Join our Newsletter — 33% off our NHI Course

Datadog's read-only MCP model: what it fixes and what it misses

 

(@nhi-mgmt-group)
Member Moderator
Joined: 1 year ago
Posts: 19129
Topic starter  

TL;DR: Read-only MCP access removes destructive write actions but still leaves production telemetry exposed to exfiltration through connected tools, according to Repello AI. The real control problem is session-level containment, because data can still flow from logs, traces, topology, and findings into an agent’s context and then out again.

Editorial analysis by NHI Mgmt Group, based on content published by Repello AI: “Datadog MCP Server Security: Read-Only Is Not the Same as Safe”.

Key questions

Q: What breaks when an MCP server is read-only but connected to outbound tools?

A: Read-only stops the server from making changes back to its source system, but it does not stop the agent from forwarding what it reads somewhere else.

Q: Why does read-only access not eliminate exfiltration risk in agent sessions?

A: Because exfiltration is usually a read followed by a forward.

Q: How should teams decide what telemetry an AI agent is allowed to see?

A: Start with least-necessary observability, not full-fidelity access.

Practitioner guidance

  • Scope the MCP application key to the minimum telemetry surface Use a read-only key limited to the specific services or environments the agent actually needs, rather than granting broad observability access that turns debugging into wholesale telemetry collection.
  • Redact sensitive fields before telemetry enters context Strip tokens, customer data, and other sensitive values on the response path so the model never receives them in the first place, rather than trying to clean them up after ingestion.
  • Review connected tools as a single session graph Assess which outbound-capable tools sit beside observability access in the same agent session, because the exfiltration path is created by the combination, not by either server alone.

Bottom line: Read-only MCP access reduces destructive change risk, but it does not stop an agent from moving sensitive telemetry into another tool.

Explore further

View Full Forum →  |  NHI Foundation Course →  |  Our Services →  |  Read the full analysis →



   
Quote
Share:

Free weekly newsletter

Subscribe to the NHI & AI Identity Journal

The latest on NHI and Agentic AI security – articles, research, breaches, news and events every week.

Bonus 33% off our NHI Course when you subscribe.