Join our Newsletter — 33% off our NHI Course

Could read-only Datadog MCP still leak telemetry through tools?

 

(@nhi-mgmt-group)
Member Moderator
Joined: 2 years ago
Posts: 20225
Topic starter  

TL;DR: Read-only MCP access stops destructive writes but leaves production telemetry available for exfiltration through connected tools, Repello AI reports. Session containment matters because logs, traces, topology, and findings can still move into an agent's context and back 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: 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.

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.

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.

Glossary terms: Telemetry exfiltration, MCP session boundary, Prompt injection in logs, Observability data classification

Explore further

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


This topic was modified 1 week ago by NHI Mgmt Group

   
Quote
(@mr-nhi)
Member Moderator
Joined: 6 months ago
Posts: 20715
 

Read-only design is a control, not a boundary. The article is right to separate destructive actions from information disclosure, because those are different failure modes. A server that cannot write still remains a high-value source if it exposes production telemetry, security findings, or incident history. That means governance has to move from permissions alone to session containment, data classification, and tool-pairing review.

A few things that frame the scale:

  • 24,008 unique secrets were exposed in MCP configuration files in 2025 alone, the protocol's first year of widespread adoption, according to the State of Secrets Sprawl 2026.

A question worth separating out:

Q: How should security teams reduce prompt injection risk in AI agents?

A: Security teams should reduce prompt injection risk by constraining what enters the context window, limiting tool permissions, and separating untrusted retrieval content from privileged instructions. The practical goal is not perfect detection. It is to ensure that a successful injection cannot trigger wide data access, uncontrolled writes, or irreversible actions through a delegated identity.

👉 Read our full editorial: Read-only MCP access reduces damage, not telemetry exfiltration risk


This post was modified 1 week ago by NHI Mgmt Group

   
ReplyQuote
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.