mcp
Luzmo MCP Server (hosted at /0.1.0/mcp) - connect Claude, Cursor, ChatGPT, Codex, or your own agent to Luzmo, or expose a white-labeled, per-user MCP server to your own end users. Use for MCP client config, Luzmo login (OAuth) vs API key-token vs embed key-token, which tools a session gets and how to enable more (tools, permissions), saved Agent MCP URLs (agentId), product name and chart theme, MCP App chart and dashboard previews, and setting up a workspace through MCP tools (connections, datasets, metadata and AI context, formulas, dashboards, docs search). Triggers on: "Luzmo MCP", "/mcp", "MCP server", "MCP connector for our customers", answer_question, create_chart, generate_dashboard, search_docs, update_dataset_metadata, "agentId in the MCP URL", "tool missing in Claude/Cursor". Not for direct /aiprompt calls, IQ Chat/Answer components, or creating saved Agents and Rules (use ai-analytics), or tenant row isolation in the embed token (use multitenancy).
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow involves doc retrieval and searching via developer.luzmo.com, which falls under low risk as it involves actively fetched public documentation/Academy pages.
- Repository
luzmo-official/agent-skills
- Revision
7dc2a09
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.