Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

New CVE Detected

CVE-2026-81094 – Missing Authentication / Unauthenticated Network Exposure – mcp-router before 0.6.3

Be the first to know when new zero-days emerge:

Summary

CVE-2026-81094 is a missing-authentication vulnerability (CWE-306) affecting mcp-router, an open-source MCP (Model Context Protocol) aggregator/CLI. In vulnerable versions, the serve command bound the aggregator to all network interfaces by default and only enforced authentication when an operator explicitly configured it, leaving the service reachable and usable by anyone who could route traffic to the listening port. The issue carries a CVSS v3.1 base score of 9.1 (CVSS v4.0: 9.3), reflecting network-exploitable, low-complexity, unauthenticated access with a high confidentiality impact.

Technical details

  • Root cause: The mcp-router serve command defaulted to binding on all network interfaces (0.0.0.0) rather than localhost, and did not mandate an authentication token unless the operator explicitly configured one.
  • Trigger conditions: Any deployment running mcp-router serve with default settings on a host reachable over a network (e.g., not restricted by firewall/NAT) is exposed; no special configuration is required to trigger exposure — it is the out-of-the-box behavior.
  • Attack vector: Network (AV:N) — a remote, unauthenticated attacker who can reach the exposed port can connect directly to the MCP aggregator.
  • Impact: Unauthorized access to the MCP aggregator allows an attacker to interact with aggregated MCP servers/tools without credentials, resulting in high confidentiality impact (potential exposure of aggregated tool data/configuration); integrity/availability impact is not indicated in the scoring (I:N/A:N per CVSS v3.1 vector observed in source data, C:H).

Affected software

  • Product: mcp-router (https://github.com/mcp-router/mcp-router)
  • Versions affected: All versions prior to 0.6.3
  • Fixed version: 0.6.3 and later (fix commit 4c4642cfd274097ec8b33ecd3047390829c79d35)

Severity

  • CVSS v3.1 Base Score: 9.1 (Critical) — CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
  • CVSS v4.0 Score: 9.3 (Critical) — CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N
  • CWE-306: Missing Authentication for Critical Function

Mitigation and recommended actions

  • Immediate: Upgrade mcp-router to version 0.6.3 or later, which changes the serve command’s default bind address to 127.0.0.1 (localhost only) and enforces that a --token be supplied whenever a non-loopback --host is specified, ensuring network-exposed instances require authentication.
  • If immediate patching is not possible:
    • Restrict network access to the mcp-router listening port using host-based firewalls, security groups, or network segmentation so it is reachable only from trusted hosts.
    • Do not run serve bound to a public or non-loopback interface without explicitly configuring an authentication token.
    • Audit existing deployments for instances currently bound to 0.0.0.0 or other non-loopback interfaces without authentication configured, and reconfigure them to bind to localhost or require a token immediately.
    • Review logs/network traffic for unexpected inbound connections to the mcp-router port as an indicator of possible exploitation prior to remediation.

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge