CVE-2026-108586: Incorrect Authorization in 1mcp-app @1mcp/agent
Description
1MCP Agent (@1mcp/agent) 0.20.0 through 0.39.0 contains an incorrect authorization vulnerability that allows authenticated clients to bypass OAuth tag-scope enforcement using negated advanced tag-filter expressions. Attackers holding a single-tag token can send a filter like not <granted-tag> to list and invoke tools on backend MCP servers outside their granted scopes.
CVSS v4.0
Score 5.3medium
Affected software
1mcp-app
@1mcp/agent
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-108586 describes an incorrect authorization vulnerability in the 1MCP Agent (@1mcp/agent) affecting versions 0.20.0 through 0.39.0. Authenticated clients holding a token scoped to a single tag can bypass OAuth tag-scope restrictions by using negated tag-filter expressions (e.g., 'not <granted-tag>'). This allows them to list and invoke backend MCP server tools beyond their authorized tag scopes, violating intended access controls. The vulnerability has a CVSS 4.0 base score of 5.3, indicating medium severity.
Potential Impact
Authenticated users with limited tag-scoped tokens can bypass authorization controls to access and invoke backend tools outside their granted scopes. This could lead to unauthorized actions on MCP servers, potentially compromising system integrity or confidentiality within the scope of the backend tools accessible.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, restrict access to trusted users and monitor for suspicious use of negated tag-filter expressions. Avoid granting overly broad tag scopes to tokens.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-10-10T16:07:40.380Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6aca68f62cdf04f6563ae068
Added to database: 10/10/2026, 16:33:58 UTC
Last enriched: 10/10/2026, 16:48:14 UTC
Last updated: 10/10/2026, 21:26:20 UTC
Views: 15
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.