Skip to content
Heist/ feed
Back to feed
High

Chainlit: SSRF via MCP SSE and streamable-http transports allows unauthenticated internal network access

Type: advisorySources: OSV

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.

Products
Not specified
Affected versions
Not specified
Fixed versions
Not specified
CVEs
CVE-2026-45019
Confirmed fixed CVEs
Not specified
Updated in this feed
4 Nov 2026, 13:55 UTC · Revision 1

Source evidence

Chainlit: SSRF via MCP SSE and streamable-http transports allows unauthenticated internal network access

core-osv · Original source

Published 25 Aug 2026, 19:20 UTC

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.

osv:CVE-2026-45019
Complete source record
{
  "id": "fa62b5834fdbab53765aed525d0f1268aeed04c72f6b6aeb4e4afa6bcaa7d9eb",
  "url": "https://osv.dev/vulnerability/CVE-2026-45019",
  "method": "structured",
  "payload": {
    "kind": "advisory",
    "title": "Chainlit: SSRF via MCP SSE and streamable-http transports allows unauthenticated internal network access",
    "summary": "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.",
    "evidence": "osv:CVE-2026-45019",
    "products": [],
    "severity": "high",
    "structured": {
      "id": "CVE-2026-45019",
      "aliases": [
        "CVE-2026-45019",
        "GHSA-hvfh-5mj3-5f3j",
        "PYSEC-2026-3811"
      ],
      "metrics": [
        {
          "type": "CVSS_V3",
          "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N"
        }
      ],
      "affected": [
        {
          "ranges": [
            {
              "repo": "https://github.com/chainlit/chainlit",
              "type": "GIT",
              "events": [
                {
                  "introduced": "dc13fc0c858ce65814b685ee39dc112a3bd38c87"
                },
                {
                  "fixed": "0565fd0eccb915fce159929598b053ed79f6e0c9"
                }
              ],
              "database_specific": {
                "extracted_events": [
                  {
                    "range": [
                      {
                        "introduced": "2.4.0rc0"
                      },
                      {
                        "fixed": "2.12.0"
                      }
                    ],
                    "source": "AFFECTED_FIELD",
                    "strategy": "StringRangeExpression"
                  },
                  {
                    "range": [
                      {
                        "fixed": "0565fd0eccb915fce159929598b053ed79f6e0c9"
                      }
                    ],
                    "source": "REFERENCES_COMMIT"
                  },
                  {
                    "range": [
                      {
                        "fixed": "0565fd0eccb915fce159929598b053ed79f6e0c9"
                      }
                    ],
                    "source": "REFERENCES_TAG",
                    "original_tag": "2.12.0"
                  },
                  {
                    "range": [
                      {
                        "introduced": "0"
                      },
                      {
                        "fixed": "2.12.0"
                      }
                    ],
                    "source": "DESCRIPTION"
                  }
                ]
              }
            }
          ],
          "versions": [
            "2.11.1",
            "2.11.0",
            "2.10.1",
            "2.10.0",
            "2.9.6",
            "2.9.5",
            "2.9.4",
            "2.9.3",
            "2.9.2",
            "2.9.1",
            "2.9.0",
            "2.8.5",
            "2.8.4",
            "2.8.3",
            "2.8.2",
            "2.8.1",
            "2.8.0",
            "2.7.2",
            "2.7.1.1",
            "2.7.1",
            "2.7.0",
            "2.6.9",
            "2.6.8",
            "2.6.7",
            "2.6.6",
            "2.6.5",
            "2.6.4",
            "2.6.3",
            "2.6.2",
            "2.6.1",
            "2.6.0",
            "2.5.5",
            "2.4.400",
            "2.4.302",
            "2.4.301",
            "2.4.3",
            "2.4.201",
            "2.4.2",
            "2.4.1",
            "2.4.0",
            "2.4.0rc0"
          ],
          "database_specific": {
            "source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-45019.json"
          }
        }
      ],
      "modified": "2026-10-28T02:30:35.865165407Z",
      "provider": "osv",
      "references": [
        "https://github.com/Chainlit/chainlit/releases/tag/2.12.0",
        "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/45xxx/CVE-2026-45019.json",
        "https://github.com/Chainlit/chainlit/blob/2.12.0/docs/security-advisory-2026-mcp.md#spl-2026-002--ssrf-via-mcp-streamable-http--sse",
        "https://github.com/Chainlit/chainlit/security/advisories/GHSA-hvfh-5mj3-5f3j",
        "https://nvd.nist.gov/vuln/detail/CVE-2026-45019",
        "https://github.com/Chainlit/chainlit/commit/0565fd0eccb915fce159929598b053ed79f6e0c9"
      ],
      "provider_metadata": {
        "cwe_ids": [
          "CWE-918"
        ],
        "cna_assigner": "GitHub_M",
        "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/45xxx/CVE-2026-45019.json"
      }
    },
    "related_cves": [
      {
        "value": "CVE-2026-45019",
        "evidence": "/id"
      }
    ],
    "security_relevant": true,
    "severity_evidence": "/severity/0/score"
  },
  "source_id": "core-osv",
  "document_id": 503365,
  "published_at": "2026-08-25T19:20:59.339+00:00"
}