Validated IdP claims
MCP access should carry validated IdP claims before a tool call is allowed, whether the token represents an agent, workload, user, or delegated session.
AI agent governance
Datawiza Agent Gateway verifies enterprise IdP tokens and uses validated claims to make MCP access decisions before agents reach sensitive tools.

For MCP teams
MCP makes tools easy for agents to discover and call. That becomes risky when servers expose SaaS data, internal APIs, databases, tickets, code repositories, or business workflows.
MCP access should carry validated IdP claims before a tool call is allowed, whether the token represents an agent, workload, user, or delegated session.
One MCP server may expose read, write, export, and admin-style tools. Access needs to be checked at the tool and action level.
Security teams need proof of who called which tool, what policy applied, and what happened next.
Partners & integrations
Review supported identity integrations, cloud marketplace paths, and procurement channels for Datawiza Agent Gateway.
Gateway pattern
Datawiza Agent Gateway sits between agents and MCP servers. Agents authenticate with your enterprise IdP, send their access token to the gateway, and Datawiza validates the token before applying tool-level policy.
Let agents authenticate with Microsoft Entra ID, Okta, Ping, AWS IAM, or another IdP, then present signed access tokens to Datawiza for validation.
Map validated groups, scopes, app roles, and custom claims to allowed MCP servers, tools, and actions.
Validate issuer, audience, signature, expiry, scopes, and claims, then capture user, agent, tool, policy, and outcome for audit.
Architecture
Agent traffic flows through Datawiza before it reaches MCP servers. Validated IdP claims and policy become part of every tool-call decision.
Step 1
Authenticates with Entra ID, Okta, or another IdP and receives a signed access token.
Step 2
Validates issuer, audience, signature, expiry, scopes, and claims, then checks MCP server, tool, and action policy.
Step 3
Receive only approved MCP requests. Denied, approved, and approval-routed decisions are logged.
Identity providers
Deployment options
Token validation: trust the IdP token only after Datawiza verifies it.
Tool policy: allow or deny by agent, claim, MCP server, tool, action, and environment.
Audit: record who or what called the tool, which policy matched, and the outcome.
Workflow
Start with one MCP server and one agent workflow. Prove the token validation, policy, and audit path before expanding to more tools.
Comparison
IdP policy examples
Use Entra ID, Okta, or enterprise IdP group claims to distinguish finance users, managers, contractors, and service agents.
Use scopes, app roles, audiences, and custom claims as trusted identity context before MCP tools are allowed.
Send MCP access logs to your SIEM with issuer, subject, group, agent, server, tool, decision, and result.
Next step
Bring one MCP server, one agent workflow, and your IdP token requirements. We can map where token validation, policy, and audit should sit before you roll out MCP broadly.
Related tutorial
Follow the step-by-step guide for protecting an MCP server with Datawiza Agent Gateway and Microsoft Entra ID before Claude or another MCP client reaches sensitive tools.