Join our Newsletter — 33% off our NHI Course

Where does Claude Code's name-keyed approval leave standing grants exposed?

 

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

TL;DR: The risk is a standing grant that can outlive the review, with Repello AI reporting that a server name can keep approval alive after the command changes. Claude Code needs configuration diffs and tighter approval scope so startup paths do not become silent execution points.

Editorial analysis by NHI Mgmt Group, based on content published by Repello AI: “A Trusted Name Is Not a Trusted Command: MCP Approvals in Claude Code”.

Key questions

Q: Why do agentic developer tools make standing trust grants riskier than traditional approvals?

A: Because the tool can act at runtime without a new user decision, so a durable grant can authorize future behaviour the user never saw.

Q: How should security teams evaluate MCP trust in shared repositories?

A: They should treat the configuration file as an execution surface and assume any collaborator with commit access can alter what runs under an already approved name.

Q: What breaks when an MCP approval is tied to server name instead of command definition?

A: The approval no longer guarantees that the reviewed code is the code that runs.

Practitioner guidance

  • Prefer the narrow MCP grant Approve only the specific server in front of you instead of the standing project-wide option when the toolchain supports it.
  • Inspect .mcp.json on every change Review the repository file on each pull, merge, or branch switch, because a server-name-preserving edit can still replace the command that will run at startup.
  • Reset project approvals when trust changes Clear stored project choices before re-opening a repo you did not author, inherited, or have not reviewed in a while.

Bottom line: The central risk is not a hidden exploit but a trust model that authorizes future commands under an old approval.

Glossary terms: Standing Grant, Definition Drift, Project-scoped Approval, Execution surface

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
 

Definition-bound trust, not name-bound trust, is the minimum viable control for agentic developer tools. The article shows that a project-wide MCP grant can persist even when the command behind the server name changes. That means the trust decision is attached to a label, not to the actual executable definition. For identity governance, that is a structural mismatch between approval and execution. The practitioner conclusion is simple: if the grant does not bind to the reviewed definition, it is not a safe authorization boundary.

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.
  • Claude Code-assisted commits leaked secrets at a rate of 3.2%, more than double the human-only baseline of 1.5%, with peaks reaching 31 secrets per 1,000 commits in August 2025, according to the State of Secrets Sprawl 2026.

A question worth separating out:

Q: What is the difference between approving a project and approving a specific MCP server?

A: Approving a specific server should bind trust to the reviewed command, while approving a project can become a broader standing grant for future servers or future command changes. The first is narrower and easier to reason about; the second is more convenient but creates far more room for silent definition drift.

👉 Read our full editorial: Name-keyed MCP approvals let changed commands run silently


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.