Creed Lite

v2.0.0

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
    "creed-lite": {
      "url": "https://creedlite-6a65d6a4-gugu-gaga-amrita-university-coimbatore.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
    "creed-lite": {
      "serverUrl": "https://creedlite-6a65d6a4-gugu-gaga-amrita-university-coimbatore.app.nitrocloud.ai/mcp"
    }
  }
}

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

[mcp_servers.creed-lite]
url = "https://creedlite-6a65d6a4-gugu-gaga-amrita-university-coimbatore.app.nitrocloud.ai/mcp"

Connect directly using the Server-Sent Events endpoint: 

https://creedlite-6a65d6a4-gugu-gaga-amrita-university-coimbatore.app.nitrocloud.ai/mcp
Available Tools
evaluate_applicant

Evaluate a loan applicant against the bank underwriting model. Returns APPROVED/REJECTED with continuous probability score, component-level breakdown, and risk factors.

simulate_intervention

Simulate what happens if the applicant makes specific financial changes. Compares before/after against the bank model with full score breakdown.

get_causal_graph

Returns the structural causal model (SCM) showing how financial variables are causally connected. Use this to understand which actions affect which outcomes.

find_recourse_paths

Find causally valid and fraud-checked action paths that can flip a loan rejection to approval. Computes individualized recourse from the applicant's actual profile. Each path includes a simulated Oracle re-evaluation proving whether it achieves approval.

check_fraud_safety

Check a proposed action path against 4 named industry fraud vectors: Tradeline Renting, Loan Stacking, Debt Parking, and Unverified Income Inflation. Uses typed action schemas for reliable detection.

get_adverse_action_reasons

Map a loan denial to standardized ECOA/Reg B adverse action reason codes. These are the legally required specific reasons a lender must provide to a rejected applicant.