Teleport Agentic Identity Framework
The Teleport Agentic Identity Framework is a standards-driven security architecture and a reference implementation for deploying AI agents across infrastructure. It provides designs and reference implementations for safe agent adoption across infrastructure with built-in security invariants, observability, and governance. The framework is architected for the pace and scale of AI, enabling engineers to integrate security into agentic systems from the initial design phase.
As with the AI ecosystem as a whole, the Teleport Agentic Identity Framework is under development. Each component includes one of the following status categories:
- Ready: Available for production use.
- Development: Partially complete.
- Planned: Not yet it development, but on the roadmap.
Agentic Identity
You can use Teleport to issue and manage cryptographic identities for agents, including delegated identities and identities for long-running agents across all of your infrastructure.
Teleport includes the following capabilities for Agentic Identity:
| Feature | Status |
|---|---|
| Delegated Identity (Digital Twins) | Development |
| Identity for Long-Running Agents | Development |
| Identity for LLM Apps | Development |
Delegated Identity (Digital Twins)
Agents operate on behalf of principals while preserving approval/authorization workflows.
Delegation Flows
Description TODO
Session Management
Description TODO
Access Requests
Description TODO
Identity for Long-Running Agents
Durable identities for long-running agents with verification and rotation patterns.
Attestation
Description TODO
Renewal and Issuance
Description TODO
Identity for LLM Apps
Every agent has a unique cryptographic identity that can be audited.
Framework Integrations
Description TODO
Identity Provider Integrations
Description TODO
Agentic Access
You can use Teleport to manage authorization to infrastructure, services, and data with discovery of MCP servers and LLM controls, including rate limiting, load balancing, budgets, prompt/response tracking, and guardrails.
Teleport includes the following capabilities for Agentic Access:
| Feature | Status |
|---|---|
| MCP Access | Development |
| MCP Catalog | Development |
| LLM Access | Development |
MCP Access
Securely authorize and observe agent calls to databases, services, and infrastructure through MCP.
MCP Catalog
Discover MCP servers across infrastructure, track drift over time, and reduce unmanaged endpoints.
Discovery
Description TODO
Tracking Changes and Provenance
Description TODO
Access Control
Description TODO
LLM Access
Description TODO
Guardrails
Description TODO
Rate Limiting
Description TODO
Budgeting
Description TODO
Multiplexing
Description TODO
Agentic Security
Teleport provides discovery, detection, and analytics for AI agents and MCP servers to reduce shadow deployments and context poisoning attacks.
Teleport includes the following capabilities for Agentic Security:
| Feature | Status |
|---|---|
| Visibility and Discovery | Development |
| Audit and Security | Development |
Visibility and Discovery
Continuous discovery, detection, and policy violation insights for agents and MCP endpoints.
Analytics
Description TODO
Discovery
Description TODO
Audit and Security
Description TODO
Session Recording and Audit
Description TODO
Behavior Analysis
Description TODO
Scheduling and Orchestration
Integrations and SDKs for modern agentic orchestration tools enable secure identities for agentic workflows accessing resources like databases and git repositories, as well as file sharing and developer tooling.
Teleport includes the following capabilities for Scheduling and Orchestration:
| Feature | Status |
|---|---|
| Data Sharing | Planned |
| Workflows | Planned |
| Developer Experience | Planned |
Data Sharing
Description TODO
Workflows
Description TODO
Developer Experience
Description TODO