PT-2026-105823

A weakness has been identified in BerriAI litellm up to 1.59.8. Affected is the function UserAPIKeyAuth of the file litellm/proxy/ experimental/mcp server/auth/user api key auth mcp.py of the component MCP Proxy. Executing a manipulation can lead to improper authentication. The attack may be...

PT-2026-105851

Summary MCP Atlassian exposes Jira and Confluence attachment upload tools that accept arbitrary local filesystem paths and upload those file contents to Atlassian. In HTTP or multi-user deployments, an MCP caller who can invoke write tools can cause the server to read any file accessible to the M...

PT-2026-105848

Environment - Project: sooperset/mcp-atlassian - Affected function: validate url for ssrf - Affected path: header-based Jira/Confluence URL authentication flow - Tested endpoint: POST /mcp - Tested version: 2.14.5 Description The SSRF protection in validate url for ssrf can be bypassed with a URL...

PT-2026-105835

Summary A critical Confused Deputy Arbitrary File Read & Exfiltration vulnerability in the Atlassian MCP server Python allows an AI agent to exfiltrate sensitive host files and environment secrets. By providing absolute system paths to the attachments parameter of the update issue tool, an agent...

PT-2026-105843

Summary The upload attachment method in confluence/attachments.py reads and uploads arbitrary local files to Confluence without calling validate safe path. Both download methods download attachment at line 223, download content attachments at line 272 correctly call validate safe path before...

PT-2026-105839

Summary The UserTokenMiddleware extracts URLs from X-Atlassian-Jira-Url and X-Atlassian-Confluence-Url HTTP headers and passes them directly to API client constructors without any SSRF validation. Affected Package - Ecosystem: PyPI - Package: mcp-atlassian - Affected versions: all versions before...

PT-2026-105825

A weakness has been identified in BerriAI litellm up to 1.82.2. Affected by this vulnerability is the function load openapi spec async of the file litellm/proxy/ experimental/mcp server/openapi to mcp generator.py of the component MCP OpenAPI Spec Loader. This manipulation of the argument spec pa...

PT-2026-105858

Summary In SSE/HTTP transport mode, mysql mcp server constructs SseServerTransport without passing security settings. As a result, the MCP Python SDK's DNS-rebinding protection Origin/Host header validation is disabled; the Starlette application has no CORS or TrustedHost middleware; and the...

PT-2026-105853

Summary The mcp-atlassian server exposes an MCP tool confluence upload attachment and the Jira attachment variant that accepts an arbitrary server-side file path and opens it for upload without any path validation. When the server is deployed in HTTP transport mode streamable-http or sse, a remot...

PT-2026-105805

Apache Doris MCP Server contains a SQL injection vulnerability in a metadata query path. A user-controlled database name is directly interpolated into a SQL query, and the query is executed without passing the caller's authorization context. This may allow an authenticated attacker, or an anonymo...

PT-2026-105852

Summary mcp-atlassian is a popular community MCP server wrapper exposing Jira / Confluence to MCP clients. Operators commonly restrict the surface to a small allowlist of projects/spaces via the JIRA PROJECTS FILTER and CONFLUENCE SPACES FILTER environment variables, which the README documents as...

CVE-2026-97662: Improper Neutralization of Argument Delimiters in a Command

An argument injection issue in the diff scan operation in AWS security-agent-mcp-server before version 0.2.0 might allow context-dependent threat actors to create, overwrite, or truncate arbitrary files on the host outside the intended workspace directory via a crafted reference value supplied to...

PT-2026-103877

Subscriber Privilege Escalation in ByteCoreStack MCP Connector for AI Tools = 1.2.2 versions...

The vulnerability of the PostgresConnector.connect() function on the MCP-server, when used to interact with DBHub databases, allows an attacker to gain unauthorized access for read and write operations, or to execute arbitrary code.

The vulnerability of the PostgresConnector.connect function on the MCP-server, when used to interact with DBHub databases, is related to the use of an incomplete black list. Exploiting this vulnerability could allow an attacker to gain unauthorized read and write access, or execute arbitrary code...

CVE-2026-19807: Improper Privilege Management

The ByteCoreStack – MCP Connector for AI Tools plugin for WordPress is vulnerable to Privilege Escalation in all versions up to, and including, 1.2.3 This is due to the wpupdateusermeta MCP tool in executetool gating writes solely with currentusercan'edituser', $uid — a check that WordPress core'...

PT-2026-105847

Summary When OAuth tokens are saved, MCP Atlassian always writes a plaintext fallback copy under /.mcp-atlassian/oauth-.json. The fallback file is created with the process default umask rather than restrictive permissions. In this environment the file was created as mode 0664, exposing access and...

PT-2026-105849

Summary The upload attachment functions in both the Jira and Confluence modules accept a user-controlled file path parameter and open the specified file for reading without calling validate safe path. An authenticated MCP client can supply an arbitrary path such as /etc/passwd or...

PT-2026-105807

A flaw was found in foreman-mcp-server. This component utilizes two distinct logging mechanisms that can expose sensitive session and authentication data. One mechanism logs session identifiers, which are treated as authentication credentials, at an informational level. The other, when debug...

PT-2026-105845

Summary The Jira and Confluence attachment upload tools accept caller-controlled file path parameters and read those paths from the MCP server's local filesystem before uploading the file as an Atlassian attachment. In local stdio deployments, this can expose files readable by the user's MCP...

PT-2026-103965

Name of the Vulnerable Software and Affected Versions AWS security-agent-mcp-server versions prior to 0.2.0 Description An argument injection issue exists in the diff scan operation. A threat actor can provide a crafted reference value to the diff scan operation to create, overwrite, or truncate...