cve.bz

CVE-2026-104850 modelcontextprotocol typescript-sdk: Insufficiently Protected Credentials

7.5 highEPSS 0.3%Fix available

High (7.5) in modelcontextprotocol typescript-sdk. EPSS 0.3% estimated probability of exploitation activity in the next 30 days. Fixed in @modelcontextprotocol/sdk 1.31.0.

On this page
MCP TypeScript SDK is the official TypeScript SDK for Model Context Protocol servers and clients. Starting in version 1.12.0 and prior to versions 1.31.0 and 2.2.0, the SDK's OAuth client support let the MCP server a client connected to decide which authorization server received the client's OAuth credentials. Stored and pre-provisioned credentials were not bound to the authorization server they belong to. A malicious or compromised MCP server could name its own authorization server in its protected resource metadata. Without any user interaction, the client would send that server the `refresh_token` and `client_secret` stored from an earlier sign-in (1.x), or the configured `client_secret` or signed assertion of a bundled non-interactive provider (1.x and 2.x). Only those applications that use the SDK as an MCP client over HTTP with an `authProvider`: your own `OAuthClientProvider`, or the bundled `ClientCredentialsProvider`, `PrivateKeyJwtProvider`, `StaticPrivateKeyJwtProvider` or (2.x) `CrossAppAccessProvider` and that may connect to an MCP server the owners does not fully trust while holding credentials for a legitimate authorization server are affected. `@modelcontextprotocol/sdk` 1.31.0 (1.x) and `@modelcontextprotocol/client` 2.2.0 (2.x) patch the issue. A workaround for those who cannot upgrade is available. 2.0.0 and 2.1.0 already accept `expectedIssuer`. On 1.x, the only workaround is to connect OAuth-enabled clients only to MCP servers you trust.

Severity

CVSS 3.1

7.5 high
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
EPSS
0.3% (unchanged from 0.3% a week ago; 0.2% 30 days ago) estimated probability of exploitation activity in the next 30 days; 21st percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: yes · Technical impact: partial, assessed 2026-10-06. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWEs
CWE-345 Insufficient Verification of Data Authenticity
CWE-522 Insufficiently Protected Credentials
OWASP Top 10
A06:2025 Insecure Design, A08:2025 Software or Data Integrity Failures
Published
Modified
NVD analysis
Awaiting analysis
Record from
the NVD, synced

Fix and patched versions

  • @modelcontextprotocol/sdk (npm): fixed in 1.31.0
  • @modelcontextprotocol/client (npm): fixed in 2.2.0

Ask an AI about this CVE

Show the promptExplain CVE-2026-104850 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-104850?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-104850?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-2026-104850 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 typescript-sdk>= 1.12.0, < 1.31.0
modelcontextprotocol typescript-sdk>= 2.0.0, < 2.2.0

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-6qxp-vccf-f47hnpm@modelcontextprotocol/sdk>=1.12.0 <1.31.01.31.0
GHSA-6qxp-vccf-f47hnpm@modelcontextprotocol/client>=2.0.0 <2.2.02.2.0

Red Hat

Red Hat rates this Important.

Red Hat's statement

Red Hat rates this vulnerability as an Important severity because it allows a malicious endpoint to silently extract sensitive authentication secrets and tokens over the network without requiring user interaction. The exposure specifically affects environments where Model Context Protocol client components establish HTTP connections to untrusted external servers while configured with OAuth authentication providers. Workloads communicating exclusively over local standard input/output channels or connecting only to verified, trustworthy endpoints are not susceptible to credential exfiltration.

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
Migration Toolkit for Applications 8mta/mta-solution-server-rhel9Affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-27/mcp-server-rhel9Affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-tech-preview/mcp-server-rhel9Affected
Red Hat Enterprise Linux 10gooseNot affected
Red Hat Enterprise Linux 10grafanaNot affected
Red Hat Enterprise Linux 9gooseNot affected
Red Hat Hardened Imagesgrafana12.4Not affected
Red Hat Hardened Imagesgrafana13.1Not affected
Red Hat Hardened Imagesgrafana13.2Not affected
Red Hat OpenShift AI (RHOAI)rhoai/odh-workbench-codeserver-datascience-cpu-py312-rhel9Affected
Red Hat OpenShift Dev Spacesdevspaces/code-rhel9Affected

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-2026-104850.

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), CWE-522 (13).

References

Check your stackJSON