635 matches found
pentest-mcp
Pentest MCP Pentest MCP is a TypeScript MCP server for authorized security assessments. It gives a human researcher or a tool-using assessment agent one scoped interface for discovery, validation, capture, credential checks, local audit, evidence retrieval, and report preparation. Each active too...
studio
ShipSec Studio Open-Source Security Workflow Orchestration Platform. ShipSec is currently in active development. We are optimizing the platform for stable production use and high-performance security operations. ShipSec Studio provides a visual DSL and runtime for building, executing, and...
damn-vulnerable-MCP-server
Cursor SSE Compatibility for Damn Vulnerable MCP This document provides an overview of the updates made to the Damn Vulnerable Model Context Protocol DVMCP project to make it compatible with Cursor's Server-Sent Events SSE implementation. Overview The original DVMCP project has been enhanced to...
sandbox-agent
Agents Agent infrastructure from Rivet. Join us on Discord. Projects Project| Directory| Docs ---|---|--- Rivet Agents : run agents such as Pi as durable Rivet Actors @rivet-dev/pi, @rivet-dev/sandbox-adapter| packages/, docs in docs/| rivet.dev/agents/docs Sandbox Agent : run coding agents in...
GitLab MCP Server < 2.1.27 - Unauthenticated SSE Transport Access
The @zereight/mcp-gitlab GitLab MCP server exposes its SSE transport endpoints without any authentication when SSE mode is enabled. An unauthenticated attacker with network access can establish an MCP session and invoke every registered tool, including uploadmarkdown, which reads arbitrary files...
MCP-Inspector-CVE-2025-49596
MCP Inspector CVE-2025-49596 Vulnerability Checker This script checks if an MCP Inspector server is vulnerable to CVE-2025-49596, a security issue where the /sse endpoint responds to unauthenticated requests missing auth token. How It Works The script sends a GET request to the /sse endpoint of t...
CVE-2026-129875
REBUILD 4.5.0 through 4.5.4 contains an information disclosure vulnerability that allows low-privileged authenticated users to recover the administrator password hash by filtering User.password through the MCP QueryRecords tool. Attackers can send LK2 prefix-match filters to the /gw/mcp/sse gatew...
EUVD-2026-126445
REBUILD 4.5.0 through 4.5.4 contains an information disclosure vulnerability that allows low-privileged authenticated users to recover the administrator password hash by filtering User.password through the MCP QueryRecords tool. Attackers can send LK2 prefix-match filters to the /gw/mcp/sse gatew...
CVE-2026-129875 REBUILD 4.5.0 through 4.5.4 Password Hash Disclosure via MCP QueryRecords
REBUILD 4.5.0 through 4.5.4 contains an information disclosure vulnerability that allows low-privileged authenticated users to recover the administrator password hash by filtering User.password through the MCP QueryRecords tool. Attackers can send LK2 prefix-match filters to the /gw/mcp/sse gatew...
firecrawl-mcp-server
Firecrawl MCP Server A Model Context Protocol MCP server that brings Firecrawl, the context API for AI agents, to MCP-compatible clients: search, scrape, and interact with the live web and get back clean Markdown or structured data. Big thanks to @vrknetha, @knacklabs for the initial...
POC-CVE-2026-93680
Description Proof of concept exploit code for CVE-2026-93680 Usage Step 1: Connect to MCP SSE terminal 1 Step 2: Initialize MCP session and list MCP tools terminal 2 Step 3: Bypass auth and exfiltrate data terminal 1, output result of step 2...
CVE-2026-34227
Unauthenticated MCP Interface + CORS Bypass Sliver's MCP server spins up an unauthenticated SSE interface and fires back Access-Control-Allow-Origin: on every response. The mcp-go library doesn't validate Content-Type, so Simple Requests text/plain skip the browser's preflight check entirely. No...
EUVD-2026-125435
@utcp/http before 1.1.14 contains a server-side request forgery vulnerability that allows remote manuals to reach loopback services by bypassing the remote-loopback check with a host placeholder. Attackers can supply host arguments like 127.0.0.1 or register tools via Streamable HTTP and SSE...
PT-2026-146930
@utcp/http before 1.1.14 contains a server-side request forgery vulnerability that allows remote manuals to reach loopback services by bypassing the remote-loopback check with a host placeholder. Attackers can supply host arguments like 127.0.0.1 or register tools via Streamable HTTP and SSE...
CVE-2026-67542
Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.70, POST /api/mcp/fetch-tools is reachable by any authenticated user lowest role; no admin/workflow association and fetches an attacker-supplied URL through the sse and...
CVE-2026-67542
Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.70, POST /api/mcp/fetch-tools is reachable by any authenticated user lowest role; no admin/workflow association and fetches an attacker-supplied URL through the sse and...
CVE-2026-67542 Heym: SSRF via POST /api/mcp/fetch-tools: any authenticated user reaches local/private URLs through the SSE and streamable-HTTP transports
Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.70, POST /api/mcp/fetch-tools is reachable by any authenticated user lowest role; no admin/workflow association and fetches an attacker-supplied URL through the sse and...
EUVD-2026-124043
Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.70, POST /api/mcp/fetch-tools is reachable by any authenticated user lowest role; no admin/workflow association and fetches an attacker-supplied URL through the sse and...
CVE-2026-67542 Heym: SSRF via POST /api/mcp/fetch-tools: any authenticated user reaches local/private URLs through the SSE and streamable-HTTP transports
Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.70, POST /api/mcp/fetch-tools is reachable by any authenticated user lowest role; no admin/workflow association and fetches an attacker-supplied URL through the sse and...
CVE-2026-67542
The Heym platform for agentic systems and business-process automations is vulnerable to Server-Side Request Forgery (SSRF) prior to version 0.0.70 . The issue exists in the POST /api/mcp/fetch-tools endpoint, which is accessible to any authenticated user. An attacker can force the application to ...