mcp-security provides Security and Authorization support for Model Context Protocol in Spring AI. Prior to 0.1.9, the mcp-security framework fails to implement the mandatory SSRF mitigations outlined in the Model Context Protocol (MCP) security specifications. Specifically, it processes untrusted URLs for OAuth-related discovery and metadata without verifying if the targets are malicious or internal to the network. This only affects installations with Dynamic Client Registration (DCR) enabled This vulnerability is fixed in 0.1.9.
mcp-security: Unvalidated URL Fetching (SSRF)
Problem type
Affected products
spring-ai-community
< 0.1.9 - AFFECTED
References
GitHub Security Advisories
GHSA-qjp4-4jvr-xqg3
Spring AI MCP Security: Unvalidated URL Fetching (SSRF)
https://github.com/advisories/GHSA-qjp4-4jvr-xqg3Summary
The mcp-security framework fails to implement the mandatory SSRF mitigations outlined in the Model Context Protocol (MCP) security specifications. Specifically, it processes untrusted URLs for OAuth-related discovery and metadata without verifying if the targets are malicious or internal to the network.
This only affects installations with Dynamic Client Registration (DCR) enabled:
spring.ai.mcp.client.authorization.dynamic-client-registration.enabled=true
DCR does not validate URLs exposed by MCP Servers (protected resource metadata URL, authorization server URL) and Authorization Servers (all OAuth2 endpoints).
Workaround
When users need to perform DCR, they may provide their own McpOAuth2ClientManager. Both McpMetadataDiscoveryService and DynamicClientRegistrationService are also affected, if used, users should provide their own subclasses.
Alternatively, users can provide the default implementations of these classes with a RestClient that implements URL filtering through ClientHttpRequestInterceptor.
https://github.com/spring-ai-community/mcp-security/security/advisories/GHSA-qjp4-4jvr-xqg3
https://github.com/spring-ai-community/mcp-security/pull/68
https://github.com/spring-ai-community/mcp-security/commit/e6b67d8a67cd7acbee6e4c0741c385d62e3ed576
https://github.com/spring-ai-community/mcp-security/releases/tag/v0.1.9
https://github.com/advisories/GHSA-qjp4-4jvr-xqg3
JSON source
https://cveawg.mitre.org/api/cve/CVE-2026-45609Click to expand
{
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"cveMetadata": {
"cveId": "CVE-2026-45609",
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"dateUpdated": "2026-05-29T13:48:06.703Z",
"dateReserved": "2026-05-12T20:31:43.447Z",
"datePublished": "2026-05-29T13:48:06.703Z",
"state": "PUBLISHED"
},
"containers": {
"cna": {
"providerMetadata": {
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M",
"dateUpdated": "2026-05-29T13:48:06.703Z"
},
"title": "mcp-security: Unvalidated URL Fetching (SSRF)",
"descriptions": [
{
"lang": "en",
"value": "mcp-security provides Security and Authorization support for Model Context Protocol in Spring AI. Prior to 0.1.9, the mcp-security framework fails to implement the mandatory SSRF mitigations outlined in the Model Context Protocol (MCP) security specifications. Specifically, it processes untrusted URLs for OAuth-related discovery and metadata without verifying if the targets are malicious or internal to the network. This only affects installations with Dynamic Client Registration (DCR) enabled This vulnerability is fixed in 0.1.9."
}
],
"affected": [
{
"vendor": "spring-ai-community",
"product": "mcp-security",
"versions": [
{
"version": "< 0.1.9",
"status": "affected"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"lang": "en",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"cweId": "CWE-918",
"type": "CWE"
}
]
}
],
"references": [
{
"url": "https://github.com/spring-ai-community/mcp-security/security/advisories/GHSA-qjp4-4jvr-xqg3",
"name": "https://github.com/spring-ai-community/mcp-security/security/advisories/GHSA-qjp4-4jvr-xqg3",
"tags": [
"x_refsource_CONFIRM"
]
}
],
"metrics": [
{
"cvssV3_1": {
"version": "3.1",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N",
"attackVector": "NETWORK",
"attackComplexity": "LOW",
"privilegesRequired": "NONE",
"userInteraction": "NONE",
"scope": "CHANGED",
"confidentialityImpact": "LOW",
"integrityImpact": "LOW",
"availabilityImpact": "NONE",
"baseScore": 7.2,
"baseSeverity": "HIGH"
}
}
]
}
}
}