firecrawl-mcp-server 3.20.2 contains an arbitrary local file read vulnerability in the firecrawl_parse tool that accepts unconstrained filePath arguments without directory containment validation. Attackers can supply absolute paths or directory traversal sequences to read sensitive files like credentials and environment variables, which are then uploaded and returned to the model context.
The npm package 'mcp-consultasdeveiculos-client' versions 0.0.2, 0.1.0, and 0.1.1 contains malicious code that collects system information and a user-supplied token, then sends this data to a hardcoded third-party server unrelated to the package's stated purpose. The package's README falsely claims it contains no code or install scripts, misleading developers. This results in unintended leakage of sensitive tokens to an external collector when the CLI is executed as instructed by an external project's documentation.
OpenAI Codex CLI for Windows, macOS, and Linux and Codex Desktop for Windows and macOS misclassified certain PowerShell commands as safe because their command-safety parser interpreted PowerShell's stop-parsing token (--%) differently than PowerShell itself. If a user opens an attacker-prepared repository and Codex follows its instructions, Codex can run a file-writing Git command without requesting user approval. On macOS and Linux, exploitation additionally requires separately installed PowerShell Core (pwsh) to be invoked. If filesystem protections permit the write, the command can modify Codex's configuration. If Codex later loads the modified configuration, it can launch an attacker-controlled MCP server and execute code with the user's privileges, allowing it to read, change, or delete files accessible to that account. The approval bypass does not disable filesystem sandboxing; the default filesystem sandbox on macOS and Linux can prevent writes outside permitted locations.
appium-mcp-server through 0.1.61 fails to validate or normalize file paths in the write_file and write_files_batch tools, allowing attackers to write files outside the intended PROJECT_ROOT directory. Attackers can supply absolute paths or relative paths with parent directory segments to overwrite arbitrary files with the server user's privileges, including shell profiles and configuration files in the home directory.
The BetterDocs – AI Documentation, Knowledge Base, Docs, Wikis, FAQ with Chatbot plugin for WordPress is vulnerable to Stored Cross-Site Scripting via Heading 'id' Attribute in Post Content in all versions up to, and including, 4.8.1 due to insufficient input sanitization and output escaping. This makes it possible for authenticated attackers, with contributor-level access and above, to inject arbitrary web scripts in pages that will execute whenever a user accesses an injected page. The exploit survives wp_kses_post because entity-encoded quotes in a heading id attribute are treated as a single legitimate attribute value at save time; the dangerous payload only materialises after process_content_for_toc() calls html_entity_decode() on the stored content and the broken id is extracted by a lazy regex before being echoed unescaped into the Table of Contents output.
CVE-2026-82905 is a server-side request forgery (SSRF) vulnerability in the sdcb chats product affecting versions 1.0 through 1.12.0. The flaw exists in the McpController function within the fetch-tools endpoint, allowing remote attackers to manipulate requests. The vulnerability has a medium severity rating with a CVSS score of 5.3. Exploit code is publicly available, but no vendor response or patch has been provided as of the publication date.
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, the built-in prompt and resource controllers perform no role checking. The mutating POST/PUT /api/prompts* and POST/PUT /api/resources* routes are attached to the authenticated router with no admin gate, and the handlers never read req.user. The DAO singletons they write are consulted first — ahead of any connected MCP server — for every session in handleGetPromptRequest / handleReadResourceRequest. A non-admin can therefore create, overwrite, and shadow global prompt templates and resources that all other users are served. The scored impact is the unauthorized integrity violation (creation/tampering/shadowing of globally-served records); stored prompt injection into other users' LLM sessions is a downstream consequence of that tampering. This issue has been patched in version 1.0.32.
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.31, when a bearer key with accessType: 'servers' (or 'custom') is used against a group route, isBearerKeyAllowedForRequest grants access to the entire group as long as any single server in that group appears in the key's allowedServers list — not only when every server the key is scoped to matches, and critically, without ever re-checking allowedServers again once the group-level connection is authorized. A key explicitly scoped to one specific server therefore also grants full access to every other server that happens to share a group with it, including servers the key was never authorized for. This issue has been patched in version 1.0.31.
CVE-2026-79747 is a Server-Side Request Forgery (SSRF) vulnerability in samanhappy's MCPHub prior to version 1.0.32. An authenticated non-admin user can register a server with an arbitrary URL, causing the hub to issue server-side requests without egress filtering, including to loopback and private IP ranges. The vulnerability allows full response reflection via the OpenAPI proxy path and blind requests via the SSE/streamable-http transport. This issue has been patched in version 1.0.32.
CVE-2026-79748 is a critical vulnerability in samanhappy's MCPHub prior to version 0.12.15. It involves missing authorization checks on POST /api/servers and PUT /api/servers/:name endpoints, allowing any authenticated non-admin user to execute arbitrary OS commands as the MCPHub server user. The flaw arises because these endpoints spawn configured processes without restricting command or argument inputs, potentially leading to full system compromise. The issue has been patched in version 0.12.15.
CVE-2026-79749 is a Server-Side Request Forgery (SSRF) vulnerability in samanhappy mcphub prior to version 1.0.32. The vulnerability arises because the SSRF guard does not check certain IPv6 transition address families, allowing attackers to bypass protections by encoding private IPv4 addresses within these IPv6 formats. This can enable unauthorized access to internal infrastructure. The issue has been patched in version 1.0.32.
CVE-2026-81315 is an origin validation error vulnerability in ash-project's ash_ai server component that allows a malicious web page to bypass DNS-rebinding protections. The vulnerability arises because the server trusts the Host header and X-Forwarded-Proto header without proper validation, enabling an attacker to issue cross-site requests to a user's local MCP server with that user's privileges. This affects ash_ai versions from 0.8.0 up to but not including 1.0.0. The default configuration is insecure, but the fix involves restricting trusted origins to localhost and requiring an explicit allowlist for others.
CVE-2026-81848 is a server-side request forgery (SSRF) vulnerability in the cyberchitta scrapling-fetch-mcp package affecting versions 0.2.0, 0.2.1, and 0.2.2. The vulnerability exists in the s_fetch_page and s_fetch_pattern functions within src/scrapling_fetch_mcp/_fetcher.py. An attacker can remotely manipulate these functions to perform SSRF attacks. Upgrading to version 0.2.3 resolves the issue.
CVE-2026-81845 is a path traversal vulnerability in the arben-adm mcp-sequential-thinking component affecting versions up to 0.5.0. The flaw exists in the import_session/export_session functions of mcp_sequential_thinking/server.py, where manipulation of the file_path argument allows remote attackers to perform path traversal. The vulnerability has been publicly disclosed and a patch is available in version 0.6.0.
startServer.ts in the mcp-http-server package of UI-TARS-desktop defaulted its listen address to '::' when no host was given, so startSseAndStreamableHttpMcpServer bound the Streamable HTTP and SSE MCP transports to every interface, and its authentication middleware was optional: middlewares are applied only when a caller supplies them. The @agent-infra/mcp-server-commands and @agent-infra/mcp-server-filesystem entry points call startSseAndStreamableHttpMcpServer with a host and port alone and pass no middleware, so neither server required a credential. The commands server exposes a run_command tool that hands its caller-supplied command string to promisify(child_process.exec), so any unauthenticated client able to reach the port could run arbitrary commands as the user running the server, and the filesystem server exposed its file read and write tools on the same terms. The listen default became 127.0.0.1 in commit c2ad42e3eb9b27830db41a3e6f51ca7179d9b168; the package version stayed at 1.2.4 across that change, so the boundary is the commit rather than a release.
CVE-2026-81102 is a low-severity origin validation vulnerability in Dropbox's mcp-server-dash component. The server listener was bound to the loopback address but did not verify the host name of incoming requests. This allowed a malicious page in a visitor's browser to interact with the local server using the attacker's host name, potentially invoking company-search and file-detail tools under Dropbox credentials. The issue affected only the network mode of the server, not the standard input mode. The fix introduces transport-security settings that enforce host checking, restricting access to only the loopback name and port.
CVE-2026-81100 is a high-severity vulnerability in the timescale tiger-gh-mcp-server where the MCP HTTP transport did not enable host allow-listing, allowing it to accept requests with arbitrary host headers. This flaw stems from the httpServerFactory helper not setting the DNS-rebinding-protection option, enabling potential control of the locally reachable GitHub MCP endpoint via a maliciously crafted host name. The issue was fixed by explicitly passing the protection option alongside a dependency update. No official release includes this fix, so only the commit preceding the fix is affected.
CVE-2026-81099 is a high-severity vulnerability in the timescale tiger-slack product where the MCP HTTP transport did not enable host allow-listing, allowing DNS rebinding attacks. This flaw allows an attacker to craft a request with a controlled hostname to interact with the local Slack MCP server via a victim's browser. The issue was fixed by explicitly setting the DNS-rebinding-protection option alongside a dependency update. No official release version brackets the fix, so the affected versions are those prior to the commit containing the fix.