cve.bz

CVE-2026-63127 modelcontextprotocol rust-sdk

8.2 highEPSS 0.2%Fix available

High (8.2) in modelcontextprotocol rust-sdk. EPSS 0.2% estimated probability of exploitation activity in the next 30 days. Fixed in rmcp 2.0.0.

On this page
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.

Severity

CVSS 3.1

8.2 high
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:L/A:N
EPSS
0.2% (unchanged from 0.2% a week ago; 0.2% 30 days ago) estimated probability of exploitation activity in the next 30 days; 9th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: PoC · Automatable: no · Technical impact: partial, assessed 2026-09-16. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-345 Insufficient Verification of Data Authenticity
OWASP Top 10
A08:2025 Software or Data Integrity Failures
Published
Modified
NVD analysis
Deferred: the NVD does not plan to analyze it
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-63127 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-63127?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-63127?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-63127 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the CNA's record in the CVE List.

ProductAffected
modelcontextprotocol rust-sdk< 2.0.0

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-33f5-2c5q-wgwjcrates.iormcp<2.0.02.0.0

Linux distributions

DistributionReleasePackageFixed inAdvisory
Red Hatenterprise_linux:9::extensionsgoose, goose-debuginfo, goose-debugsource0:1.45.0-1.el9_8RHSA-2026:80764
Red Hatenterprise_linux:10.2goose, goose-debuginfo, goose-debugsource0:1.45.0-1.el10_2RHSA-2026:80765
openSUSETumbleweedopenai-codex0.155.1-1.1openSUSE-SU-2026:11849-1

From the distributions' data via OSV.dev: Red Hat Security Data © Red Hat, Inc., CC BY 4.0; SUSE security data, CC BY 4.0. Modified: reformatted and linked to CVE records. Credits. On the distributions' own pages: Red Hat · openSUSE.

Red Hat

Red Hat rates this Important.

Red Hat's statement

This is an Important flaw in the `rmcp` Rust SDK, which is utilized by the `goose` component in Red Hat products. The vulnerability allows a malicious Model Context Protocol (MCP) server to facilitate token impersonation by omitting a critical resource field during OAuth metadata discovery. This can lead to a client unknowingly sending a legitimate access token to the malicious server, resulting in unauthorized access and potential information disclosure within the token's granted scopes. Exploitation requires user interaction, but the attack complexity is low.

Red Hat's mitigation

Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.

ProductPackageStateAdvisory
Red Hat Enterprise Linux 10gooseAffected
Red Hat Enterprise Linux 9gooseAffected

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-63127.

Attack patterns (CAPEC)

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits. More on the page of CWE-345 (12).

References

Check your stackJSON