PatchSiren cyber security CVE debrief
CVE-2026-0621 Anthropic CVE debrief
Anthropic's MCP TypeScript SDK versions up to and including 1.25.1 contain a regular expression denial of service (ReDoS) vulnerability in the UriTemplate class when processing RFC 6570 exploded array patterns. The dynamically generated regular expression used during URI matching contains nested quantifiers that can trigger catastrophic backtracking on specially crafted inputs, resulting in excessive CPU consumption. An attacker can exploit this by supplying a malicious URI that causes the Node.js process to become unresponsive, leading to a denial of service. This vulnerability has a high impact on organizations using the affected SDK versions, as it can lead to service disruption and potential data breaches.
- Vendor
- Anthropic
- Product
- MCP TypeScript SDK
- CVSS
- HIGH 8.7
- CISA KEV
- Not listed in stored evidence
- Original CVE published
- 2026-01-05
- Original CVE updated
- 2026-07-14
- Advisory published
- 2026-01-05
- Advisory updated
- 2026-07-14
Who should care
Organizations using Anthropic's MCP TypeScript SDK versions up to and including 1.25.1 should prioritize updating to a patched version to prevent potential denial-of-service attacks. Additionally, security teams and vulnerability management teams should be aware of the potential impact of this vulnerability on their systems and take steps to mitigate it. Operators and administrators of affected systems should also be aware of the potential risks and take steps to protect their systems.
Technical summary
The vulnerability exists in the UriTemplate class of the MCP TypeScript SDK, specifically in the handling of RFC 6570 exploded array patterns. This feature allows for complex URI templating but also introduces the risk of ReDoS when not properly sanitized. The dynamically generated regular expression used for URI matching can enter into catastrophic backtracking with specially crafted inputs, leading to high CPU usage and potential service disruption. The affected SDK versions do not properly validate or sanitize the input URIs, making it possible for attackers to craft malicious inputs that exploit this vulnerability.
Defensive priority
High
Recommended defensive actions
- Update to a patched version of the MCP TypeScript SDK
- Implement input validation and sanitization for URI templates
- Monitor for suspicious URI requests
- Review compensating controls for exposed systems while remediation is scheduled and verified
- Check relevant monitoring, detection, and logs for exposed assets that need extra review
- Track exceptions, retest remediated assets, and close the item only after evidence is documented
- Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up
Evidence notes
The CVE record was published on 2026-01-05T21:16:14.533Z and was last modified on 2026-07-14T16:16:43.063Z. The NVD entry is currently Analyzed. The vulnerability was reported by an external researcher and is based on limited source information. Further verification and testing are recommended to confirm the impact and scope of this vulnerability.
Sources and references
Verified primary and authoritative sources
-
CVE-2026-0621 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2026-0621
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2026-0621 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2026-0621
NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.
Supplemental references
-
Source reference
Unverified legacy reference
URL: https://github.com/modelcontextprotocol/typescript-sdk/issues/965
[email protected] - Exploit, Issue Tracking
-
Mitigation or vendor reference
Unverified legacy reference
URL: https://www.vulncheck.com/advisories/mcp-typescript-sdk-uritemplate-exploded-array-pattern-redos
[email protected] - Third Party Advisory
Methodology and review provenance
AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.