Entity Types
Praesidia manages three types of entities. Each represents a component in your AI infrastructure that needs to communicate securely with other components.
Applications
An application is any web or mobile application in your stack. This could be a frontend app, a backend service, or a microservice.
When you register an application:
- It receives a client key and client secret
- It can be configured as a client (makes requests) or a server (receives requests) in connections
- Guardrails and policies can be set for its interactions
Example: A customer-facing web application that needs to call an MCP server for AI-powered features.
MCP Servers
A Model Context Protocol server provides tools and resources to AI models. MCP servers are a critical part of modern AI infrastructure, exposing databases, APIs, and business logic to agents and applications.
When you register an MCP server:
- It receives credentials for authentication
- Praesidia acts as the authentication and authorization layer
- You can control which entities are allowed to connect and what tools they can access
- Content-aware guardrails can filter requests and responses
Example: An MCP server that provides access to a product database. You want to allow a customer agent to query products but prevent it from modifying inventory.
Agents
An agent is an AI system that can take actions. Praesidia supports two types:
- External agents: Agents running outside of Praesidia. You register them and manage their connections and security.
- Platform agents: Agents built and hosted directly on Praesidia using OpenClaw or ZeroClaw, deployed on Heroku. Full lifecycle management from creation to monitoring.
When you register an agent:
- It receives credentials like any other entity
- It can connect to applications and MCP servers
- Guardrails control what it can request and what it receives
- Policies set operational boundaries (rate limits, schedules, etc.)
Example: An AI agent that processes customer support tickets. It connects to a CRM MCP server and a knowledge base MCP server, with guardrails preventing it from accessing financial data.
Entity credentials
Every entity receives:
- Client key: A public identifier for the entity
- Client secret: A private key used for authentication
Use these credentials to authenticate requests through Praesidia's OAuth2 endpoint:
POST https://auth.praesidia.ai/oauth/token
Content-Type: application/x-www-form-urlencoded
grant_type=client_credentials
&client_id=YOUR_CLIENT_KEY
&client_secret=YOUR_CLIENT_SECRET
The response includes an access token to use in subsequent authenticated requests.