Technology · Anthropic
Anthropic Model Context Protocol vulnerabilities
Updated . Rebuilt every hour.
Junglewise Threat Intelligence has tracked 10 vulnerabilities in Anthropic Model Context Protocol: 0 in the last 7 days and 6 in the last 90 days, 0 of them critical and 0 exploited in the wild. The most recent, CVE-2026-63128, was published on 16 September 2026.
- Last 7 days
- 0
- Last 90 days
- 6
- Critical, all time
- 0
- Exploited in the wild
- 0
About Anthropic Model Context Protocol
An open protocol for building AI agent-based applications with standardized client-server communication.
Latest Anthropic Model Context Protocol vulnerabilities
- CVE-2026-63128: RMCP is an official Rust SDK for the Model Context Protocol. Prior to 2.0.0, the rmcp crate's stateful Streamable HTTP…highCVSS 7.5EPSS 0.6%
- CVE-2026-63127: RMCP is an official Rust SDK for the Model Context Protocol. Prior to 2.0.0, the rmcp crate's OAuth implementation in…highCVSS 8.2EPSS 0.2%
- CVE-2026-67432: Model Context Protocol Ruby SDK memory exhaustion in StreamableHTTPTransporthighCVSS 7.5EPSS 0.8%
- CVE-2026-59950: modelcontextprotocol python-sdk missing origin validation in WebSocket transporthighCVSS 4EPSS 0.2%
- CVE-2026-52870: Model Context Protocol Python SDK missing authorization in experimental taskshighCVSS 7.6EPSS 0.4%
- CVE-2026-52869: modelcontextprotocol mcp authorization bypass in SSE and HTTP transportshighCVSS 7.1EPSS 0.5%
- CVE-2026-42559: Model Context Protocol RMCP DNS rebinding in Streamable HTTP serverhighCVSS 8.8EPSS 0.2%
- CVE-2026-25536: Model Context Protocol TypeScript SDK data leak in McpServer transporthighCVSS 7.1EPSS 0.4%
- CVE-2025-66416: Model Context Protocol Python SDK DNS rebinding in HTTP servershighCVSS 4EPSS 0.5%
- CVE-2025-53365: Model Context Protocol Python SDK denial of service in HTTP transporthighCVSS 4EPSS 0.4%
Most severe Anthropic Model Context Protocol vulnerabilities
Exploited in the wild first, then by severity and CVSS score.
- CVE-2026-42559: Model Context Protocol RMCP DNS rebinding in Streamable HTTP serverhighCVSS 8.8EPSS 0.2%
- CVE-2026-63127: RMCP is an official Rust SDK for the Model Context Protocol. Prior to 2.0.0, the rmcp crate's OAuth implementation in…highCVSS 8.2EPSS 0.2%
- CVE-2026-52870: Model Context Protocol Python SDK missing authorization in experimental taskshighCVSS 7.6EPSS 0.4%
- CVE-2026-67432: Model Context Protocol Ruby SDK memory exhaustion in StreamableHTTPTransporthighCVSS 7.5EPSS 0.8%
- CVE-2026-63128: RMCP is an official Rust SDK for the Model Context Protocol. Prior to 2.0.0, the rmcp crate's stateful Streamable HTTP…highCVSS 7.5EPSS 0.6%
- CVE-2026-52869: modelcontextprotocol mcp authorization bypass in SSE and HTTP transportshighCVSS 7.1EPSS 0.5%
- CVE-2026-25536: Model Context Protocol TypeScript SDK data leak in McpServer transporthighCVSS 7.1EPSS 0.4%
- CVE-2025-66416: Model Context Protocol Python SDK DNS rebinding in HTTP servershighCVSS 4EPSS 0.5%
- CVE-2025-53365: Model Context Protocol Python SDK denial of service in HTTP transporthighCVSS 4EPSS 0.4%
- CVE-2026-59950: modelcontextprotocol python-sdk missing origin validation in WebSocket transporthighCVSS 4EPSS 0.2%
Vulnerabilities per week
The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 6 Jul 2026 | 0 | 0 | |
| 13 Jul 2026 | 3 | 0 | |
| 20 Jul 2026 | 0 | 0 | |
| 27 Jul 2026 | 1 | 0 | |
| 3 Aug 2026 | 0 | 0 | |
| 10 Aug 2026 | 0 | 0 | |
| 17 Aug 2026 | 0 | 0 | |
| 24 Aug 2026 | 0 | 0 | |
| 31 Aug 2026 | 0 | 0 | |
| 7 Sep 2026 | 0 | 0 | |
| 14 Sep 2026 | 2 | 0 | |
| 21 Sep 2026 | 0 | 0 | |
| 28 Sep 2026 | 0 | 0 |
How this is built
Junglewise Threat Intelligence collects vulnerabilities from NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories, and matches each one to the technologies and vendors it affects. Dates are the date a vulnerability was published, in UTC.
The pages are rebuilt from the database every hour. Frozen weekly and monthly reports never change once published, so they can be cited.
Use this data
The same data is at https://junglewise.ai/threats/technologies/model-context-protocol.json, for scripts and language models. It is free to reuse under CC BY 4.0 with a link back to this page.
Cite as: Junglewise Threat Intelligence, "Anthropic Model Context Protocol vulnerabilities", https://junglewise.ai/threats/technologies/model-context-protocol, 28 September 2026.