CVE-2026-63127

HIGHCVSS 8.2/10

Last modified

CVE-2026-63127 is a high-severity vulnerability rated 8.2/10 on the CVSS scale. RMCP is an official Rust SDK for the Model Context Protocol. Prior to 2.0.0, the rmcp crate's OAuth implementation in crates/rmcp/src/transport/auth.rs omits the RFC 9728 resource field from ResourceServerMetadata and allows discover_oauth_server_via_resource_metadata to use protected-resource metadata without confirming that the returned resource identifier exactly matches the configured MCP server.

Description

RMCP is an official Rust SDK for the Model Context Protocol. Prior to 2.0.0, the rmcp crate's OAuth implementation in crates/rmcp/src/transport/auth.rs omits the RFC 9728 resource field from ResourceServerMetadata and allows discover_oauth_server_via_resource_metadata to use protected-resource metadata without confirming that the returned resource identifier exactly matches the configured MCP server. A malicious MCP server can publish metadata for a different legitimate MCP resource and its authorization server, causing a victim who connects and completes the authorization flow to obtain a legitimate access token that the client subsequently sends to the malicious server. The attacker can capture the token and impersonate the victim against the legitimate MCP resource within the token's granted scopes. This issue is fixed in version 2.0.0.

Metrics

Weakness Enumeration

Affected Software

Source: CNA advisory (CVE.org). NVD analysis pending.

VendorProductVersions
modelcontextprotocolrust-sdk< 2.0.0

References

Timeline

Published
Last Modified
Status
Received

Frequently Asked Questions

What is CVE-2026-63127?
RMCP is an official Rust SDK for the Model Context Protocol. Prior to 2.0.0, the rmcp crate's OAuth implementation in crates/rmcp/src/transport/auth.rs omits the RFC 9728 resource field from ResourceServerMetadata and allows discover_oauth_server_via_resource_metadata to use protected-resource metadata without confirming that the returned resource identifier exactly matches the configured MCP server. A malicious MCP server can publish metadata for a different legitimate MCP resource and its authorization server, causing a victim who connects and completes the authorization flow to obtain a legitimate access token that the client subsequently sends to the malicious server. The attacker can capture the token and impersonate the victim against the legitimate MCP resource within the token's granted scopes. This issue is fixed in version 2.0.0.
How severe is CVE-2026-63127?
CVE-2026-63127 has a CVSS score of 8.2/10 (HIGH severity).
How do I fix CVE-2026-63127?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

How Strix Helps

Related CVEs from 2026

Are you affected by CVE-2026-63127?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST