Agent Analytics
io.github.dannyshmueli/agent-analytics-mcp · v1.0.0 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Analytics your AI agent can actually use. Track, experiment, and optimize via MCP.
Source: https://github.com/Agent-Analytics/agent-analytics-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 32 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (delete_experiment). Require confirmation before the agent calls them. |
What was checked
- https://mcp.agentanalytics.sh/mcp: answers without auth
Public tools: account_usage, analytics_panel, list_projects, create_project, get_project_context, set_project_context, append_project_annotation, properties, properties_received, sessions, list_experiments, create_experiment, get_experiment, update_experiment, delete_experiment, live_now, all_sites_overview, bot_traffic_overview, all_sites_bot_traffic, query, compare, errors, web_vitals, analytics_funnel, analytics_retention, analytics_overview, analytics_insights, analytics_breakdown, analytics_pages, analytics_paths
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-dannyshmueli-agent-analytics-mcp-19e8fb4e)