A path traversal vulnerability exists in the MCPHub MCPB file upload handler due to improper sanitization of the 'name' field in the uploaded manifest.json. The 'name' field is directly concatenated into file system paths without validation, allowing an attacker to craft a malicious MCPB file that causes extraction and file operations outside the intended directory. This can lead to arbitrary file creation or deletion on the server file system.
CVE-2026-40933 is a critical OS command injection vulnerability in FlowiseAI's Flowise product prior to version 3.1.0. It arises from unsafe serialization of stdio commands in the MCP adapter, allowing an authenticated attacker to add a malicious MCP stdio server with arbitrary commands. Despite input sanitization attempts, attackers can bypass these checks and execute arbitrary OS commands. This vulnerability is fixed in Flowise version 3.1.0.
Next AI Draw.io is a next.js web application that integrates AI capabilities with draw.io diagrams. Prior to 0.4.15, the embedded HTTP sidecar contains three POST handlers (/api/state, /api/restore, and /api/history-svg) that process incoming requests by accumulating the entire request body into a JavaScript string without any size limitations. Node.js buffers the entire payload in the V8 heap. Sending a sufficiently large body (e.g., 500 MiB or more) will exhaust the process heap memory, leading to an Out-of-Memory (OOM) error that crashes the MCP server. This vulnerability is fixed in 0.4.15.
excel-mcp-server is a Model Context Protocol server for Excel file manipulation. A path traversal vulnerability exists in excel-mcp-server versions up to and including 0.1.7. When running in SSE or Streamable-HTTP transport mode (the documented way to use this server remotely), an unauthenticated attacker on the network can read, write, and overwrite arbitrary files on the host filesystem by supplying crafted filepath arguments to any of the 25 exposed MCP tool handlers. The server is intended to confine file operations to a directory set by the EXCEL_FILES_PATH environment variable. The function responsible for enforcing this boundary — get_excel_path() — fails to do so due to two independent flaws: it passes absolute paths through without any check, and it joins relative paths without resolving or validating the result. Combined with zero authentication on the default network-facing transport and a default bind address of 0.0.0.0 (all interfaces), this allows trivial remote exploitation. This vulnerability is fixed in 0.1.8.
Apache Doris MCP Server versions earlier than 0.6.1 are affected by an improper neutralization flaw in query context handling that may allow execution of unintended SQL statements and bypass of intended query validation and access restrictions through the MCP query execution interface. Version 0.6.1 and later are not affected.
Upsonic version 0.71.6 contains a critical remote code execution vulnerability in its MCP server/task creation functionality. The vulnerability arises because users can define MCP tasks with arbitrary command and argument values. Although an allowlist restricts commands, some allowed commands like npm and npx accept argument flags that enable execution of arbitrary OS commands. This can lead to remote code execution with the privileges of the Upsonic process. Version 0.72.0 introduced a warning about the risks of using Stdio servers that can execute commands directly on the host machine. No official patch or remediation has been confirmed yet.
LangChain-ChatChat 0.3.1 contains a remote code execution vulnerability in its MCP STDIO server configuration and execution handling. A remote attacker can access the publicly exposed MCP management interface and configure an MCP STDIO server with attacker-controlled commands and arguments. When the MCP server is started and MCP is enabled for agent execution, subsequent agent activity triggers execution of arbitrary commands on the server. Successful exploitation allows arbitrary command execution within the context of the LangChain-ChatChat service.
Jaaz 1.0.30 contains a remote code execution vulnerability in its MCP STDIO command execution handling. A remote attacker can send crafted network requests to the network-accessible Jaaz application, causing attacker-controlled commands to be executed on the server. Successful exploitation results in arbitrary command execution within the context of the Jaaz service, potentially allowing full compromise of the affected system.
mcp-server-kubernetes is a Model Context Protocol server for Kubernetes cluster management. Versions 3.4.0 and prior contain an argument injection vulnerability in the port_forward tool in src/tools/port_forward.ts, where a kubectl command is constructed via string concatenation with user-controlled input and then naively split on spaces before being passed to spawn(). Unlike all other tools in the codebase which correctly use array-based argument passing with execFileSync(), port_forward treats every space in user-controlled fields (namespace, resourceType, resourceName, localPort, targetPort) as an argument boundary, allowing an attacker to inject arbitrary kubectl flags. This enables exposure of internal Kubernetes services to the network by injecting --address=0.0.0.0, cross-namespace targeting by injecting additional -n flags, and indirect exploitation via prompt injection against AI agents connected to the MCP server. This issue has been fixed in version 3.5.0.
Server-Side Request Forgery via SW-URL Header vulnerability in Apache SkyWalking MCP.
This issue affects Apache SkyWalking MCP: 0.1.0.
Users are recommended to upgrade to version 0.2.0, which fixes this issue.
A critical remote code execution vulnerability (CVE-2026-5059) exists in aws-mcp-server versions up to 1.7.0. The flaw is due to improper validation of user-supplied input in the allowed commands list, allowing unauthenticated attackers to execute arbitrary system commands on the server.
FastGPT is an AI Agent building platform. Prior to 4.14.10.3, the /api/core/app/mcpTools/runTool endpoint accepts arbitrary URLs without authentication. The internal IP check in isInternalAddress() only blocks private IPs when CHECK_INTERNAL_IP=true, which is not the default. This allows unauthenticated attackers to perform SSRF against internal network resources. This vulnerability is fixed in 4.14.10.3.
Apollo MCP Server is a Model Context Protocol server that exposes GraphQL operations as MCP tools. Prior to version 1.7.0, the Apollo MCP Server did not validate the Host header on incoming HTTP requests when using StreamableHTTP transport. In configurations where an HTTP-based MCP server is run on localhost without additional authentication or network-level controls, this could potentially allow a malicious website—visited by a user running the server locally—to use DNS rebinding techniques to bypass same-origin policy restrictions and issue requests to the local MCP server. If successfully exploited, this could allow an attacker to invoke tools or access resources exposed by the MCP server on behalf of the local user. This issue is limited to HTTP-based transport modes (StreamableHTTP). It does not affect servers using stdio transport. The practical risk is further reduced in deployments that use authentication, network-level access controls, or are not bound to localhost. This vulnerability is fixed in 1.7.0.
## Impact
An authenticated Server-Side Request Forgery in `n8n-mcp` allows a caller holding a valid `AUTH_TOKEN` to cause the server to issue HTTP requests to arbitrary URLs supplied through multi-tenant HTTP headers. Response bodies are reflected back through JSON-RPC, so an attacker can read the contents of any URL the server can reach — including cloud instance metadata endpoints (AWS IMDS, GCP, Azure, Alibaba, Oracle), internal network services, and any other host the server process has network access to.
The primary at-risk deployments are multi-tenant HTTP installations where more than one operator can present a valid `AUTH_TOKEN`, or where a token is shared with less-trusted clients. Single-tenant stdio deployments and HTTP deployments without multi-tenant headers are not affected.
## Affected versions
`n8n-mcp` ≤ `2.47.3` (all versions up to and including 2.47.3).
## Patched versions
`n8n-mcp` `2.47.4` and later.
## Workarounds
If you cannot immediately upgrade:
1. **Egress filtering at the network layer** — block outbound traffic from the `n8n-mcp` container to RFC1918 ranges (10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16), link-local `169.254.0.0/16`, and any other internal ranges. This defends against any future SSRF-class issue and is recommended even after upgrading.
2. **Disable multi-tenant headers** — if your deployment does not require per-request instance switching, unset `ENABLE_MULTI_TENANT` and do not accept `x-n8n-url` / `x-n8n-key` headers at the reverse proxy.
3. **Restrict `AUTH_TOKEN` distribution** — ensure the bearer token is only held by fully trusted operators until you can upgrade.
## Remediation
Upgrade to `n8n-mcp` 2.47.4 or later. No configuration changes are required; the fix adds validation at the URL entry points and normalizes URLs at the API client layer.
## Credits
Reported by the Eresus Security Research Team. @ibrahmsql
CVE-2026-5833 is a command injection vulnerability in the awwaiid mcp-server-taskwarrior product versions up to 1.0.1. The issue exists in the server.setRequestHandler function within index.ts, where manipulation of the Identifier argument can lead to command injection. Exploitation requires local access. The vendor has released a fixed version promptly after being notified, and a patch is available to resolve this issue. The vulnerability has a medium severity rating with a CVSS score of 4.8.
A weakness has been identified in atototo api-lab-mcp up to 0.2.1. This affects the function analyze_api_spec/generate_test_scenarios/test_http_endpoint of the file src/mcp/http-server.ts of the component HTTP Interface. This manipulation of the argument source/url causes server-side request forgery. The attack is possible to be carried out remotely. The exploit has been made available to the public and could be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.
CVE-2026-5831 is a medium severity OS command injection vulnerability in Agions taskflow-ai versions up to 2.1.8. The flaw exists in an unspecified function within src/mcp/server/handlers.ts related to the terminal_execute component. This vulnerability allows remote attackers to execute arbitrary OS commands. The vendor has released version 2.1.9 to address this issue promptly after being notified.
CVE-2026-39885 is a Server-Side Request Forgery (SSRF) vulnerability in the frontmcp product by agentfront, specifically in versions prior to 1.0.4. The vulnerability arises because the mcp-from-openapi library uses @apidevtools/json-schema-ref-parser to dereference $ref pointers in OpenAPI specifications without restricting URLs or using custom resolvers. This allows malicious OpenAPI specs to cause the server to fetch internal network resources, cloud metadata endpoints, or local files during initialization, enabling SSRF and local file read attacks. The vulnerability has a high severity with a CVSS score of 7.5. No official patch or remediation level is explicitly stated in the provided data, but the description notes the issue is fixed in version 2.3.0 of the framework, which suggests upgrading to a fixed version is the recommended mitigation.
A weakness has been identified in suvarchal docker-mcp-server up to 0.1.0. The impacted element is the function stop_container/remove_container/pull_image of the file src/index.ts of the component HTTP Interface. This manipulation causes os command injection. The attack is possible to be carried out remotely. The exploit has been made available to the public and could be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.