UTC
High

@grackle-ai/mcp has a workspace authorization bypass in its knowledge_search MCP tool

GHSA-647h-p824-99w7 · published 2026-03-25

Severity
High
CVSS score
8.6
Chance of exploitation (EPSS)
No CVE
Fixed in
0.70.2
What it is

The knowledgesearch and knowledgegetnode MCP tools are included in SCOPEDTOOLS (visible to scoped agents) but their handlers do not receive authContext and do not enforce workspace scoping. A scoped agent in Workspace A can supply an arbitrary workspaceId parameter to search or retrieve knowledge graph nodes from Workspace B, bypassing workspace isolation boundaries. This is a cross-workspace data leakage vulnerability affecting any deployment where multiple workspaces contain sensitive knowledge graph data and scoped agents are used.

What to do

Upgrade @grackle-ai/mcp to 0.70.2 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

Fix: Add authContext parameter to knowledgesearch and knowledgegetnode handlers and enforce workspace scoping, matching the pattern in knowledgecreate_node: When cross-workspace collaboration is designed, this check can be relaxed intentionally with proper access controls.

If you cannot upgrade yet

Do not use scoped agent tokens in multi-workspace deployments until patched. Alternatively, remove knowledgesearch and knowledgegetnode from the SCOPEDTOOLS set in tool-scoping.ts.

Affected
PackageRegistryAffectedFixed in
@grackle-ai/mcpnpm<= 0.70.10.70.2

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.

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].