EUVD-2026-80824Severity by source
AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:L/A:N
Network-reachable malicious server, low complexity, no attacker privileges, but victim must connect and complete OAuth consent (UI:R); token abuse hits a separate legitimate resource (S:C); confidentiality/impersonation dominant.
Primary rating from Vendor (GitHub_M).
CVSS VectorVendor: GitHub_M
Lifecycle Timeline
3DescriptionCVE.org
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.
AnalysisAI
OAuth access-token theft in the rmcp Rust SDK (the official Rust SDK for the Model Context Protocol) before 2.0.0 allows a malicious MCP server to harvest a victim's legitimate bearer token by publishing RFC 9728 protected-resource metadata that names a different, legitimate MCP resource together with that resource's authorization server. The OAuth client transport never verifies that the returned resource identifier matches the MCP server URL it was actually configured to contact, so a victim who connects and completes the normal authorization/consent flow receives a genuine access token and then sends it to the attacker's endpoint, letting the attacker replay it against the legitimate MCP resource within the granted scopes. …
Unlock full vulnerability intelligence
- Risk assessment & exploitation conditions
- Attack chain visualization
- Remediation with exact patch versions
- Threat intelligence from 22 sources
- Personal watchlist & email alerts
Free forever · No credit card required
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata
Vulnerability AssessmentAI
| Exploitation | Requires that the victim's application use the rmcp crate (<2.0.0) OAuth client transport (crates/rmcp/src/transport/auth.rs) and initiate a connection to an attacker-controlled MCP server that the attacker has provisioned with crafted RFC 9728 protected-resource metadata referencing a legitimate resource and its authorization server. … Additional conditions and limiting factors are described in the full assessment. |
| Risk Assessment | This is a genuine, well-characterized authenticity/spoofing flaw (CWE-345) rather than a hollow high-CVSS entry, but the vendor's 8.2 is toward the upper bound of what the mechanics support. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | Full exploit scenario with step-by-step reproduction available after sign-in. |
| Remediation | Upgrade the rmcp dependency to v2.0.0 or later (release tag rmcp-v2.0.0, commit c1a8b29, PR #937), which adds the RFC 9728 `resource` field to `ResourceServerMetadata` and enforces an exact identifier match between protected-resource metadata and the configured MCP server URL - see the advisory at https://github.com/modelcontextprotocol/rust-sdk/security/advisories/GHSA-33f5-2c5q-wgwj. … Detailed patch versions, workarounds, and compensating controls in full report. |
Recommended ActionAI
Within 24 hours, inventory every application, plugin, and internal tool built on the rmcp Rust SDK and determine which carry versions below 2.0.0; treat any user who completed an OAuth consent flow against a third-party or unverified MCP server as potentially compromised and immediately revoke and reissue the affected OAuth access and refresh tokens at the corresponding authorization server, and temporarily block outbound connectivity from MCP clients to non-approved server endpoints. …
Sign in for detailed remediation steps and compensating controls.
Threat intelligence, references, and detailed analysis are available after sign-in.
Same technique Information Disclosure
View allShare
External POC / Exploit Code
Leaving vuln.today