Vulnerabilities
All
My stack
Known exploited
Public exploit
Critical (9+)
Likely exploited (EPSS ≥ 50%)
Changed, 24 h
New, 24 h
Sort:
risk
modified
published
CVSS
EPSS
| CVE | CVSS | EPSS | Vendor, product | Description | Modified |
|---|---|---|---|---|---|
| CVE-2025-59528exploit ×15 | 10.0 critical | 86.0% | flowiseai, flowise | Flowise is a drag & drop user interface to build a customized large language model flow. In version 3.0.5, Flowise is vulnerable to remote code execution. The CustomMCP node allows users to input configuration settings for connecting to an external MCP server. This node parses the user-provided mcpServerConfig string to build the MCP server configuration. However, during this process, it executes JavaScript code without any security validation. Specifically, inside the convertToValidJSONString function, user input is directly passed to the Function() constructor, which evaluates and executes the input as JavaScript code. Since this runs with full Node.js runtime privileges, it can access dangerous modules such as child_process and fs. This issue has been patched in version 3.0.6. | 18 Oct |
| CVE-2026-73296exploit ×2 | 9.4 critical | 4.0% | no CPE yet | Microsoft UFO open-source framework for intelligent automation across devices and platforms. Prior to 3.0.8, create_mobile_data_collection_server and create_mobile_action_server in ufo/client/mcp/http_servers/mobile_mcp_server.py exposed Streamable HTTP MCP services on TCP ports 8020 and 8021 without authentication, allowing an unauthenticated remote attacker to invoke capture_screenshot, get_ui_tree, tap, swipe, type_text, launch_app, press_key, and click_control against an ADB-connected Android device, disclose screen and device data, and modify device state. This issue is fixed in version 3.0.8. | 24 Oct |
| CVE-2026-61459exploit | 9.3 critical | 2.0% | suyogs, mcp-server-kubernetes | MCP Server Kubernetes before 3.9.0 contains an argument injection vulnerability in structured tools (kubectl_get, kubectl_describe, kubectl_delete) that allows attackers to bypass the assertNoDangerousFlags security check by supplying resourceType and name parameters with leading dashes. Attackers can inject the --server flag to redirect kubectl commands to an attacker-controlled API server, causing the operator's bearer token to be transmitted externally and enabling full cluster compromise. | 25 Oct |
| CVE-2026-105697exploit | 9.9 critical | 1.0% | no CPE yet | Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and (before 1.10.3) wrapped in bash -c "exec {command} ...". Any user able to reach the MCP server settings ("Settings → MCP Servers → Add MCP Server", POST/PATCH /api/v2/mcp/servers/{server_name}) or to build a flow with the MCP Tools component could add a "server" whose command is an arbitrary OS command (touch, rm -rf, a reverse shell, ...). The command runs on the Langflow host as the Langflow process user as soon as Langflow tries to connect to the server (listing servers, loading tools, running the flow) — even when the UI then reports that the stdio server failed to start. With the default LANGFLOW_AUTO_LOGIN=true, GET /api/v1/auto_login hands out a token without credentials, so on an exposed instance running the default configuration this is reachable without an account. AUTO_LOGIN is documented as a development-only setting; with it disabled, any authenticated (non-admin) user can exploit it. This issue is fixed in Langflow 1.10.3, langflow-base 0.10.3, and lfx 1.10.3. | 9 Oct |
| CVE-2025-35028 | 9.1 critical | 5.0% | no CPE yet | By providing a command-line argument starting with a semi-colon ; to an API endpoint created by the EnhancedCommandExecutor class of the HexStrike AI MCP server, the resultant composed command is executed directly in the context of the MCP server’s normal privilege; typically, this is root. There is no attempt to sanitize these arguments in the default configuration of this MCP server at the affected version (as of commit 2f3a5512 in September of 2025). | 18 Oct |
| CVE-2025-11202 | 9.8 critical | 3.0% | no CPE yet | win-cli-mcp-server resolveCommandPath Command Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of win-cli-mcp-server. Authentication is not required to exploit this vulnerability. The specific flaw exists within the implementation of the resolveCommandPath method. The issue results from the lack of proper validation of a user-supplied string before using it to execute a system call. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-27787. | 19 Oct |
| CVE-2025-59834 | 9.8 critical | 3.0% | srmorete, adb_mcp_server | ADB MCP Server is a MCP (Model Context Protocol) server for interacting with Android devices through ADB. In versions 0.1.0 and prior, the MCP Server is written in a way that is vulnerable to command injection vulnerability attacks as part of some of its MCP Server tool definition and implementation. This issue has been patched via commit 041729c. | 11 Oct |
| CVE-2026-6942 | 9.3 critical | 2.0% | radare, radare2_mcp_server | radare2-mcp version 1.6.0 and earlier contains an os command injection vulnerability that allows remote attackers to execute arbitrary commands by bypassing the command filter through shell metacharacters in user-controlled input passed to r2_cmd_str(). Attackers can inject shell metacharacters through the jsonrpc interface parameters to achieve remote code execution on the host running radare2-mcp without requiring authentication. | Mon 26 Oct |
| CVE-2026-49257 | 10.0 critical | 1.0% | no CPE yet | mcp-pinot is a Python-based Model Context Protocol (MCP) server for interacting with Apache Pinot. In versions 3.0.1 and below, mcp-pinot defaults to running an HTTP MCP server bound to 0.0.0.0:8080 with no authentication enabled. All MCP tools, including SQL query execution, schema creation, and table-config mutation, are reachable by any network-adjacent caller. The server proxies these calls using server-side Pinot credentials, producing a confused-deputy condition that yields full read/write access to the configured Pinot cluster. This issue has been fixed in version 3.1.0 | 26 Oct |
| CVE-2026-16326 | 10.0 critical | 1.0% | no CPE yet | In consul-mcp-server, versions 0.1.0 up to 0.1.3 did not properly isolate session state in stateless mode, which may allow one client's Consul authentication token to be used for subsequent requests from other clients. This vulnerability (CVE-2026-16326) is fixed in consul-mcp-server 0.1.4. | 24 Oct |
| CVE-2025-65719 | 9.8 critical | 1.0% | no CPE yet | An issue in Open Source Kubectl MCP Server v1.1.1 allows attackers to execute arbitrary code on a victim system via user interaction with a crafted HTML page. | Mon 26 Oct |
| CVE-2026-52830 | 9.4 critical | 1.0% | no CPE yet | fast-mcp-telegram is a Telegram MCP Server. Prior to 0.19.1, fast-mcp-telegram validates HTTP Bearer tokens by joining the raw token string into a session-file path. The verifier rejects the exact reserved token telegram, but it does not reject path separators or normalize the path before checking whether the session file exists. A remote HTTP client can therefore authenticate as the default legacy session with a token such as ../fast-mcp-telegram/telegram when the documented default session file ~/.config/fast-mcp-telegram/telegram.session exists. This bypasses the reserved session name control that is intended to prevent HTTP multi-user sessions from colliding with the default stdio or legacy account. With account-prefixed MCP tools enabled, the attacker still sees and calls the prefixed tools for the default account, so the prefix middleware does not stop the session selection bypass. This vulnerability is fixed in 0.19.1. | 25 Oct |
| CVE-2026-96620 | 9.2 critical | 1.0% | no CPE yet | Claude Agent SDK is a Python SDK for Claude Code. Prior to 0.2.121, the resume option is passed to the Claude CLI as a separate token without validation, so a dash-leading value is parsed as an independent CLI flag. An attacker can inject the --mcp-config flag to define a stdio MCP server, causing arbitrary command execution at CLI startup outside the SDK permission controls. The issue is exploitable when an application passes untrusted input as the session ID to resume. This issue is fixed in version 0.2.121. | 21 Oct |
| CVE-2026-76404 | 9.1 critical | 1.0% | splunk, model_context_protocol_server | In Splunk MCP Server app versions below 1.2.1, a user who holds the "admin" Splunk role could execute arbitrary commands on the underlying operating system. The vulnerability is possible because of missing input validation in the app's credential management component, which deserializes stored data without checking whether the content is of the expected type. | 24 Oct |
| CVE-2026-48039 | 9.1 critical | 1.0% | no CPE yet | Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.109, `AuthInjectionMiddleware.dispatch()` at `http_auth_integration.py:272` unconditionally forwards unauthenticated Streamable HTTP requests to downstream MCP tool handlers without issuing a `401` response, allowing any network-reachable caller to invoke MCP tools without authentication. When no per-request credential is present, tool handlers fall back to the `META_ACCESS_TOKEN` environment variable, and when the downstream Meta Graph API call fails, `api.py:263–269` serialises the raw `httpx` request URL—including the operator's `access_token` as a query parameter—into the JSON-RPC response body, delivering the credential to the unauthenticated caller. Version 1.0.109 fixes the issue. | 23 Oct |
| CVE-2026-62674 | 9.0 critical | 1.0% | no CPE yet | Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, PUT /sessions/{session_id}/agent checks LEVEL_EDIT permission for a session but does not reject a bound shared or template agent whose agent.session_id is None. An authenticated user with edit access to a session can replace that shared agent bundle through omnigent/server/routes/sessions.py, add a stdio MCP server, and cause later sessions that use the shared agent to launch an attacker-controlled command through omnigent/tools/mcp.py. The command executes with the Omnigent runner process permissions and can expose files, credentials, workspace data, internal services, and runner availability. This issue is fixed in version 0.3.0. | 14 Oct |
| CVE-2026-16498 | 10.0 critical | 0.00% | no CPE yet | The terraform-mcp-server before version 1.1.0 is vulnerable to a cross-tenant credential reuse issue in the streamable-HTTP stateless transport mode that may allow one user's Terraform token to be used to execute tool calls on behalf of subsequent users. This vulnerability, CVE-2026-16498, is fixed in terraform-mcp-server 1.1.0. | 23 Oct |
| CVE-2026-54052 | 9.9 critical | 0.00% | n8n-mcp | n8n-MCP is an MCP server that provides AI assistants access to n8n node documentation, properties, and operations. Prior to 2.56.1, in HTTP mode with multi-tenancy enabled through ENABLE_MULTI_TENANT=true, n8n-mcp's local workflow version history backups were not isolated per tenant, allowing an authenticated tenant to read workflow version snapshots belonging to other tenants and delete or destroy other tenants' stored backups, including full node definitions, credential references, and authorization headers. This issue is fixed in version 2.56.1. | 24 Oct |
| CVE-2026-62863 | 9.6 critical | 0.00% | gojue, moling | MoLing is a computer-use and browser-use based MCP server. Prior to 0.5.0, when MoLing runs in SSE mode using `-l`, its `/sse` and `/message` HTTP endpoints do not authenticate requests and the `mcp-go` dependency sets `Access-Control-Allow-Origin: *`. A malicious web page can open a cross-origin `EventSource` to `/sse`, including a loopback listener, and read the `endpoint` event to obtain `sessionId`. After a victim running SSE mode visits that page, the attacker can use the disclosed `sessionId` against `/message` to send unauthorized MCP tool calls. Depending on the configured tools, those calls can read or write local files, execute commands or perform other actions. Binding only to loopback does not prevent this browser-mediated attack. This issue is fixed in version 0.5.0. | Fri 30 Oct |
| CVE-2026-71424 | 9.6 critical | 0.00% | no CPE yet | Onyx is an open-source AI platform. Prior to 3.1.10, 3.2.14, and 4.0.0, Onyx's GET /api/mcp/servers and GET /api/mcp/servers/persona/{persona_id} endpoints expose another user's OAuth Authorization header because OnyxTokenStorage.set_tokens and OnyxTokenStorage.set_client_info in backend/onyx/server/features/mcp/api.py copy per-user tokens into a shared admin MCPConnectionConfig row and _db_mcp_server_to_api_mcp_server returns that row through auth_template.headers to any BASIC_ACCESS user. This issue is fixed in versions 3.1.10, 3.2.14, and 4.0.0. | 22 Oct |
| CVE-2026-57496 | 9.6 critical | 0.00% | no CPE yet | NetLicensing MCP Server is a natural-language interface that enables agentic applications to manage the software-licensing lifecycle in Labs64 NetLicensing. Prior to 0.1.8, netlicensing_get_product passes the caller-controlled product_number to src/netlicensing_mcp/tools/products.py, which interpolates it into a REST path consumed by nl_get() in src/netlicensing_mcp/client.py without path-segment validation. A traversal segment can be normalized from the intended product path to the /token endpoint, after which the response is serialized through _wrap_json instead of _wrap_json_token_read, bypassing redact_token_read() protections for APIKEY number and SHOP shopURL fields. An authenticated MCP client with a non-administrative API key can retrieve plaintext token values, and a recovered administrative token can provide broad read, write, and delete access to the NetLicensing account. This issue is fixed in version 0.1.8. | 21 Oct |
| CVE-2026-40576 | 9.4 critical | 0.00% | no CPE yet | 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. | Mon 26 Oct |
| CVE-2026-54030 | 9.3 critical | 0.00% | librechat | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.5, LibreChat's MCP OAuth implementation does not validate that the resource parameter from OAuth Protected Resource metadata (RFC 9728) matches the configured MCP server URL, allowing a malicious MCP server to steal access tokens intended for a legitimate server. This vulnerability is fixed in 0.8.5. | 25 Oct |
| CVE-2026-47708 | 9.3 critical | 0.00% | no CPE yet | MCP-for-Stata is an MCP server for Stata to integrate Stata into an agent. Prior to version 1.17.3, the `log_file_name` parameter in the `stata_do` API and CLI is directly interpolated into a Stata command string without sanitization. The security guard (`GuardValidator`) only scans the do-file content but does not validate this parameter. An attacker can inject arbitrary Stata commands (including `shell`, `python`, `erase`, etc.) by crafting a malicious `log_file_name` containing quotes, newlines, or Stata command separators. Version 1.17.3 contains a patch for the issue. | 24 Oct |
| CVE-2026-107824 | 9.3 critical | 0.00% | no CPE yet | x64dbg-MCP Server is a native Model Context Protocol (MCP) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Prior to 1.1, x64dbg-MCP Server exposes all MCP debugger tools over HTTP and SSE without authentication while listening on 0.0.0.0 by default. Any unauthenticated network client that can reach the default port, 9094 for x64 or 9095 for x32, can execute arbitrary x64dbg commands, attach to processes by PID, read and write debuggee memory, and write files to arbitrary paths. This issue is fixed in version 1.1. | 16 Oct |
| CVE-2026-15643 | 9.2 critical | 0.00% | no CPE yet | AWS HealthLake MCP Server (awslabs.healthlake-mcp-server) is a Model Context Protocol server that enables AI assistants to interact with AWS HealthLake FHIR datastores. A server-side request forgery in the pagination handling component in AWS awslabs.healthlake-mcp-server before 0.0.14 on all platforms might allow a remote authenticated user to exfiltrate AWS temporary security credentials to an arbitrary endpoint via a crafted next_token parameter. The server does not validate that pagination URLs point back to the expected HealthLake endpoint, allowing an actor to redirect subsequent requests to an actor-controlled server. Its recommended to upgrade to version 0.0.14 or later. | 24 Oct |
| CVE-2026-48814 | 9.1 critical | 0.00% | no CPE yet | Network-AI is a TypeScript/Node.js multi-agent orchestrator. In versions 5.7.1 and earlier, the MCP SSE server allows unauthenticated cross-origin MCP tool invocation due to an empty default secret. This issue was partially addressed by CVE-2026-46701 in version 5.4.5 by closing the CORS flaw (with Access-Control-Allow-Origin now set only for localhost origins), but the empty-default-secret flaw described in the title remained: the SSE MCP server still defaulted to an empty secret, _isAuthorized() still returned true when the secret was empty, and a non-loopback bind only produced a warning. As a result, the server still ran fully unauthenticated by default. Any non-browser caller (for example, curl, SSRF, or a 0.0.0.0 bind) could invoke all 22 MCP tools (config_set, agent_spawn, blackboard_write, token_*) with no credentials. This issue was fixed in version 5.7.2. | 25 Oct |
27 of 27
Download these 27 as CSV · subscribe to this list.
EPSS scores: 2026-11-01. NVD cursor: 2026-10-29 00:22. The News page shows only notable CVEs (KEV, your stack, new criticals, EPSS over 50%, or active exploitation per SSVC); this table has all of them.