Vendor
Model Context Protocol vulnerabilities
Updated . Rebuilt every hour.
Junglewise Threat Intelligence has tracked 20 vulnerabilities in 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-2026-111770, was published on 5 November 2026. 5 vulnerabilities in the last four weeks, up from none in the four before. 2 technologies have a page of their own.
- Last 7 days
- 0
- Last 90 days
- 6
- Critical, all time
- 0
- Exploited in the wild
- 0
About Model Context Protocol
The Model Context Protocol is an open standard for connecting AI models to data sources and tools.
Model Context Protocol technologies
Latest Model Context Protocol vulnerabilities
- CVE-2026-111770: MCP TypeScript server SDK cross-client message delivery in shared HTTP transporthighCVSS 7.7
- MCP TypeScript SDK denial of service via unbounded request body and JSON-RPC batchhighCVSS 7.5
- rmcp OAuth client SSRF via unresolved hostnamesinfo
- CVE-2026-111767: MCP TypeScript SDK missing authorization in experimental taskshighCVSS 8.6EPSS 0.4%
- CVE-2026-108395: Model Context Protocol Java SDK unbounded HTTP request body readhighCVSS 7.5EPSS 0.6%
- CVE-2026-53937: MCP Kotlin SDK unbounded memory growth in ReadBuffermediumCVSS 6.2EPSS 0.2%
- CVE-2026-19753: Model Context Protocol mcp-rdf-explorer SSRF in explore_urlhighCVSS 7.3EPSS 0.5%
- CVE-2026-67431: modelcontextprotocol ruby-sdk session hijacking in StreamableHTTPTransporthighCVSS 4EPSS 0.5%
- CVE-2026-67430: Model Context Protocol Ruby SDK memory exhaustion in StreamableHTTPTransportmediumCVSS 5.3EPSS 0.5%
- 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-2026-44428: Model Context Protocol Registry OIDC token replay via shared audiencemediumCVSS 4.7EPSS 0.3%
- CVE-2026-44427: Model Context Protocol Registry open redirect in TrailingSlashMiddlewaremediumCVSS 4EPSS 0.4%
- CVE-2026-45781: Model Context Protocol Registry ownership bypass in OCI validatorlowCVSS 3.5EPSS 0.3%
- CVE-2026-44430: Model Context Protocol Registry SSRF via IPv6 Filter BypassmediumCVSS 4EPSS 0.3%
- CVE-2026-44429: MCP Registry stored XSS in catalogue UI via websiteUrlmediumCVSS 5.4EPSS 0.2%
- CVE-2026-42559: Model Context Protocol RMCP DNS rebinding in Streamable HTTP serverhighCVSS 8.8EPSS 0.2%
- CVE-2026-34237: Model Context Protocol Java SDK hardcoded wildcard CORS policymediumCVSS 6.1EPSS 0.3%
- CVE-2026-25536: Model Context Protocol TypeScript SDK data leak in McpServer transporthighCVSS 7.1EPSS 0.4%
Most severe 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-2026-111767: MCP TypeScript SDK missing authorization in experimental taskshighCVSS 8.6EPSS 0.4%
- CVE-2026-111770: MCP TypeScript server SDK cross-client message delivery in shared HTTP transporthighCVSS 7.7
- CVE-2026-52870: Model Context Protocol Python SDK missing authorization in experimental taskshighCVSS 7.6EPSS 0.4%
- CVE-2026-108395: Model Context Protocol Java SDK unbounded HTTP request body readhighCVSS 7.5EPSS 0.6%
- MCP TypeScript SDK denial of service via unbounded request body and JSON-RPC batchhighCVSS 7.5
- CVE-2026-19753: Model Context Protocol mcp-rdf-explorer SSRF in explore_urlhighCVSS 7.3EPSS 0.5%
- 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-2026-67431: modelcontextprotocol ruby-sdk session hijacking in StreamableHTTPTransporthighCVSS 4EPSS 0.5%
Vulnerabilities per week
5 vulnerabilities in the last four weeks, up from none in the four before. The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 17 Aug 2026 | 0 | 0 | |
| 24 Aug 2026 | 0 | 0 | |
| 31 Aug 2026 | 0 | 0 | |
| 7 Sep 2026 | 1 | 0 | |
| 14 Sep 2026 | 0 | 0 | |
| 21 Sep 2026 | 0 | 0 | |
| 28 Sep 2026 | 0 | 0 | |
| 5 Oct 2026 | 0 | 0 | |
| 12 Oct 2026 | 1 | 0 | |
| 19 Oct 2026 | 2 | 0 | |
| 26 Oct 2026 | 1 | 0 | |
| 2 Nov 2026 | 1 | 0 | |
| 9 Nov 2026 | 0 | 0 |
Embed a badge
A live badge for a README, a status page or an internal wiki: how many Model Context Protocol vulnerabilities were published in the last 7 days and how many of them are critical, refreshed hourly.
[](https://junglewise.ai/threats/vendors/model-context-protocol)<a href="https://junglewise.ai/threats/vendors/model-context-protocol"><img src="https://junglewise.ai/threats/vendors/model-context-protocol/badge.svg" alt="Model Context Protocol vulnerabilities" /></a>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/vendors/model-context-protocol.json, and this page as text at https://junglewise.ai/threats/vendors/model-context-protocol.md, 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, "Model Context Protocol vulnerabilities", https://junglewise.ai/threats/vendors/model-context-protocol, 13 November 2026.