Spring AI MCP Security: Unvalidated URL Fetching (SSRF)
CVE-2026-45609 · GHSA-qjp4-4jvr-xqg3 · published 2026-05-18 · updated 2026-06-09
- Severity
- High
- CVSS score
- 7.2
- Chance of exploitation (EPSS)
- 0.21%
- Fixed in
- 0.1.9
- Exploitation No known exploitation
- Automatable Yes
- Technical impact Partial
- CISA SSVC
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: DCR does not validate URLs exposed by MCP Servers (protected resource metadata URL, authorization server URL) and Authorization Servers (all OAuth2 endpoints).
Upgrade org.springaicommunity:mcp-client-security to 0.1.9 or later.
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.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| org.springaicommunity:mcp-client-security | Maven | < 0.1.9 | 0.1.9 |
- CriticalMLflow: Unauthenticated full-read SSRF in webhook delivery: _validate_webhook_url bypassed via unvalidated HTTP redirects (and DNS rebindingmlflowExploited
- Critical@zereight/mcp-gitlab Vulnerable to Server-Side Request Forgery@zereight/mcp-gitlab
- CriticalSSRF + LLM API key exfiltration via user-controlled basepath / baseUrl in 8 chat-model nodesflowise, flowise-components
- CriticalLocalAI POST /models/apply permits unauthenticated server-side request forgery through gallery URLsgithub.com/mudler/LocalAI
- CriticalFastMCP OpenAPI Provider has an SSRF & Path Traversal Vulnerabilityfastmcp
- CriticalBentoML SSRF Vulnerability in File Upload Processingbentoml
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.