UTC

@grackle-ai/mcp

2 published advisories; version 0.70.2 or later fixes all but 1 of them.

Registry
npm
Advisories
2
Latest fix
0.70.2
Exploited in the wild
None listed

Check your machine

Finds @grackle-ai/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/nick-pape/grackle, named in the package metadata (not verified)

0 of the last 10 releases of @grackle-ai/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.

  • 0.195.0
  • 0.194.0
  • 0.193.0
  • 0.192.0
  • 0.191.0
  • 0.190.0
  • 0.189.0
  • 0.188.0
  • 0.187.0
  • 0.186.0

Green: published with provenance. Grey: without.

OpenSSF Scorecard has not scored this repository.

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

Advisories
AdvisorySeverityAffectedFixed inPublished
Grackle: Fail-open authorization in the MCP tool layer lets scoped agents perform cross-task and cross-session mutations (IDOR)GHSA-f9ff-5x35-7gfwHigh<= 0.132.1No fix yet2026-07-02
@grackle-ai/mcp has a workspace authorization bypass in its knowledge_search MCP toolGHSA-647h-p824-99w7High<= 0.70.10.70.22026-03-25

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].