PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-50287 agenticmail CVE debrief

CVE-2026-50287 is a HIGH severity vulnerability in AgenticMail. Prior to version 0.9.27, @agenticmail/mcp exposes a Streamable HTTP transport when started with --http or MCP_HTTP=1. In that mode, the /mcp endpoint accepts requests without any HTTP authentication layer. A remote client can initialize a session and call tools directly. This issue has been patched in version 0.9.27.

Vendor
agenticmail
Product
Unknown
CVSS
HIGH 8.7
CISA KEV
Not listed in stored evidence
Original CVE published
2026-06-12
Original CVE updated
2026-06-16
Advisory published
2026-06-12
Advisory updated
2026-06-16

Who should care

Users of AgenticMail prior to version 0.9.27 who have enabled the Streamable HTTP transport by starting with --http or setting MCP_HTTP=1.

Technical summary

The @agenticmail/mcp module in AgenticMail, when started with --http or MCP_HTTP=1, exposes an unauthenticated /mcp endpoint. This allows remote clients to initialize sessions and call tools directly without any HTTP authentication.

Defensive priority

HIGH

Recommended defensive actions

  • Update AgenticMail to version 0.9.27 or later.
  • Avoid using the --http or MCP_HTTP=1 flags to start the @agenticmail/mcp module.
  • Implement proper authentication and authorization for the /mcp endpoint.

Evidence notes

CVE-2026-50287 has a CVSS score of 8.7 and is classified as HIGH severity. The vulnerability was patched in version 0.9.27 of AgenticMail.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-50287 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-50287

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-50287 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-50287

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.