Skip to main content

CVE-2026-64684: CWE-200: Exposure of Sensitive Information to an Unauthorized Actor in modelcontextprotocol rust-sdk

0
Medium
VulnerabilityCVE-2026-64684cvecve-2026-64684cwe-200
Published: 09/16/2026 (09/16/2026, 21:18:48 UTC)
Source: CVE Database V5
Vendor/Project: modelcontextprotocol
Product: rust-sdk

Description

RMCP is an official Rust SDK for the Model Context Protocol. Prior to 2.1.0, the rmcp crate's StreamableHttpClientTransport in crates/rmcp/src/transport/common/reqwest/streamable_http_client.rs builds its default_http_client with reqwest's automatic redirect policy and applies caller-supplied values from StreamableHttpClientTransportConfig.custom_headers without marking them as sensitive. When a malicious or compromised MCP endpoint returns a cross-origin 307 or 308 redirect, reqwest follows the redirect and apply_custom_headers causes custom API keys or authentication tokens to be replayed to the new origin, where an attacker can capture and reuse them. The separate auth_header path is not affected because it uses the standard Authorization header, which reqwest strips on cross-origin redirects. This issue is fixed in version 2.1.0.

CVSS v3.1

Score 6.8medium

Attack Vector
Network
Attack Complexity
High
Privileges Required
None
User Interaction
None
Scope
Changed
Confidentiality
High
Integrity
None
Availability
None
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:N/A:N

Affected software

modelcontextprotocol

rust-sdk

Affected versions
<2.1.0
crates.iomore threats →ai
rmcp
pkg:cargo/rmcp
Affected versions
<2.1.0

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

AILast updated: 09/16/2026, 21:47:58 UTC

Technical Analysis

The rmcp crate's StreamableHttpClientTransport in versions before 2.1.0 builds its default HTTP client with reqwest's automatic redirect policy and applies caller-supplied custom headers without marking them as sensitive. When a malicious or compromised MCP endpoint returns a cross-origin 307 or 308 redirect, reqwest follows the redirect and the custom headers (including API keys or tokens) are replayed to the new origin. This can lead to exposure of sensitive information to unauthorized actors. The standard Authorization header path is not affected because reqwest strips it on cross-origin redirects. The vulnerability is resolved in version 2.1.0.

Potential Impact

An attacker controlling or compromising an MCP endpoint can exploit this vulnerability by returning a cross-origin 307 or 308 redirect, causing the client to resend sensitive custom headers such as API keys or authentication tokens to an unintended origin. This leads to exposure of sensitive information, which an attacker can capture and reuse, potentially compromising the security of the affected system. The vulnerability does not affect the standard Authorization header, limiting the scope to custom headers.

Mitigation Recommendations

Upgrade to modelcontextprotocol rust-sdk version 2.1.0 or later, where this issue is fixed. The fix involves marking custom headers as sensitive to prevent them from being replayed on cross-origin redirects. No other mitigation is required as the vulnerability is addressed by this official fix.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
GitHub_M
Date Reserved
2026-07-20T17:12:12.892Z
Cvss Version
3.1
State
PUBLISHED

Threat ID: 6aab0ad855bf5e2cf52e9606

Added to database: 09/16/2026, 21:32:08 UTC

Last enriched: 09/16/2026, 21:47:58 UTC

Last updated: 09/16/2026, 22:11:09 UTC

Views: 5

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

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

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses