CVE-2026-45019

What it is

Chainlit is a Python framework for building production-ready conversational AI applications. From 2.4.0rc0 until 2.12.0, Chainlit deployments with features.mcp.enabled set to true in .chainlit/config.toml expose the POST /mcp endpoint without requiring authentication. For sse and streamable-http transports, ConnectSseMCPRequest and ConnectStreamableHttpMCPRequest in backend/chainlit/types.py accept a user-controlled url and optional headers dictionary without scheme validation, private-address filtering, or an allowlist. The connect_mcp handler in backend/chainlit/server.py passes these values to sse_client() or streamablehttp_client(), allowing the Chainlit server to make blind outbound requests to arbitrary internal or external services, including cloud metadata endpoints, with attacker-controlled Authorization and Cookie headers. The SSE URL sink has existed since 2.4.0rc0, while attacker-controlled header forwarding and streamable-http support were added in 2.6.4. The response is consumed internally and not returned, but the attacker can issue state-changing authenticated requests, discover internal services, scan ports, and probe metadata endpoints. This issue is fixed in version 2.12.0.

At a glance

Exploitability

Can be exploited over the network without logging in. Limited direct impact.

Exploit odds

0.4% chance of exploitation in the next 30 days (EPSS).

Fix

A patch, advisory or fixed version is referenced. Upgrade or apply it.

Timeline

1. 2026-08-25 20:16 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-09-09 21:07 UTC Last updatedMost recent change to the record

Details

Published

2026-08-25 20:16 UTC

Last modified

2026-09-09 21:07 UTC

Exploit probability

0.4% · EPSS, next 30 days

Weakness

CWE-918 · Server-side request forgery

Record status

Deferred

Attack profile CVSS 3.1 · 7.2

Attack vector

Network

Complexity

Low

Privileges needed

None

User interaction

None

Scope

Changed

Confidentiality

Low

Integrity

Low

Availability

None