github.com/modelcontextprotocol/registry
5 published advisories; version 1.7.9 or later fixes all of them.
- Registry
- Go
- Advisories
- 5
- Latest fix
- 1.7.9
- Exploited in the wild
- None listed
Check your projects
shieldpi agent-config checks agent and MCP packages from npm and PyPI, not github.com/modelcontextprotocol/registry. Any scanner that reads the OSV database finds it in your lockfiles, for example Google's open-source OSV-Scanner.
osv-scanner scan source -r .Or check a lockfile against ShieldMap in your browser.
Source: github.com/modelcontextprotocol/registry, named in the package metadata (not verified)
OpenSSF Scorecard has not scored this repository.
Provenance from deps.dev (CC BY 4.0); Scorecard from OpenSSF (CDLA-Permissive-2.0). As of 2026-11-22.
| Advisory | Severity | Affected | Fixed in | Published |
|---|---|---|---|---|
| MCP Registry: OCI validator skips ownership check on upstream rate limitsCVE-2026-45781 | Low | < 1.7.9 | 1.7.9 | 2026-05-19 |
| MCP Registry's GitHub OIDC tokens are replayable across registry deployments due to shared audienceCVE-2026-44428 | Low | < 1.7.6 | 1.7.6 | 2026-05-08 |
| MCP Registry has an unauthenticated SSRF: HTTP namespace verification dials 6to4 / NAT64 / site-local IPv6 addresses, bypassing private-addrCVE-2026-44430 | Medium | < 1.7.7 | 1.7.7 | 2026-05-08 |
| MCP Registry vulnerable to stored XSS in catalogue UI via attribute-quote breakout in publisher-controlled `websiteUrl`CVE-2026-44429 | Medium | < 1.7.7 | 1.7.7 | 2026-05-08 |
| MCP Registry has open redirect via protocol-relative path in trailing-slash middlewareCVE-2026-44427 | Medium | >= 1.1.0, < 1.7.5 | 1.7.5 | 2026-05-08 |
Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].