Model Context Protocol

PraisonAI 4.6.63's MCP HTTP-stream server applies authentication only when an API key is set, and the CLI defaults `--api-key` to `None`, so `praisonai mcp serve --transport http-stream` exposes the full MCP surface without authentication. An unauthenticated client can call `initialize` and `tools/list` (about 50 tools), and the dispatcher in `mcp_server/server.py` forwards tool-call arguments to handlers without validating them against the advertised `inputSchema`. The source states this is not an RCE or file read in 4.6.63, because `workflow.run` and `workflow.run_file` fail at runtime.

Langflow versions 1.5.0 through 1.10.3 contain an IP spoofing flaw in the MCP configuration installation endpoint, POST /api/v1/mcp/project/{project_id}/install. An authenticated remote attacker can send a spoofed X-Forwarded-For: 127.0.0.1 header, making the server treat the request as local and bypass the "local-only" restriction. This lets the attacker write or overwrite an MCP client configuration file on the server's filesystem.

Langflow versions from 1.6.8 through 1.9.1 fail to authorize the resource URI passed to resources/read on project-scoped MCP connections. An authenticated user with access to any project-scoped MCP endpoint can read another user's flow-backed files, including uploaded documents, structured data, prompts and other private flow artifacts. Global handle_list_resources and handle_list_tools behavior can also disclose the flow and file identifiers needed to target them. Victim files and stored flows are not modified.

CVE-2026-97662 is an argument injection flaw in the diff scan operation of security-agent-mcp-server, an open-source MCP server published by AWS in the awslabs/mcp repository. Affected versions are 0.1.1 up to but not including 0.2.0. A crafted reference value is parsed as a command-line option instead of a revision, letting a context-dependent actor create, overwrite, or truncate arbitrary files on the host outside the workspace directory and bypass the server's workspace-confinement control.

The AI Engine plugin for WordPress, up to and including 3.8.0, contains a stored cross-site scripting flaw. An unauthenticated attacker can send crafted input to the /mwai-ui/v1/chats/submit REST endpoint, which writes an attacker-controlled string into the PHP error log as a forged line. The plugin's Advisor feature then passes that content into an AI prompt and stores the result unescaped, so the injected script runs when an administrator opens the WordPress dashboard.

Prior to version 5.1.0, token-optimizer-mcp is vulnerable to OS command injection in the smart_user tool. Any MCP client that can call smart_user can run arbitrary shell commands through the username argument of the get-user-info operation, with the privileges of the user running the server.

The Cline Hub dashboard server (`@cline/cline-hub`), launched with the `cline dashboard` CLI command, accepts WebSocket connections on `/browser` without validating the HTTP `Origin` header. When `ROOM_SECRET` is unset, which is the default for `127.0.0.1` binds, `isAuthorizedBrowserRequest()` returns `true`, so any website a developer visits can open a cross-origin WebSocket to `ws://127.0.0.1:8787/browser`. Dashboard sessions default to `autoApprove: true` for all tools, and the source reports that an injected `upsert_mcp_server` frame wrote a malicious `stdio` MCP server entry into the victim's Cline settings file.

IBM Financial Transaction Manager (FTM) for RedHat OpenShift is affected by CVE-2026-18875, a RAG poisoning flaw (CWE-74) caused by an unauthenticated runbook upsert in the FTM AI agent server at api.vectordb.runbooks.js:51. An unauthenticated attacker can insert malicious runbook content into the agent's vector database. This can steer AI-driven MCP tool calls, potentially triggering unauthorized payment actions or exfiltrating payment data.

The upload_attachment method in confluence/attachments.py of mcp-atlassian reads and uploads arbitrary local files to Confluence without calling validate_safe_path(), although the download methods do call it. An MCP-connected AI agent, or an attacker influencing it through prompt injection, can read any file the server process can access, such as SSH keys, AWS credentials or .env files, and exfiltrate it as a Confluence page attachment. The issue was reproduced with mcp-atlassian 0.21.1 on Python 3.11.