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

Back
New CVE Detected

CVE-2026-7664 – Authorization Bypass in MCP Endpoint – IBM Langflow OSS 1.0.0–1.8.4

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

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-7664 is a critical authorization bypass vulnerability (CVSS 9.8) affecting IBM Langflow OSS versions 1.0.0 through 1.8.4, an AI pipeline-building platform widely deployed as an internet-facing web application. The flaw stems from improper authorization enforcement in the Streamable MCP (Model Context Protocol) HTTP transport endpoint, allowing unauthenticated remote attackers to access protected MCP project resources and execute MCP operations without any credentials. IBM has released a fix and recommends immediate upgrade to version 1.9.1.

Technical details

  • Root cause: Improper authentication enforcement (CWE-287) in the Streamable HTTP MCP transport endpoint. The endpoint fails to correctly validate authorization before processing inbound MCP requests, exposing project-scoped resources and operations to unauthenticated callers.
  • Trigger conditions: Any internet-accessible Langflow instance running versions 1.0.0–1.8.4 is potentially vulnerable. Streamable HTTP is the default MCP transport in Langflow, served at the /streamable URL path, meaning default deployments are exposed without additional configuration changes.
  • Attack vector: Remote, unauthenticated network access. An attacker sends crafted HTTP requests to the Streamable MCP transport endpoint without supplying any credentials. No user interaction is required.
  • Impact: High impact across confidentiality, integrity, and availability. An attacker can read protected MCP project resources, execute arbitrary MCP operations (including triggering or manipulating AI pipelines), and potentially disrupt service availability. Langflow’s own documentation warns that without authentication configured, the MCP server "becomes a public endpoint that anyone can access."

Affected software

  • IBM Langflow OSS 1.0.0 through 1.8.4 (inclusive)

Severity

CVSS v3.1 base score: 9.8 (Critical)
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Mitigation and recommended actions

  • Immediate: Upgrade to IBM Langflow OSS version 1.9.1 or later, available on PyPI.
  • IBM’s security bulletin documents no available workarounds or interim mitigations; upgrading to 1.9.1 is the only supported remediation path.
  • Until patching is complete, consider restricting network-level access to Langflow instances and ensuring MCP server authentication is explicitly enabled, as Langflow documentation notes that unauthenticated MCP deployments are fully publicly accessible.

IONIX Status

The IONIX research team is tracking ongoing exploitation attempts and recommends immediate patching. Potentially affected assets are outlined in this post.

References

Are you exposed?

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

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

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

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

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

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge