Verifai

v1.0.0

A powerful MCP server built with NitroStack

Connection Setup

Add via Cursor Settings UI (Settings > Features > MCP > Add New MCP Server): 

{
  "mcpServers": {
    // your other mcp servers
    "verifai": {
      "url": "https://verifai-6a5aa2ee-zenith-amrita-university-amritapuri-campus-1.app.nitrocloud.ai/mcp"
    }
  }
}

Connect remote tools directly via Claude's Web UI:

Add custom connector BETA
Connect Claude to your data and tools. Learn more about connectors or get started with pre-built ones.
Advanced settings
Only use connectors from developers you trust. Anthropic does not control which tools developers make available and cannot verify that they will work as intended or that they won't change.
Building an MCP server? Report issues and subscribe to updates here

Configure custom tools directly via ChatGPT's Web UI:

New App
Icon (optional)
PNG only. Best results at 256 x 256 px or larger. Max file size: 10 KB
Name
Description (optional)
Connection
Authentication
Custom MCP servers introduce risk. Learn more
OpenAI hasn't reviewed this MCP server. Attackers may attempt to steal your data or trick the model into taking unintended actions, including destroying data.
Read the guide

Add the following configuration block under mcpServers in your Antigravity configuration file (~/.gemini/config/mcp_config.json): 

{
  "mcpServers": {
    // your other mcp servers
    "verifai": {
      "serverUrl": "https://verifai-6a5aa2ee-zenith-amrita-university-amritapuri-campus-1.app.nitrocloud.ai/mcp"
    }
  }
}

Add the following configuration block to your Codex configuration file (~/.codex/config.toml): 

[mcp_servers.verifai]
url = "https://verifai-6a5aa2ee-zenith-amrita-university-amritapuri-campus-1.app.nitrocloud.ai/mcp"

Connect directly using the Server-Sent Events endpoint: 

https://verifai-6a5aa2ee-zenith-amrita-university-amritapuri-campus-1.app.nitrocloud.ai/mcp
Available Tools
audit_response

MANDATORY RULE: You MUST call this tool immediately when asked to check, audit, verify, or review any statement or text. Do NOT answer conversationally, do NOT list available resources, and do NOT ask for clarification before calling this tool. You MUST call this tool even if the input statement is completely empty, blank, missing, or null (for example: "Audit this:", "Audit this: """, "Audit this: ''", or just "Audit"). In these empty statement cases, you MUST call this tool with agentOutput set to "" (empty string) and sources set to [] (empty array). If the request is vague or lacks source documents (e.g. "The agent said something about our policy."), pass the vague statement (e.g. "something about our policy") as agentOutput and sources as [].

explain_audit

Get detailed factual mismatches and citations for a previously completed audit by its ID. CRITICAL: ALWAYS call this tool IMMEDIATELY when the user asks to explain, detail, review mismatches, or follow up on an audit result. Pass the auditId returned by audit_response directly to this tool. If the audit ID is not found in the current session, the tool returns a helpful error message.

get_audit_log

Retrieve audit history records filtered by a date range. CRITICAL: ALWAYS call this tool IMMEDIATELY when the user requests audit history, logs, records, or mentions "last month", "past week", "yesterday", or any date range. Pass the user-supplied dates directly to this tool even if they appear invalid — the tool performs ALL date validation internally and returns appropriate error messages for: - Invalid format (non-ISO) - Impossible values (month > 12, day > 31) - Illogical ranges (end date before start date) NEVER pre-validate dates or answer conversationally. Always pass dates directly to this tool.

get_trust_summary

Retrieve aggregate trust metrics and statistics across all historical audits, including pass rate, average score, min/max scores, and daily trend data. ALWAYS call this tool when the user asks about trust statistics, dashboards, or audit summaries.