Authenticated RCE via MCP tool addition
Any authenticated Langflow user before version 1.9.0 can execute arbitrary code on the server by adding a crafted MCP server or tool. Patch to 1.9.0 immediately.
- Vendor
- Langflow
- Product
- Langflow (prior to 1.9.0)
- CVSS
- 9.9
- EPSS (exploit probability)
- 3.9%
- Status
- patched
- Published
Is CVE-2026-105740 being exploited?
Not on any exploited-vulnerability catalog we track. CVE-2026-105740 was not on the CISA, ENISA or CIRCL exploited catalogs as of our 2026-11-22 snapshot. That can change quickly; check the write-up below for the latest reporting.
FIRST's EPSS model puts the probability of exploitation activity in the next 30 days at 3.9% (scored November 4, 2026).
- CISA KEV[ — ]
- ENISA EUVD (exploited)[ — ]
- CIRCL KEV[ — ]
Catalog snapshot 2026-11-22. Full cross-catalog view: /kev-comparison
CVE-2026-105740 timeline
Every event links to its source. Catalog dates are each catalog's own; day offsets count from NVD publication. Data: JSON
CVE-2026-105740 affects Langflow, the open-source platform for building and deploying AI agent workflows. In versions prior to 1.9.0, the Model Context Protocol (MCP) server and tool handler did not adequately restrict execution on the server side. Any authenticated user could add a malicious MCP tool and trigger remote code execution on the server without needing elevated permissions.
The CVSS score of 9.9 reflects the low attack complexity and low privileges required: a standard account is enough. The flaw is patched in version 1.9.0.
What to do: Update to Langflow 1.9.0 or later. Audit account access on shared or multi-user instances. If patching is delayed, restrict MCP tool creation at the application or network level.
Other Langflow CVEs we track
| CVE / Vulnerability | Severity | CVSS | EPSS | Added to KEV |
|---|---|---|---|---|
| CVE-2026-93674 Langflow Authenticated Blind Command Injectionwrite-up | [ CRITICAL ] | 9.8 | 14.1% | — |
| CVE-2026-7873 Langflow Authenticated RCE via Code Validation Endpointwrite-up | [ CRITICAL ] | 9.9 | 6.9% | — |
| CVE-2026-10134 Langflow Unauthenticated RCE in Public Flow Build Endpointwrite-up | [ CRITICAL ] | 10.0 | 2.3% | — |
| CVE-2026-0769 Langflow Unauthenticated RCE via Custom Component Evaluationwrite-up | [ CRITICAL ] | 9.8 | 41.2% | — |
| CVE-2026-0768 Langflow Unauthenticated RCE via Code Execution Endpointwrite-up | [ CRITICAL ] | 9.8 | 28.1% | — |
| CVE-2026-0770 Langflow validate-endpoint exec_globals RCE (unauthenticated)write-up | [ CRITICAL ] | 9.8 | 62.6% | |
| CVE-2026-55255 Langflow /api/v1/responses IDOR — cross-user flow executionwrite-up | [ HIGH ] | 8.4 | 0.9% | |
| CVE-2025-34291 Langflow CORS misconfiguration enables CSRF-driven token theft and RCEwrite-up | [ HIGH ] | 8.8 | 93.2% |
