The MCP inspector is a developer tool for testing and debugging MCP servers. Versions of MCP Inspector below 0.14.1 are vulnerable to remote code execution due to lack of authentication between the Inspector client and proxy, allowing unauthenticated requests to launch MCP commands over stdio. Users should immediately upgrade to version 0.14.1 or later to address these vulnerabilities.
https://thehackernews.com/2026/04/anthropic-mcp-design-vulnerability.html
https://thehackernews.com/2025/07/critical-mcp-remote-vulnerability.html
https://thehackernews.com/2025/07/critical-vulnerability-in-anthropics.html
https://github.com/shunfeng8421/exploit-library
https://github.com/shunfeng8421/security-audit
https://github.com/ak4hit/mcp-hardening-benchmark
https://github.com/patchwright/mcp-lint
https://github.com/TYehan/CVE-2026-23744
https://github.com/SuriyaBoon/DevHub-HackTheBox-ss11
https://github.com/phoenix-assistant/mcp-security-scanner
https://github.com/studiomeyer-io/mcp-armor
https://github.com/boxed-dev/vibe-coding-security
https://github.com/acseguin21/trust-boundary-ctf
https://github.com/pppxo/CVE-2025-49596-PoC
https://github.com/InzegoSec/CVE-2026-23744
https://github.com/Acczdy/CVE-Vault
https://github.com/skew202/agentic-ide-security
https://github.com/ashiqrehan-21/MCP-Inspector-CVE-2025-49596
https://www.oligo.security/blog/critical-rce-vulnerability-in-anthropic-mcp-inspector-cve-2025-49596
https://thenewstack.io/mcp-vulnerability-exposes-the-ai-untrusted-code-crisis
https://github.com/modelcontextprotocol/inspector/security/advisories/GHSA-7f8r-222p-6f5g
https://github.com/modelcontextprotocol/inspector/commit/50df0e1ec488f3983740b4d28d2a968f12eb8979
Published: 2025-06-13
Updated: 2026-04-15
Base Score: 7.5
Vector: CVSS2#AV:N/AC:L/Au:N/C:P/I:P/A:P
Severity: High
Base Score: 9.8
Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Severity: Critical
Base Score: 9.4
Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
Severity: Critical
EPSS: 0.44453