A powerful MCP server built with NitroStack
Add via Cursor Settings UI (Settings > Features > MCP > Add New MCP Server):
{
"mcpServers": {
// your other mcp servers
"nexusiq-mcp": {
"url": "https://nexusiq-6a5b4334-akkanda-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp"
}
}
}
Connect remote tools directly via Claude's Web UI:
Configure custom tools directly via ChatGPT's Web UI:
Add the following configuration block under mcpServers in your Antigravity configuration file (~/.gemini/config/mcp_config.json):
{
"mcpServers": {
// your other mcp servers
"nexusiq-mcp": {
"serverUrl": "https://nexusiq-6a5b4334-akkanda-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp"
}
}
}
Add the following configuration block to your Codex configuration file (~/.codex/config.toml):
[mcp_servers.nexusiq-mcp] url = "https://nexusiq-6a5b4334-akkanda-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp"
Connect directly using the Server-Sent Events endpoint:
https://nexusiq-6a5b4334-akkanda-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp
Analyzes a procurement contract for commercial risks, extracts supporting evidence, flags evidence gaps, and returns a deterministic APPROVE/REVIEW/REJECT recommendation with confidence.
Looks up a vendor in the knowledge base by ID (preferred) or name, and returns compliance, financial stability, and risk data. Unknown vendors return riskRating "UNKNOWN" rather than an error.
Estimates the financial impact of a procurement deal, factoring in vendor risk premium and negotiation leverage. estimatedSavings can be negative - that is a valid outcome, not an error.
Turns identified procurement risks into structured negotiation talking points, each tied to a specific risk and clause reference. Use only when negotiation opportunities exist (recommendation was REVIEW or risks were found).
Deterministic final decision step. Takes the outputs of analyze_contract, vendor_intelligence, and cost_simulator and combines them into one finalRecommendation with confidence = minimum across all three signals. This is rule-based, not another model call - same inputs always produce the same decision.