LiveActive security incident?Get immediate response
CVE Record

CVE-2026-25536: @modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

MCP TypeScript SDK is the official TypeScript SDK for Model Context Protocol servers and clients. From version 1.10.0 to 1.25.3, cross-client response data leak when a single McpServer/Server and transport instance is reused across multiple client connections, most commonly in stateless StreamableHTTPServerTransport deployments. This issue has been patched in version 1.26.0.

HighCVSS 7.1Not KEV-listedUpdated
Glexia's TakeAutomated analysishigh

Security readout for executives and security teams

Plain-English summary

A vulnerable MCP TypeScript SDK deployment can send one client’s response data to another client when server and transport instances are shared across connections. This is primarily a confidentiality issue for MCP services that process sensitive prompts, tool results, or business data. The source bundle says it is fixed in version 1.26.0.

Executive priority

Treat as a high-priority confidentiality fix for AI or automation services using MCP. Upgrade affected SDK versions quickly, then verify deployment patterns. Business urgency is highest where MCP traffic includes confidential customer, employee, security, or operational data.

Technical view

Versions 1.10.0 through 1.25.3 of modelcontextprotocol/typescript-sdk are affected. The flaw is a race/TOCTOU condition involving reused McpServer/Server and transport instances, especially stateless StreamableHTTPServerTransport deployments. CVSS is 7.1, network exploitable, low complexity, requiring low privileges, with high confidentiality and low integrity impact.

Likely exposure

Exposure is most likely in custom MCP servers using @modelcontextprotocol/sdk 1.10.0-1.25.3 and reusing one server or transport instance across multiple client connections. Deployments that create isolated instances per connection may not match the described vulnerable pattern.

Exploitation context

The bundle does not cite active exploitation, and KEV is false. The CVSS vector indicates an authenticated network attacker with low privileges could trigger impact without user interaction. Evidence supports cross-client data leakage, not unauthenticated compromise or code execution.

Researcher notes

The vulnerability is implementation-pattern dependent: the affected SDK range alone is not enough to prove exposure. Focus review on shared mutable server/transport state and concurrent client handling. Sources identify CWE-362 and CWE-367, consistent with race and time-of-check/time-of-use behavior.

Mitigation direction

  • Upgrade @modelcontextprotocol/sdk to version 1.26.0 or later.
  • Review vendor advisory for any additional project-specific guidance.
  • Avoid sharing one McpServer/Server instance across multiple client connections.
  • Avoid reusing one transport instance across concurrent clients.
  • Prioritize MCP services handling secrets, prompts, customer data, or tool outputs.

Validation and detection

  • Inventory package manifests and lockfiles for @modelcontextprotocol/sdk versions below 1.26.0.
  • Inspect MCP HTTP server code for shared McpServer, Server, or transport singletons.
  • Identify stateless StreamableHTTPServerTransport deployments and review connection lifecycle handling.
  • Confirm deployed artifacts resolve to @modelcontextprotocol/sdk 1.26.0 or later.
  • Run regression tests covering concurrent client isolation without exposing sensitive production data.
Prepared
Confidence
high
Sources
9

Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.

Potential ATT&CK relevance

Conservative CVE-to-ATT&CK context

These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.

ATT&CK lookup starting points

Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.

cwe · low confidence lookup

CWE-362: Exact CWE lookup

Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
cwe · low confidence lookup

CWE-367: Exact CWE lookup

Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
cve · low confidence lookup

CVE-2026-25536 mapping review

Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.

Open ATT&CK lookup
Vulnerability profileCVE Program record
Severity
High
CVSS
7.1 (3.1)
Known Exploited
No
Published

Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N

Official CVE source material

CNA and ADP enrichment extracted from CVE v5

These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.

2CVSS vectors
5Timeline events
2ADP providers
8Source links

SSVC decision data

CISA-ADPCISA Coordinator
Timestamp
Version
2.0.3
Exploitation: noneAutomatable: noTechnical Impact: partial

CVSS vector scores

2 official scores

We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.

ScoreVersionSeverityVectorExploitImpactSource
7.1CVSS 3.1HighCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N2.84.2GitHub_M
7.1CVSS 3.1HighCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N2.84.2redhat-SADP

Vulnerability scoring details

Base CVSS 3.1 score

7.1High
CVSS 3.1 vector shape for CVE-2026-25536Attack VectorAttack ComplexityPrivileges RequiredUser InteractionScopeConfidentiality ImpactIntegrity ImpactAvailability Impact

Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N

Attack Vector
NetworkAdjacentLocalPhysical
Attack Complexity
LowHigh
Privileges Required
NoneLowHigh
User Interaction
NoneRequired
Scope
ChangedUnchanged
Confidentiality Impact
HighLowNone
Integrity Impact
HighLowNone
Availability Impact
HighLowNone

Vulnerability timeline

Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.

  1. CVE reservedCVE Program

    The CVE ID was reserved by the assigning CNA.

  2. ADP timelineredhat-SADP

    Made public.

  3. CVE publishedCVE Program

    The CVE record was published.

  4. ADP timelineredhat-SADP

    Reported to Red Hat.

  5. CVE updatedCVE Program

    The CVE record metadata indicates this as the latest update time.

ADP provider summaries

CISA-ADPCISA ADP Vulnrichment
other:ssvc
redhat-SADP@modelcontextprotocol/sdk: @modelcontextprotocol/sdk cross-client data leak
other:Red Hat severity ratingcvssV3_1
  • 2026-02-04T22:00:54.864Z: Reported to Red Hat.
  • 2026-02-04T21:29:38.276Z: Made public.

Source materials

Affected products

Products and packages named in the record

VendorProductVersion / packageStatus
modelcontextprotocoltypescript-sdk>= 1.10.0, < 1.26.0Listed
Weakness

CWE details

CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.

CWE-362 · source CWE mapping

Concurrent Execution using Shared Resource with Improper Synchronization ('Race Condition')

Concurrent Execution using Shared Resource with Improper Synchronization ('Race Condition') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.

CWE-367 · source CWE mapping

Time-of-check Time-of-use (TOCTOU) Race Condition

Time-of-check Time-of-use (TOCTOU) Race Condition represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.