CVE-2026-45609
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.
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
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 High
CVSS: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 High
CVSS: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 High
CVSS: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 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N - CVSS 3.1
- 6.5 Medium
CVSS: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 High
CVSS: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 High
CVSS: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
| Package | Affected | Fixed |
|---|---|---|
org.springaicommunity:mcp-client-securityMaven |
before 0.1.9 | 0.1.9 |
org.springaicommunity:mcp-client-securityMaven |
before 0.1.9, plus listed versions 0.0.10.0.20.0.30.0.40.0.5 Show 10 moreShow less0.0.60.1.00.1.10.1.20.1.30.1.40.1.50.1.60.1.70.1.8 |
0.1.9 |
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE 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
github.com/spring-ai-community/mcp-security/security/advisories/GHSA-qjp4-4jvr-xqg3
github.com/spring-ai-community/mcp-security/pull/68
github.com/spring-ai-community/mcp-security/commit/e6b67d8a67cd7acbee6e4c0741c385d62e3ed576
github.com/spring-ai-community/mcp-security/releases/tag/v0.1.9
nvd.nist.gov/vuln/detail/CVE-2026-45609
github.com/advisories/GHSA-qjp4-4jvr-xqg3
github.com/CVEProject/cvelistV5/tree/main/cves/2026/45xxx/CVE-2026-45609.json
github.com/spring-ai-community/mcp-security