The mem0-mcp-server npm package contains malicious code that compromises any computer on which it is installed or running. This compromise potentially grants full control to an outside entity, risking exposure of all stored secrets and keys. Immediate removal of the package and rotation of all secrets from a different, uncompromised machine is strongly advised.
Incorrect Privilege Assignment vulnerability in AtlasAiDev MCP Server for WordPress ai-workflow-automation-ai-agent-hub allows Privilege Escalation.This issue affects MCP Server for WordPress: from n/a through 2.0.3.
IBM ContextForge MCP Gateway versions 1.0.0 through 1.0.11 contain a server-side request forgery (SSRF) vulnerability. An authenticated attacker could exploit this flaw to send unauthorized requests from the affected system. This may enable network enumeration or assist in launching further attacks. The vulnerability has a medium severity rating with a CVSS score of 5.4. No official patch or remediation information is provided in the available data.
SiYuan before 3.8.10 contains a server-side request forgery vulnerability in the skill-install download path because fetchBytes performs only a parse-time hostname check instead of using ssrfSafeClient. Attackers can supply a skill URL via the MCP skill install action that redirects or DNS-rebinds to loopback addresses, reaching internal services and metadata endpoints.
OpenTelemetry Python provides the Python API and SDK for OpenTelemetry. Prior to 1.45.2, TraceContextTextMapPropagator.extract() in opentelemetry-api can perform quadratic-time regular-expression backtracking on a malformed traceparent value containing a trace-context prefix, a long whitespace sequence, and an embedded newline. Exploitation requires an attacker-controlled carrier that preserves embedded newlines and permits a sufficiently large value, because conforming HTTP header values cannot contain embedded newlines. JSON-based carriers, including applicable MCP request metadata integrations, can preserve the required newline depending on the SDK, instrumentation, and message-size limits. Parsing on an asynchronous server's event-loop thread can consume excessive CPU and delay unrelated requests, while the advisory does not establish disclosure, modification, or code execution. This issue is fixed in version 1.45.2.
pgEdge Postgres MCP Server enables SQL queries against PostgreSQL databases through Model Context Protocol compatible clients. Prior to 1.1.0, the bundled CLI and web clients classified query_database statements only by their first keyword before deciding whether to display a write confirmation. SELECT INTO, data-modifying common table expressions beginning with WITH, and EXPLAIN ANALYZE of a write were treated as reads and could execute without confirmation on an allow_writes connection. Read-only connections remain protected by PostgreSQL transaction access mode, and EXPLAIN without ANALYZE and SELECT FOR UPDATE remain classified as reads. This issue is fixed in 1.1.0.
pgEdge Postgres MCP Server enables SQL queries against PostgreSQL databases through Model Context Protocol compatible clients. Prior to 1.1.0, the bundled clients, including the CLI and web client, decided whether to request write confirmation by checking only for the query_database tool name instead of server-published write annotations. Custom pl-do, pl-func, and writing sql tools therefore ran without confirmation on allow_writes connections, including when a model followed instructions in retrieved content. The affected control is a bundled-client warning rather than a server authorization boundary, and other MCP clients do not inherit that prompt. This issue is fixed in 1.1.0.
pgEdge Postgres MCP Server enables SQL queries against PostgreSQL databases through Model Context Protocol compatible clients. Prior to 1.1.0, custom pl-do tools interpolated JSON arguments into a PostgreSQL DO block delimited by fixed dollar-quote tags. An argument containing $mcp_custom_tool$ could terminate the block and inject arbitrary SQL statements, while $mcp_args$ could inject procedural code into a plpgsql block. Because the statement used the simple query protocol, injected text could include additional statements and transaction control, bypassing read_only and accessing data or modifying resources available to the connecting role. The issue requires at least one pl-do custom tool; sql and pl-func tools pass arguments as bind parameters and are not affected by this injection mechanism. This issue is fixed in 1.1.0.
pgEdge Postgres MCP Server enables SQL queries against PostgreSQL databases through Model Context Protocol compatible clients. Prior to 1.1.0, query_database on a read_only connection could send unrecognized statements through pgx Exec without bind parameters, selecting PostgreSQL's simple query protocol and allowing multiple semicolon-separated statements in one request. A caller could combine transaction or session state changes with database writes, and pooled session state could leave later calls writable, when the connecting role held write privileges. The flaw affected deployments relying on read_only as a safety boundary, could compromise integrity and availability, and did not add confidentiality impact beyond the reads already permitted by the connection. This issue is fixed in 1.1.0.
A Server-Side Request Forgery (SSRF) vulnerability exists in heymrun heym versions prior to 0.0.70. Authenticated users with the lowest role can access the POST /api/mcp/fetch-tools endpoint, which fetches attacker-supplied URLs without proper validation or allowlisting. This allows attackers to perform SSRF attacks with control over outbound request headers. The vulnerability has been fixed in version 0.0.70.
CVE-2026-125926 is a server-side request forgery (SSRF) vulnerability in the server registration and update API of Amazon's mcp-gateway-registry prior to version 1.35.0. An authenticated remote user could exploit this flaw to send crafted requests from the gateway to internal network services and cloud instance metadata endpoints, potentially reading sensitive responses. The issue is resolved by upgrading to version 1.35.0.
Siemens and other industrial technology vendors have disclosed multiple high-severity vulnerabilities affecting various ICS/OT products, including Siemens' ROS#, Simcenter Femap, Mendix Studio Pro MCP Server, Simatic SCADA and PCS 7, Meta-iot2050, and Simatic WinCC Graphics Designer. Some advisories also address the impact of the Node2Shell vulnerability. Exploitation attempts of Node2Shell have been observed, though not specifically targeting Siemens products. Additional vulnerabilities affect products from Schneider Electric, Beckhoff, Johnson Controls, Hitachi Energy, and others, with issues ranging from arbitrary code execution to privilege escalation. Siemens notes that patches are not yet available for several affected products, and some versions will not receive fixes, recommending customers apply mitigations. The flaws can lead to code injection, unauthorized data access, and system compromise.
The Security For WooCommerce WordPress plugin versions through 1.0.16 have a vulnerability where one of its REST API routes is not access-restricted. This allows unauthenticated users to retrieve detailed reports about the server, PHP, WordPress configuration, installed plugin versions, and the site administrator's email address.
The npm package @lemili9804/mcp-weather-server versions 1.0.3 and 1.0.6 contain malicious code. Any system with this package installed or running is considered fully compromised, potentially allowing an attacker full control over the affected computer. Immediate removal of the package and rotation of all secrets and keys from a different, trusted system is strongly advised.
CVE-2026-125321 is a vulnerability in pgEdge Postgres MCP Server versions prior to 1.1.0 that allows unauthenticated attackers to bypass login rate limiting by manipulating the X-Forwarded-For HTTP header. This flaw arises because the server uses the leftmost X-Forwarded-For value as the client address for rate limiting, enabling attackers to rotate addresses to evade throttling or consume another user's rate limit quota. The issue is reachable without operator misconfiguration due to the default nginx configuration appending rather than replacing X-Forwarded-For. The vulnerability is fixed in version 1.1.0.
CVE-2026-125320 is an origin validation error in pgEdge pgedge-postgres-mcp versions prior to 1.1.0. The HTTP transport did not validate the Origin header, allowing a user visiting an attacker-controlled page to be targeted via DNS rebinding. This could enable the attacker-controlled page to access local server resources, including reading database schemas and query results. The vulnerability affects deployments with HTTP transport enabled on machines running a browser. The issue is fixed in version 1.1.0.
CVE-2026-125271 is a vulnerability in the AWS API MCP Server where operation names are incorrectly normalized before security policy checks. This flaw causes operations with consecutive capital letters in their names to bypass denyList or elicitList security policies. As a result, an attacker might execute AWS API operations that should be denied or require additional approval according to the operator's security policy. The vulnerability affects versions from 0.2.13 up to but not including 1.5.1.