Home / MCP registry index / io.github.duranivrobert-glitch/riv
R/IV — Verify Claims, Citations & Agent Actions
io.github.duranivrobert-glitch/riv in the official MCP registry.
Endpoint https://rdiv-production-runtime-production.up.railway.app/mcp.
The registry describes it as: Verify claims, citations & agent actions. Free receipt trial; paid prices via live R/IV quotes.
We read its 35 tools on 2026-10-26. Nothing in them matched our tool-poisoning rules.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
capabilities.list service.match pricing.quote provenance.receipt.trial example.get system.status citation.verify claim.check answer.audit contradiction.scan evidence.bundle provenance.receipt dependency.map agent.action.verify evidence.monitor investigation.run source.verify quote.verify number.verify source.snapshot timeline.reconcile fact.extract workflow.verify transaction.verify claim.monitor vendor.monitor dependency.monitor policy.monitor agent.monitor control.check data.flow.verify model.change.audit vendor.diligence procurement.evidence ai.use.audit
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-duranivrobert-glitch-riv)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.