Frequently asked questions

Praesidia is the control plane for AI agents. It authenticates, governs, and monitors every interaction between your applications, AI agents, and MCP servers from a single platform. Instead of stitching together a gateway, a guardrails service, a cost tracker, an observability tool, and a compliance platform, you get all six control domains — identity, guardrails, cost, governance, observability, and orchestration — in one place.

Any team running AI agents in production — from startups shipping their first agent to enterprises governing a fleet across departments. If you have applications, agents, or MCP servers talking to each other or to external services, and you need to control who can call what, what they can say, what it costs, and prove it to an auditor, Praesidia is built for you.

Most teams run AI on a patchwork of separate tools — one vendor for the gateway, another for observability, another for guardrails, another for cost tracking, another for compliance — and then maintain the glue between them. Every seam is a potential security gap, a surprise bill, and an audit headache. Praesidia replaces that sprawl with one control plane: one platform, one audit trail, one bill.

Traditional IAM thinks in terms of identities and permissions on individual resources. Praesidia thinks in terms of relationships between AI entities, with content-aware guardrails. Security lives at the connection between two entities, not on the entities themselves — so you control not just who can talk to whom, but what they are allowed to say and do in both directions.

Three entity types, all first-class citizens: Applications (web and mobile apps), MCP Servers (Model Context Protocol servers), and Agents (external agents, or agents you build and deploy through the platform). Each one gets its own credentials, configurable guardrails, and operational policies.

Identity & Access (credentials for every agent, plus SSO, SCIM, MFA, and role-based access for your team); Guardrails & Content Safety (inspect and act on every request and response); Governance & Compliance (tamper-evident audit trails and the controls behind major frameworks); Cost & FinOps (attribute spend and set hard caps); Observability & Audit (logs, metrics, and traces, exportable to your SIEM); and Connect, Build & Orchestrate (govern connections, chain workflows, and deploy agents). They are designed to work together on one platform.

A connection defines a trusted relationship between two entities. It specifies which entities can communicate and what controls — guardrails and policies — govern that communication. Connections can be simple point-to-point or orchestrated into multi-layered, multi-step setups.

Guardrails are content-level controls that inspect what is said or requested in messages between entities — they can block, redact, or warn on things like prompt injection, sensitive data (PII), and policy violations. Policies are operational controls like rate limits, geo-restrictions, volume caps, time-based access, and IP allowlists. Both apply per entity and per direction — as a client and as a server — so you control what goes in and what comes out.

Controls apply in both directions on every connection. Praesidia inspects what an entity sends as a client and what it returns as a server, so you can stop a bad request before it reaches a downstream service and catch a non-compliant or unsafe response before it comes back. One connection, two enforcement points.

Each entity registers with Praesidia and receives its own credentials (a client key and secret). Every request between connected entities is authenticated through Praesidia, so only authorized entities can communicate. Your team members authenticate separately through standard options like SSO, MFA, and passkeys.

Yes. You can connect external agents you already run, or define and deploy OpenClaw and ZeroClaw agents directly from the platform — no local development and no manual deployment. Configure the agent, pick a cloud provider (such as Heroku, Render, Hetzner, or Scalingo), and ship it. Every agent gets full lifecycle management from creation to monitoring.

Yes. Go beyond single connections and chain apps, agents, and MCP servers into multi-step pipelines on a visual canvas, with security enforced at every hop. You can build workflows by hand or describe what you want and generate a starting workflow, then run, schedule, and monitor them with the same guardrails, policies, and audit trail applied throughout.

Yes — Model Context Protocol servers are a first-class entity type. Praesidia provides the authentication and authorization layer your MCP servers need, applies guardrails and policies to their tool calls, and records them in the audit trail. You can govern the MCP servers you host and the ones your agents connect out to.

If you choose to publish them. You can register public agents and MCP servers that others can find and connect to, building an ecosystem of reusable AI services within your organization or across the community. Discovery is opt-in — entities stay private unless you publish them.

Yes. Praesidia is bring-your-own-key and model-agnostic — connect the LLM providers you already use with your own keys. You are not locked into a single model or vendor, and your provider keys stay under your control.

Praesidia attributes spend to every agent, team, connection, and workflow, so you can see exactly where your AI budget is going instead of getting a single opaque provider bill. On top of that visibility you can set budgets and hard spend caps that stop runaway costs before they reach your invoice.

Yes. You can define budget policies with hard spend caps that act as an enforcement control, not just an after-the-fact alert. Budgets can be scoped so a runaway agent or workflow is stopped at the cap rather than discovered on next month's bill.

Yes. Usage and cost are tracked per connection and rolled up so you can break spend down by agent, team, and workflow. That makes it straightforward to charge back internally, spot the most expensive flows, and forecast cost as you scale.

Praesidia is multi-tenant by design. Every entity, connection, policy, and log belongs to your organization, and access is scoped to your organization on every request. Members only see and act on data within the organizations they belong to, governed by role-based access control.

For the people who manage your AI estate, Praesidia supports SSO (SAML and OIDC), SCIM provisioning, multi-factor authentication (TOTP and backup codes), and passkeys. Access is governed by role-based access control with organizations and teams, so you can give the right people the right level of access and provision or deprovision them automatically.

Praesidia is built to give you the controls and evidence behind the standards your compliance team asks about — SOC 2, GDPR, the EU AI Act, ISO/IEC 42001, the NIST AI Risk Management Framework, and the OWASP Top 10 for LLMs — so you are ready when auditors ask. The platform is built with compliance in mind from day one, guided by our CISO who led Romania's first ISO/IEC 42001 AI management certification.

Every request, response, and policy decision is logged, giving you full visibility into what your AI infrastructure is doing in real time. Audit trails are tamper-evident, so the record holds up when it matters, and you can export logs, metrics, and traces to the monitoring and SIEM tools you already run.

Praesidia is security built in Europe, for the world. The team combines over a decade of experience building authentication and access-management platforms for demanding enterprise environments with deep AI governance expertise.

Yes. During the beta phase, Praesidia is completely free for all users, and there is an open-source version for individual developers. No credit card required to get started.

Yes. The core components are Apache-licensed and open source — fully transparent and community-driven. Commercial SaaS and enterprise packages are available on top of the open-source core for teams that need additional features.

Enterprise capabilities build on the same control plane — SSO and SCIM for your identity provider, custom roles and granular permissions, advanced analytics, and the governance and audit features your security and compliance teams need to operate AI at scale. Get in touch through the platform to discuss enterprise access.

Sign up at app.praesidia.ai, register your first entity (an app, MCP server, or agent), and create a connection. You can have authenticated, governed AI interactions running in minutes. The documentation has step-by-step guides for each entity type.

Minutes, not months. The flow is three steps: register your entities, define which ones can talk to each other, and apply guardrails and policies to those connections. You can start with a single connection and add controls, workflows, and more entities as you grow.

Praesidia offers a Python SDK (install via pip install praesidia-server-sdk), CLI tools, and simple credential management. Integrations with frameworks like LangChain and CrewAI are planned.

No. You can start with one connection or one entity and expand from there. Because logs, metrics, and traces export to the monitoring and SIEM tools you already run, Praesidia fits alongside your existing stack while you consolidate onto a single control plane at your own pace.