Notifications
Clear all
Topic starter
19/08/2026 3:29 pm
TL;DR: Agent-mediated access is now exposing identity governance, consent, and privilege boundaries that traditional IAM workflows were not built to supervise, according to Descope; its MCP Server is now available as a Claude Connector and ChatGPT Plugin, exposing 23 identity tools for reading documentation, managing users and tenants, reviewing audit logs, and changing authentication flows through natural language.
NHIMG editorial — what this means for AI and NHI governance
By the numbers:
- 80% of organisations report their AI agents have already performed actions beyond their intended scope, including accessing unauthorised systems, inappropriately sharing sensitive data, and revealing access credentials.
Questions worth separating out
Q: How should security teams govern AI assistants that can make infrastructure changes?
A: Treat the assistant as a privileged non-human identity with narrowly scoped write permissions, explicit ownership, and mandatory approval for every state-changing action.
Q: Why do MCP servers create new IAM and NHI governance risks?
A: MCP servers expose tools in a way that can bypass the access assumptions many teams built for human-operated applications.
Q: What breaks when an AI assistant can manage users, tenants, and auth flows?
A: The normal separation between inquiry and administration breaks down.
Practitioner guidance
- Inventory every MCP tool by risk tier Classify each tool as read, write, or escalation-capable before enabling it for production use, and require separate approval for tools that can change users, tenants, flows, or auth keys.
- Split conversational intent from administrative execution Keep model prompts, approval prompts, and backend writes on separate control paths so a natural-language request cannot directly become a privileged change without explicit review.
- Restrict write access to identity infrastructure Default assistants to read-only access for documentation and audit tasks, then allow write operations only for narrowly defined admin roles with strong logging and rollback controls.
What's in the full announcement
Descope's full post covers the operational detail this post intentionally leaves for the source:
- The exact Claude and ChatGPT connection steps for enabling the MCP Server in each supported client.
- The full 23-tool catalog with read and write scope details for identity operations.
- The auth and consent flow mechanics for tenant selection and elevated access requests.
- The platform-specific setup guidance for agents outside the Anthropic and OpenAI ecosystems.
👉 Read Descope's post on Claude and ChatGPT access to its MCP Server →
MCP identity tools in Claude and ChatGPT: what changes for teams?
Explore further
View Full Forum → | NHI Foundation Course → | Our Services →
19/08/2026 4:13 pm
Agent-mediated identity administration turns privilege into a conversational control problem. When an assistant can inspect configuration, manage tenants, and modify authentication flows, the security question is no longer only who has access. It becomes who can cause access to change through a model-mediated request path. That expands the blast radius of a single interaction and forces identity teams to govern the conversation as carefully as the backend system.
A few things that frame the scale:
- Only 52% of companies can track and audit the data their AI agents access, leaving 48% with a complete blind spot for compliance and breach investigation, according to AI Agents: The New Attack Surface report.
- 96% of technology professionals identify AI agents as a growing security threat, and 66% believe this risk is immediate.
A question worth separating out:
Q: Which controls matter most for AI assistants in identity operations?
A: Tool scoping, consent design, auditability, and revocation. If those controls are weak, an assistant can become an unreviewed administrative proxy rather than a bounded helper, especially when it can reach both read and write functions in the same session.
👉 Read our full editorial: Claude and ChatGPT access to MCP identity tools changes governance
