Lucene search
K

421 matches found

CVE
CVE
added 2026/03/31 3:40 p.m.22 views

CVE-2026-34237

CVE-2026-34237 affects MCP Java SDK. A hardcoded wildcard CORS configuration (Access-Control-Allow-Origin: *) existed in versions before 0.83.0, 1.0.1, and 1.1.1, allowing cross-origin requests to server endpoints (including SSE paths). The issue has been patched in those versions (0.83.0, 1.0.1,...

6.1CVSS7.3AI score0.00222EPSS
Exploits0References3Affected Software1
OSV
OSV
added 2026/03/31 3:40 p.m.8 views

CVE-2026-34237 MCP Java SDK has a Hardcoded Wildcard CORS (Access-Control-Allow-Origin: *)

MCP Java SDK is the official Java SDK for Model Context Protocol servers and clients. Prior to versions 1.0.1 and 1.1.1, there is a hardcoded wildcard CORS vulnerability. This issue has been patched in versions 1.0.1 and 1.1.1...

6.1CVSS5.8AI score0.00222EPSS
Exploits0References5
ATTACKERKB
ATTACKERKB
added 2026/03/31 1:43 p.m.3 views

CVE-2026-34163

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP Model Context Protocol tools endpoints /api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the...

7.7CVSS5.8AI score0.00283EPSS
Exploits1References5Affected Software1
EUVD
EUVD
added 2026/03/31 1:43 p.m.3 views

EUVD-2026-17447

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP Model Context Protocol tools endpoints /api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the...

7.7CVSS5.8AI score0.00283EPSS
Exploits1References4
Cvelist
Cvelist
added 2026/03/31 1:43 p.m.24 views

CVE-2026-34163 Server-Side Request Forgery via MCP Tools Endpoint in FastGPT

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP Model Context Protocol tools endpoints /api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the...

7.7CVSS0.00283EPSS
Exploits1References4
Vulnrichment
Vulnrichment
added 2026/03/31 1:43 p.m.4 views

CVE-2026-34163 Server-Side Request Forgery via MCP Tools Endpoint in FastGPT

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP Model Context Protocol tools endpoints /api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the...

7.7CVSS5.8AI score0.00283EPSS
Exploits1References4
OSV
OSV
added 2026/03/31 1:43 p.m.2 views

CVE-2026-34163 Server-Side Request Forgery via MCP Tools Endpoint in FastGPT

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP Model Context Protocol tools endpoints /api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the...

7.7CVSS5.8AI score0.00283EPSS
Exploits1References6
Positive Technologies
Positive Technologies
added 2026/03/31 12:0 a.m.5 views

PT-2026-29263

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP Model Context Protocol tools endpoints /api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the...

7.7CVSS5.8AI score0.00283EPSS
Exploits1References5
CNNVD
CNNVD
added 2026/03/31 12:0 a.m.9 views

MCP Java SDK 安全漏洞

The MCP Java SDK is an open-source standard protocol SDK for integrating AI models and tools with Java applications, developed under the Model Context Protocol. Versions of the MCP Java SDK prior to 1.0.1 and 1.1.1 contained security vulnerabilities, which were caused by hardcoded wildcard CORS...

6.1CVSS7.2AI score0.00222EPSS
Exploits0References3
NVD
NVD
added 2026/03/30 6:16 p.m.40 views

CVE-2026-33032

Nginx UI is a web user interface for the Nginx web server. In versions 2.3.5 and prior, the nginx-ui MCP Model Context Protocol integration exposes two HTTP endpoints: /mcp and /mcpmessage. While /mcp requires both IP whitelisting and authentication AuthRequired middleware, the /mcpmessage endpoi...

9.8CVSS0.38477EPSS
Exploits4References2
Vulnrichment
Vulnrichment
added 2026/03/30 5:58 p.m.3 views

CVE-2026-33032 Nginx UI: Unauthenticated MCP Endpoint Allows Remote Nginx Takeover

Nginx UI is a web user interface for the Nginx web server. In versions 2.3.5 and prior, the nginx-ui MCP Model Context Protocol integration exposes two HTTP endpoints: /mcp and /mcpmessage. While /mcp requires both IP whitelisting and authentication AuthRequired middleware, the /mcpmessage endpoi...

9.8CVSS5.9AI score0.38477EPSS
Exploits4References1
Cvelist
Cvelist
added 2026/03/30 5:58 p.m.25 views

CVE-2026-33032 Nginx UI: Unauthenticated MCP Endpoint Allows Remote Nginx Takeover

Nginx UI is a web user interface for the Nginx web server. In versions 2.3.5 and prior, the nginx-ui MCP Model Context Protocol integration exposes two HTTP endpoints: /mcp and /mcpmessage. While /mcp requires both IP whitelisting and authentication AuthRequired middleware, the /mcpmessage endpoi...

9.8CVSS0.38477EPSS
Exploits4References1
OSV
OSV
added 2026/03/30 5:58 p.m.4 views

CVE-2026-33032 Nginx UI: Unauthenticated MCP Endpoint Allows Remote Nginx Takeover

Nginx UI is a web user interface for the Nginx web server. In versions 2.3.5 and prior, the nginx-ui MCP Model Context Protocol integration exposes two HTTP endpoints: /mcp and /mcpmessage. While /mcp requires both IP whitelisting and authentication AuthRequired middleware, the /mcpmessage endpoi...

9.8CVSS5.9AI score0.38477EPSS
Exploits4References3
CVE
CVE
added 2026/03/30 5:58 p.m.70 views

CVE-2026-33032

CVE-2026-33032 affects nginx-ui prior to 2.3.4. The MCP integration exposes two HTTP endpoints: /mcp (protected by AuthRequired) and /mcp_message (no authentication). The default IPWhiteList is empty, which the middleware treats as “allow all,” enabling unauthenticated MCP tool invocations (e.g.,...

9.8CVSS5.9AI score0.38477EPSS
In wildExploits4References2Affected Software1
ATTACKERKB
ATTACKERKB
added 2026/03/30 5:58 p.m.7 views

CVE-2026-33032

Nginx UI is a web user interface for the Nginx web server. In versions 2.3.5 and prior, the nginx-ui MCP Model Context Protocol integration exposes two HTTP endpoints: /mcp and /mcpmessage. While /mcp requires both IP whitelisting and authentication AuthRequired middleware, the /mcpmessage endpoi...

9.8CVSS5.9AI score0.38477EPSS
Exploits4References2Affected Software1
vulnersOsv
vulnersOsv
added 2026/03/30 5:26 p.m.6 views

com.agentsflex:agents-flex-bom (>=2.1.1 <=2.1.3), com.agentsflex:agents-flex-mcp (>=2.0.0 <=2.1.3) +28 more potentially affected by CVE-2026-34237 via io.modelcontextprotocol.sdk:mcp-core (>=1.0.0-RC3 <=1.0.0)

io.modelcontextprotocol.sdk:mcp-core MAVEN version =1.0.0-RC3, =2.1.1, =2.0.0, =2.1.1, =2.0.4, =0.1.1, =0.1.1, =0.158.v8e18e64dd93c, =0.172.v9dbcb43cdbcc - io.micronaut.mcp:micronaut-mcp-client-java-sdk =1.0.0-M2 - io.micronaut.mcp:micronaut-mcp-server-java-sdk =1.0.0-M2 -...

6.1CVSS7.4AI score0.00222EPSS
Exploits0
RedhatCVE
RedhatCVE
added 2026/03/30 5:6 p.m.5 views

CVE-2026-33946

MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients. Prior to version 0.9.2, the Ruby SDK's streamablehttptransport.rb implementation contains a session hijacking vulnerability. An attacker who obtains a valid session ID can completely hijack the victim's...

8.2CVSS5.9AI score0.00465EPSS
Exploits1References1
Github Security Blog
Github Security Blog
added 2026/03/30 4:43 p.m.15 views

nginx-ui's Unauthenticated MCP Endpoint Allows Remote Nginx Takeover

Summary The nginx-ui MCP Model Context Protocol integration exposes two HTTP endpoints: /mcp and /mcpmessage. While /mcp requires both IP whitelisting and authentication AuthRequired middleware, the /mcpmessage endpoint only applies IP whitelisting - and the default IP whitelist is empty, which t...

9.8CVSS5.9AI score0.38477EPSS
Exploits4References6Affected Software1
GitLab Advisory Database
GitLab Advisory Database
added 2026/03/30 12:0 a.m.15 views

nginx-ui's Unauthenticated MCP Endpoint Allows Remote Nginx Takeover

The nginx-ui MCP Model Context Protocol integration exposes two HTTP endpoints: /mcp and /mcpmessage. While /mcp requires both IP whitelisting and authentication AuthRequired middleware, the /mcpmessage endpoint only applies IP whitelisting - and the default IP whitelist is empty, which the...

9.8CVSS6AI score0.38477EPSS
Exploits4References6Affected Software1
RedhatCVE
RedhatCVE
added 2026/03/28 11:9 p.m.6 views

CVE-2026-31951

LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP Model Context Protocol servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containin...

6.8CVSS6AI score0.00244EPSS
Exploits1References1
Rows per page
Query Builder