Talivia AgentSAFE
Revenue-first website analytics installed and verified by AI agents through MCP
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Revenue-first website analytics that your AI agent can install, connect, and verify for you.
Talivia shows founders which referrers, campaigns, pages, search keywords, and customer journeys turn visits into revenue. @talivia/agent connects Codex, Claude Code, ChatGPT, OpenClaw, Hermes, and other MCP clients to Talivia so an agent can finish the analytics setup inside your project - not just paste a tracking snippet and hope it works.
Ask your agent to set up Talivia. It can find or create the right website, generate a framework-specific installation plan, add the tracker with its native coding tools, verify that real events are arriving, open a secure payment-provider handoff, and check that revenue attribution is ready.
Start free | Agent Kit | Documentation | npm | GitHub
See which traffic becomes revenue
Most analytics products count visits. Payment dashboards count transactions. Talivia connects the two, so you can answer the questions that matter to a growing product:
- Which referrers, campaigns, and search keywords bring paying customers?
- Which landing pages and customer journeys lead to a purchase?
- How do visitors, conversion rate, revenue per visitor, and revenue change together?
- Which tracked session produced an individual payment?
- Is analytics and checkout attribution actually working in production?
Talivia puts traffic, visitor journeys, events, payment revenue, and attribution in one workspace. Connect a supported payment provider or use the Manual Payment API for a custom checkout.
From one prompt to verified analytics
Give this to a coding ag
fd4769a9c2f1OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add agent --env TALIVIA_API_KEY=${TALIVIA_API_KEY} -- npx -y @talivia/[email protected] mcpTrust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
.codexignore
`${JSON.stringify({ apiKey: 'invalid', endpoint: 'http://127.0.0.1:1/mcp' })}\n`,Gates applied: no_behavioural_pass.
fd4769a9c2f1full audit observations/trust-audit/mcp-server/talivia-group__talivia-agent.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | fd4769a9c2f1 | SAFE | B | 89 | first audit |
Questions
What is the Talivia Agent MCP server?
Revenue-first website analytics installed and verified by AI agents through MCP
Is Talivia Agent safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Talivia Agent need?
It reads TALIVIA_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Talivia Agent run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @talivia/agent at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (fd4769a9c2f1), read on 2026-10-07. The repository is watched and re-audited when it changes.