Every CVE Search/ Get API key

CVE-2026-45609

mcp-security: Unvalidated URL Fetching (SSRF)

7.2 HighFix available

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.

Attack profile

How easy it is to exploit

Attack vector
Network
Complexity
Low
Privileges needed
None
User interaction
None

What an attacker can affect

Confidentiality
Low
Integrity
Low
Availability
None

Exploit likelihood

0.21%Up 0.2 points since May 30, 2026
90%50%10%1%

What each source reports

CVE List Score used 7.2

mcp-security: Unvalidated URL Fetching (SSRF)

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.

Record
CVE-2026-45609
CVSS 3.1
7.2 HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N
Weakness
CWE-918
Updated
2026-11-02
EUVDEUVD-2026-33323 7.2

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.

Record
EUVD-2026-33323
CVSS 3.1
7.2 HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N
Updated
2026-11-02
GitHub AdvisoriesGHSA-qjp4-4jvr-xqg3 7.2

Spring AI MCP Security: Unvalidated URL Fetching (SSRF)

Summary

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.

Record
GHSA-qjp4-4jvr-xqg3
CVSS 3.1
7.2 HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N
Weakness
CWE-918
Updated
2026-11-02
NVD 7.2

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.

Record
CVE-2026-45609
CVSS 3.1
7.2 HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N
CVSS 3.1
6.5 MediumCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
Weakness
CWE-918
Updated
2026-11-02
OSV 7.2

mcp-security: Unvalidated URL Fetching (SSRF)

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.

Record
CVE-2026-45609
CVSS 3.1
7.2 HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N
Weakness
CWE-918
Updated
2026-11-02
OSVGHSA-qjp4-4jvr-xqg3 7.2

Spring AI MCP Security: Unvalidated URL Fetching (SSRF)

Summary

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.

Record
GHSA-qjp4-4jvr-xqg3
CVSS 3.1
7.2 HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N
Weakness
CWE-918
Updated
2026-11-02

Affected products

Affected packages

Affected packages
PackageAffectedFixed
org.springaicommunity:mcp-client-security
Maven
before 0.1.9
0.1.9
org.springaicommunity:mcp-client-security
Maven
before 0.1.9, plus listed versions
0.0.10.0.20.0.30.0.40.0.5
Show 10 moreShow less
0.0.60.1.00.1.10.1.20.1.30.1.40.1.50.1.60.1.70.1.8
0.1.9

History

History
RecordedChangedSources
first indexedCVE List, EUVD, GitHub Advisories, NVD, OSV

Dates are when Every CVE recorded each change. Upstream dates may differ.

In short

CVE-2026-45609 is a high vulnerability (CVSS 7.2) in Spring-ai-community Mcp-security, published May 18, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.21%, the 10th percentile. Fixed in org.springaicommunity:mcp-client-security 0.1.9.

References

MoveEnter Open