Unizo MCPs

Connect all Unizo platform actions directly to LLM clients and agents via the standardized Model Context Protocol.

The Model Context Protocol (MCP) is an open protocol that standardizes how AI applications provide context to Large Language Models (LLMs).

Unizo provides production-ready MCP servers for each linked account, giving your AI agents direct access to all Unizo platform actions across 100s of integrations and thousands of tools. See the complete list at /docs/connectors.

Simplified Authentication: Authentication to third-party providers is completely abstracted - you only need your Unizo API key and account ID to access all integrated systems. Accounts must be linked beforehand through the Unizo Dashboard or via auth links.

Unizo's Action Layer - MCP ready

Unizo gives you access not only to remote-hosted MCP servers, but also to other flexible interfaces for integrating actions into your AI Agents, whatever stack you use to build your agent:

Multiple Integration Options

Use the MCP server, the Actions RPC endpoint, the Unified API endpoints, or even A2A Agents, all leveraging the same linked account and authentication. You can also access the Unizo AI Toolset to use specialized LLM tools.

Accuracy & Context Engineering

Enhance and dynamically optimize your agent's toolset with Meta Tools for real-time discovery, curation, and augmentation of available actions. Every tool has structured input/output schemas and documentation, making it easy for both developers and LLMs to understand how and when to use each capability, so your agent can adapt as your use cases grow without overwhelming the model.

Customizable & Extensible

Easily toggle tools on or off, customize your toolset, or create your own connectors using Unizo's Integration Engine and Integration Agent.

Purposeful Action Design

Unizo tools aren't necessarily direct wrappers to single API endpoints—many are mapped to high-value, context-optimized actions tailored to common business use cases, making them efficient and LLM-friendly, even if the underlying provider API is large, complex and easily misunderstood by LLMs.

note

Unizo empowers your agents to discover, understand, and execute real-world business actions with minimal setup and maximal flexibility, all secured by unified, enterprise authentication.

How Unizo MCP Works

flowchart LR
    Client[LLM Client or Agent]
    UnizoMCP[Unizo MCP Server]
    Toolset[Unizo Tool Catalog]
    Providers[Connected SaaS APIs]
    IntegrationConfig[Integration & Account Settings]

    Client -->|MCP Streamable HTTP| UnizoMCP
    UnizoMCP -->|tools/list| Toolset
    UnizoMCP -->|tools/call| Providers
    Providers --> UnizoMCP
    UnizoMCP --> Client
    IntegrationConfig -.->|Defines available tools| Toolset

    style UnizoMCP fill:#10b981,stroke:#059669,color:#fff
    style Toolset fill:#10b981,stroke:#059669,color:#fff
    style IntegrationConfig fill:#10b981,stroke:#059669,color:#fff

The Unizo MCP Server dynamically generates its tool catalog based on your account's configured integrations and enabled actions in the Unizo dashboard.

Key Features

• Account Specific: Each linked account gets its own MCP server endpoint
• Streamable HTTP Transport: Uses the modern HTTP-based MCP transport (not SSE)
• Complete Platform Access: All Unizo actions available as MCP tools, including custom integrations
• Action Selection Control: Respects integration configuration - only enabled actions are returned
• Production Ready: Authentication, rate limiting, and security built-in

Getting Started

🚀

Quickstart

Get started with cURL examples and basic MCP calls

🛡️

Authentication

Learn about headers, authentication, and security

🖥️

App Guides

Connect Claude, ChatGPT, Cursor, and other LLM clients

💻

Framework Guides

Integrate with SDKs like OpenAI Agents, Vercel AI, and more

Integration Options

Unizo MCP can be integrated in two ways, depending on your use case:

Applications & IDEs (No-Code/Low-Code)

Use these when you want to directly interact with integrated systems through conversational AI without writing code, eg. Claude Desktop, n8n

SDKs & Frameworks (Programmatic)

Use these when building custom AI applications, agents, or products that need to integrate with multiple systems. This pertains to libraries that support the MCP protocol, such as Anthropic SDK, Pydantic AI, OpenAI Agents SDK, LangChain, CrewAI, Vercel AI SDK and more.

Next Steps

note

All communication uses Streamable HTTP transport, not Server-Sent Events (SSE). This provides better reliability and easier debugging for production deployments.

Ready to connect your AI agents to Unizo? Start with our Quickstart Guide or jump directly to your preferred client or framework.

For more information about Unizo's platform capabilities, see our AI Tools documentation.