UTC

n8n-mcp

11 published advisories; version 2.57.4 or later fixes all of them.

Registry
npm
Advisories
11
Latest fix
2.57.4
Exploited in the wild
None listed

Check your machine

Finds n8n-mcp in your agent and MCP configs, installed skills, global npm packages, the npx and uvx caches, uv and pipx tools, Claude Code and Cursor. It runs offline and sends nothing anywhere.

pip install "shieldpi>=0.10.0"
shieldpi agent-config . --installed
Provenance

Source: github.com/czlonkowski/n8n-mcp, named in a signed build attestation

10 of the last 10 releases of n8n-mcp were published with build provenance: a signed record of the repository and commit each was built from, which the registry checks before it accepts the release.

  • 2.103.0
  • 2.102.0
  • 2.101.4
  • 2.101.3
  • 2.101.2
  • 2.101.1
  • 2.101.0
  • 2.100.0
  • 2.99.2
  • 2.99.1

Green: published with provenance. Grey: without.

OpenSSF Scorecard: 7.5 of 10 on 2026-11-18.

No dangerous CI workflows
10/10
CI tokens read-only by default
10/10
Build dependencies pinned
8/10
Branch protection
4/10
Changes reviewed before merge
0/10
Signed releases
6/10
Actively maintained
10/10
Security policy
10/10
Full Scorecard →

Provenance from deps.dev (CC BY 4.0); Scorecard from OpenSSF (CDLA-Permissive-2.0). As of 2026-11-18.

In the Docker MCP Catalog

From the Docker MCP Catalog (MIT), as of 2026-11-18. The version is read from the package manifest at the commit the catalog pins.

Advisories
AdvisorySeverityAffectedFixed inPublished
n8n-MCP: Incorrect authorization can expose default-scope workflow version backups in multi-tenant HTTP modeCVE-2026-55608Medium<= 2.57.32.57.42026-07-14
n8n-MCP: Cross-tenant access to workflow version backups in multi-tenant HTTP deploymentsCVE-2026-54052Critical<= 2.56.02.56.12026-07-14
n8n-MCP: Workflow telemetry sanitizer could retain partial values from URL-shaped node parametersCVE-2026-45582Medium< 2.51.32.51.32026-05-18
n8n-MCP: Multi-tenant MCP requests fall back to process-level n8n credentials when tenant headers are absent or incompleteCVE-2026-45707High<= 2.51.12.51.22026-05-18
n8n-mcp affected by path traversal, redirect-following SSRF, and telemetry payload exposureGHSA-8g7g-hmwm-6rv2High< 2.50.12.50.12026-05-08
n8n-mcp webhook and API client paths has an authenticated SSRFCVE-2026-44694High>= 2.18.7, < 2.50.22.50.22026-05-08
n8n-mcp's IPv4-mapped IPv6 addresses bypass SSRF protection in validateUrlSync(), enabling full SSRF for SDK embeddersCVE-2026-42449High>= 2.47.4, < 2.47.142.47.142026-04-30
n8n-MCP: Sensitive MCP tool-call arguments logged on authenticated requests in HTTP modeCVE-2026-42282Medium< 2.47.132.47.132026-04-25
n8n-MCP Logs Sensitive Request Data on Unauthorized /mcp RequestsCVE-2026-41495Medium< 2.47.112.47.112026-04-23
n8n-mcp has unauthenticated session termination and information disclosure in HTTP transportGHSA-75hx-xj24-mqrwHigh<= 2.47.52.47.62026-04-10
n8n-mcp has authenticated SSRF via instance-URL header in multi-tenant HTTP modeCVE-2026-39974High<= 2.47.32.47.42026-04-08

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].