CVE•Published 2025-12-17•Modified 2026-09-30•1 article on news•4 live references•NVD data

CVE-2025-68143Lfprojects · Model_context_protocol_servers

Vulnerability data via NVD (ingested)

CVSS v3.1
8.8
HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
EPSS percentile
95
Exploit Prediction Scoring System · top 5% of all CVEs
Description

Model Context Protocol Servers is a collection of reference implementations for the model context protocol (MCP). In mcp-server-git versions prior to 2025.9.25, the git_init tool accepted arbitrary filesystem paths and created Git repositories without validating the target location. Unlike other tools which required an existing repository, git_init could operate on any directory accessible to the server process, making those directories eligible for subsequent git operations. The tool was removed entirely, as the server is intended to operate on existing repositories only. Users are advised to upgrade to 2025.9.25 or newer to remediate this issue.

Timeline
Published 2025-12-17
Modified 2026-09-30

External references

Search for exposed instances

Shodan + Censys queries derived from NVD's CPE data. The vuln tag catches assets Shodan has explicitly linked to this CVE; the product / banner fingerprints find exposed instances even when the vuln tag was never applied (which is common).

More intel sources (5)

Known PoCs on GitHub (8)

h5i-dev/awesome-ai-agent-incidentsunknown
A curated corpus of incidents, attack vectors, failure modes, and defensive tools for autonomous AI agents.
★ 57·updated today
mcp-security-project/mcp-cve-projectunknown
The Project shares all information on MCP related CVE's published
★ 28·updated 2w ago
AndrewAltimit/exploitsPython
Security research and exploit development: vulnerability analysis, exploit chain implementation, post-exploitation tradecraft, and defensive assessment tooling. Covers browser engi…
★ 15·updated 4mo ago
deconvolute-labs/deconvolutePython
Policy-as-code enforcement and observability for MCP tool calls. Wraps AI agent sessions with cryptographic integrity checks, argument-level CEL policies, and a full audit trail.
★ 8·updated 2mo ago
paolovella/vellavetoRust
Agentic security control plane for MCP and AI agent tool calls. MCP-native policy gateway with topology discovery and audit.
★ 6·updated 3d ago
GMU-CYSE/adop-cysePython
ADOP MVP testbed (CYSE-587/SYST-687): pinned MCP reference servers, synthetic repository, fixed task set, audit layer, and frozen log corpus
★ 2·updated 1mo ago
mattschaller/eslint-plugin-mcp-securityTypeScript
ESLint security rules for MCP servers — catches SANDWORM_MODE credential harvesting, path traversal, command injection, and CVE patterns at dev time
★ 2·updated 6d ago
Agent-Warden/Agent-WardenPython
Open-source security scanner for MCP servers — finds auth issues, SSRF, prompt injection, and more before attackers do.
★ 2·updated 5mo ago