) architectural pattern. It replaces raw JSON responses with structured perception packages — validated data, domain rules, server-rendered charts, and explicit action affordances — so AI agents perceive and act on data deterministically instead of guessing.

What is MVA (Model-View-Agent)?

MVA is a new architectural pattern created by Renato Marinho at Vinkius Labs. It replaces MVC's human-centric View with a Presenter — an agent-centric perception layer. The Model validates with Zod, the Presenter adds domain rules, UI blocks, affordances, and guardrails, and the Agent (LLM) consumes structured output to act deterministically.

How is Vurb.ts different from the official MCP SDK?

The official MCP SDK (@modelcontextprotocol/sdk) provides the protocol transport layer — stdin/stdio, HTTP. Vurb.ts builds on top and adds: MVA architecture with Presenters, action consolidation (5,000+ ops behind one tool), Zod validation with .strip(), tRPC-style middleware, self-healing errors, server-rendered UI blocks (ECharts, Mermaid), cognitive guardrails, state sync with cache signals, TOON encoding for 40% fewer tokens, and a type-safe tRPC-style client.

Is Vurb.ts free and open source?

Yes. Vurb.ts is open source under the Apache 2.0 license. It is free to use in personal and commercial projects. Built and maintained by Vinkius Labs.

What is action consolidation in Vurb.ts?

Action consolidation lets you group 5,000+ operations behind a single MCP tool using a discriminator enum. Instead of 50 separate tools flooding the LLM prompt, the agent sees ONE tool with actions like users.list, billing.refund. This reduces token usage by 10x and eliminates tool-selection hallucination.

What are cognitive guardrails in Vurb.ts?

Cognitive guardrails (.agentLimit()) prevent large datasets from overwhelming the AI context window. When a query returns 10,000 rows, the guardrail automatically truncates to a safe limit (e.g., 50 items) and injects guidance like "Showing 50 of 10,000. Use filters to narrow results." This prevents context DDoS and reduces costs by up to 100x.

Does Vurb.ts work with Claude, GPT, and other LLMs?

Yes. Vurb.ts is LLM-agnostic. It follows the Model Context Protocol standard, supported by Claude, GPT-5.2, Gemini, and any MCP-compatible client. Structured perception packages work with any LLM that processes text.

What languages and runtimes does Vurb.ts support?

Vurb.ts is written in TypeScript and runs on Node.js >= 18. It requires TypeScript >= 5.7 for full type inference. All APIs are fully typed with generics, providing autocomplete and compile-time safety.

The Express.js for MCP Servers.

Type-safe tools · Presenters that control what the LLM sees · Built-in PII redaction · Deploy once — every AI assistant connects.

30-Second Quickstart →

The MVA Pattern

Works with every MCP-compatible AI client:

ClaudeDesktop & Code

CursorIDE

CodexOpenAI

VS Code+ Copilot

WindsurfIDE

ClineTerminal

UNDERSTAND THE DIFFERENCE

MCP is the protocol. MVA is the architecture.
Together, they are Vurb.ts.

PROTOCOL

MCP

Model Context Protocol

An open standard for how AI agents talk to external tools. It handles transport, message format, and discovery. Think of MCP as the wire — it doesn't tell you how to build what's on the other end.

ARCHITECTURE

MVA

Model — View — Agent

A new architectural pattern for structuring what agents actually see. The Model owns your data. The View shapes it with domain rules and affordances. The Agent declares typed, safe actions. That's the whole contract.

=Vurb.tsA TypeScript framework for building production-grade MCP servers.

WHY MVA

Agents write your MCP servers.
MVA makes sure they get it right.

With the raw MCP SDK, you're wiring transports, writing JSON schemas by hand, and handling errors from scratch. Vurb.ts takes care of the protocol so you can focus on your business logic.

LEARNING CURVE

Skip the protocol deep-dive

You follow the same pattern every time — Model defines data, View shapes what agents see, Agent declares actions. Vurb.ts handles the MCP plumbing.

CONSISTENCY

Same structure, every server

Typed schemas, domain rules, explicit affordances — every Vurb.ts server follows the same contract. Pick up any project and know where everything lives.

AGENT-FIRST

Built for Cursor, Claude & Copilot

MVA gives coding agents a clear, repeatable target. Consistent conventions mean they write better code — and you spend less time fixing it.

SECURITY

SECURE BY DEFAULT

The MCP spec leaves security to you.
Vurb.ts ships it built-in.

The MCP SDK handles transport and messages. Auth, validation, access control? That's on you.

Vurb.ts ships with Zod schema validation on every input and a middleware pipeline for auth, rate limiting, and tenant isolation — ready to plug in, not build from scratch.

Security is part of the framework, not something you bolt on later.

OBSERVABILITY

Know exactly what every tool does, every time.

Structured Logs

Hook into tool lifecycle events and emit structured logs — input, output, duration, error context — to whatever backend you're already using.

Metrics

Track latency, throughput, and error rates per tool through the middleware pipeline. Works with Prometheus, Datadog, or whatever you're running.

Audit Traces

See exactly which data was accessed, which rules fired, and which actions were suggested. Built for teams that need audit trails.

Error Recovery

Every tool gets its own error boundary. When something breaks, you know exactly where and why — no more guessing.

WHAT CHANGES

Without MVA vs With MVA

Every line is a capability that ships in Vurb.ts today. Not a roadmap.

Without MVA

With MVA (Vurb.ts)

Tool surface

50 individual tools. LLM sees every one. Token explosion.

Action consolidation — 5,000+ operations behind ONE tool via discriminator. 10× fewer tokens.

Response shape

JSON.stringify() — the AI parses and guesses.

Structured perception — validated data + domain rules + UI blocks + action affordances in every response.

Domain context

None. 45000 — dollars? cents? yen?

System rules travel with the data. The AI knows it's cents. Always.

Next actions

AI hallucinates tool names and parameters.

Agentic HATEOAS — .suggest() with explicit affordances grounded in data state.

Large datasets

10,000 rows dumped into context. OOM crash.

Cognitive guardrails — .agentLimit() truncation + filter guidance. Context DDoS eliminated.

Security

Internal fields leak to LLM. password_hash exposed.

Egress Firewall — Zod .strict() rejects undeclared fields at RAM level. Automatic.

Visualizations

Not possible. Text-only responses.

Server-Rendered UI — ECharts, Mermaid diagrams, tables — compiled server-side. Zero hallucination.

Routing

switch/case with 50 branches.

Hierarchical groups — platform.users.list — infinite nesting with file-based autoDiscover().

Error recovery

throw Error — AI gives up or hallucinates a fix.

Self-healing — toolError() with recovery hints + suggested retry args.

Token cost

Full JSON payloads every call. Bills compound.

TOON encoding — toonSuccess() reduces response tokens by ~40%.

Type safety

Manual casting. No client types. Runtime crashes.

tRPC-style client — createVurbClient() with full end-to-end inference.

SEE THE FULL COMPARISON WITH CODE EXAMPLES →

TELL YOUR AI AGENT

"Build an MCP server for invoice management with Presenters, PII redaction on customer SSN, tenant isolation middleware, and affordances for payment actions."

Open in Claude Open in ChatGPT

ECOSYSTEM

Deploy
anywhere.
Generate from
anything.

The same ToolRegistry runs across Stdio, HTTP/SSE, and serverless runtimes without code changes. Auto-generate fully typed MCP tools from your existing infrastructure.

// DEPLOY TARGETS

Vinkius Cloud — native deployment with vurb deploy. Zero config, edge-ready, built-in auth and observability.
Vercel Edge Functions — fast cold starts in a Next.js route.
Cloudflare Workers — D1, KV, R2 bindings from 300+ edge locations.
AWS Lambda — Step Functions connector.

// DATA CONNECTORS

Prisma Generator — CRUD tools with field-level security from your schema.
OpenAPI Generator — typed tools from any REST API.
n8n Connector — n8n workflows as MCP tools.

GET STARTED

You define the architecture.
Your AI agent writes the code.

Vurb.ts gives you typed schemas, structured AI perception, built-in PII redaction, and governance — all out of the box. Ship a SKILL.md, not a tutorial.

TELL YOUR AI AGENT

"Build a patient records MCP server with Prisma. Redact SSN and diagnosis. Add an FSM that gates discharge tools until the attending physician signs off."

Try in Claude Try in ChatGPT

BUILD YOUR FIRST MCP SERVER →