fed-aura-risk-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@fed-aura-risk-mcp What's the loan recommendation for a borrower with 720 credit score and 42% DTI?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Risk Assessment MCP Server
A mortgage risk underwriting server built on FastMCP 3.x that exposes individual risk calculation tools and an aggregation tool for producing loan recommendations. Built from the FastMCP server template.
Tools
Tool | Description |
| Debt-to-Income ratio from monthly income and debts |
| Loan-to-Value ratio from loan amount and property value |
| Credit risk rating from borrower credit score |
| Income stability from employment statuses of all borrowers |
| Asset reserve adequacy relative to loan amount |
| Aggregator: combines all risk factors into Approve / Approve with Conditions / Suspend / Deny |
calculate_dti
Computes the Debt-to-Income ratio as a percentage. Rates Low below 36%, Medium at 36--43%, High above 43%.
Parameters: monthly_income (float), monthly_debts (float)
Returns: JSON with metric, value, rating, guidance.
{"monthly_income": 8000, "monthly_debts": 2400}calculate_ltv
Computes the Loan-to-Value ratio as a percentage. Rates Low below 60%, Medium at 60--80%, High above 80%. Includes pmi_required flag.
Parameters: loan_amount (float), property_value (float)
Returns: JSON with metric, value, rating, guidance, pmi_required.
{"loan_amount": 320000, "property_value": 400000}evaluate_credit_risk
Evaluates credit risk from a FICO-range score (300--850). Rates Low above 680, Medium at 620--680, High below 620.
Parameters: credit_score (int), source (str, default "self_reported")
Returns: JSON with metric, value, rating, guidance, source.
{"credit_score": 720, "source": "experian"}assess_income_stability
Takes a list of employment statuses for all borrowers and returns the worst-case rating. Valid statuses: w2_employee, self_employed, retired, unemployed, other.
Parameters: employment_statuses (list of strings)
Returns: JSON with metric, statuses, rating, guidance, individual_ratings.
{"employment_statuses": ["w2_employee", "self_employed"]}assess_asset_sufficiency
Checks asset reserves as a percentage of the loan amount. Rates Low above 20%, Medium at 10--20%, High below 10%.
Parameters: total_assets (float), loan_amount (float)
Returns: JSON with metric, value, rating, guidance.
{"total_assets": 90000, "loan_amount": 350000}generate_risk_recommendation
Aggregates all five risk assessments plus document status and optional ML predictions into a final underwriting decision. The decision logic applies deny triggers (DTI > 55%, credit < 580, LTV > 97%, all borrowers unemployed), suspend triggers (missing documents), and conditional triggers (PMI, elevated DTI, self-employment documentation). Compensating factors such as strong credit offsetting high DTI are also considered.
Parameters: dti_value, dti_rating, ltv_value, ltv_rating, credit_score, credit_rating, income_rating, asset_rating, employment_statuses, has_financial_docs, has_credit_report, document_count, ml_prediction (optional), ml_confidence (optional)
Returns: JSON with recommendation, rationale, conditions, compensating_factors, overall_risk, warnings, risk_summary.
{
"dti_value": 38.5, "dti_rating": "Medium",
"ltv_value": 75.0, "ltv_rating": "Medium",
"credit_score": 720, "credit_rating": "Low",
"income_rating": "Low", "asset_rating": "Low",
"employment_statuses": ["w2_employee"],
"has_financial_docs": true,
"has_credit_report": true,
"document_count": 5
}Related MCP server: MCP Mortgage Server
Quick Start
Local Development
make install
make run-local
# In another terminal, test with cmcp
cmcp ".venv/bin/python -m src.main" tools/list
cmcp ".venv/bin/python -m src.main" tools/call calculate_dti '{"monthly_income": 8000, "monthly_debts": 2400}'Deploy to OpenShift
make deploy PROJECT=mcp-risk-serverThe server is deployed at:
https://mcp-server-mcp-risk-server.apps.cluster-z9hbt.z9hbt.sandbox1495.opentlc.com/mcp/
Testing
# Run all 53 tests
make test
# Run a single test file
.venv/bin/pytest tests/test_risk_calculations.py -v
# Test against local STDIO server with cmcp
make test-localArchitecture
The server uses FastMCP 3.x with FileSystemProvider for automatic tool discovery. Tools use standalone @tool decorators (no shared server instance). The server runs in STDIO mode locally and uses streamable-http transport on port 8080 when deployed to OpenShift.
Tool source lives in two files under src/tools/: risk_calculations.py (five calculation tools) and risk_recommendation.py (the aggregation tool). The recommendation logic is factored into a pure compute_recommendation() function for direct use in tests.
Environment Variables
Variable | Default | Purpose |
|
| Transport mode: |
|
| HTTP bind address |
|
| HTTP port |
|
| HTTP endpoint path |
|
| Logging level |
|
| Enable hot-reload for development |
|
| Server name in MCP responses |
| (none) | JWT algorithm (e.g., RS256). Auth disabled if unset |
| (none) | Shared secret for HMAC algorithms |
| (none) | Public key for RSA/EC algorithms |
| (none) | JWKS endpoint URL |
| (none) | Expected token issuer |
| (none) | Expected token audience |
| (none) | Comma-separated default required scopes |
License
This project is licensed under the MIT License. See the LICENSE file for details.
Available Tools
6 toolsassess_asset_sufficiencyAssess Asset SufficiencyARead-onlyIdempotent
Assess whether the borrower has sufficient asset reserves relative to the loan amount.
Inputs: loan_amount (required), total_assets (required). Returns: result
assess_income_stabilityAssess Income StabilityARead-onlyIdempotent
Assess income stability risk based on borrower employment statuses.
Inputs: employment_statuses (required). Returns: result
calculate_dtiCalculate DtiARead-onlyIdempotent
Calculate the Debt-to-Income (DTI) ratio for mortgage risk assessment.
Inputs: monthly_debts (required), monthly_income (required). Returns: result
calculate_ltvCalculate LtvBRead-onlyIdempotent
Calculate the Loan-to-Value (LTV) ratio for mortgage risk assessment.
Inputs: loan_amount (required), property_value (required). Returns: result
evaluate_credit_riskEvaluate Credit RiskBRead-onlyIdempotent
Evaluate credit risk based on the borrower's credit score.
Inputs: credit_score (required), source. Returns: result
generate_risk_recommendationGenerate Risk RecommendationARead-onlyIdempotent
Generate a comprehensive risk recommendation based on all assessment factors.
This aggregator tool combines individual risk assessments (DTI, LTV, credit, income stability, asset sufficiency) to produce a final recommendation: Approve, Approve with Conditions, Suspend, or Deny.
Inputs: dti_value (required), ltv_value (required), dti_rating (required), ltv_rating (required), +10 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a distinct risk factor or calculation: DTI, LTV, credit, income stability, asset sufficiency, and final recommendation. There is no meaningful overlap between tool purposes.
All tool names follow a consistent verb_noun snake_case pattern: calculate_, assess_, evaluate_, generate_. This makes the set predictable and easy to navigate.
Six tools is well-scoped for a mortgage risk assessment server, covering individual risk factors and an aggregator without unnecessary redundancy.
The tool set covers the full stated workflow: calculating key ratios, assessing borrower risks, evaluating credit, and producing a final recommendation. There are no obvious dead ends or missing critical operations.
Maintenance
Related MCP Connectors
Lender-grade real estate underwriting and deal reports: fix and flip, BRRRR, new construction.
Deterministic Canadian mortgage calculations for qualification, debt service, LTV, and penalties.
Powered by UQUAL loan readiness tools, educational calculations and agency references.
Prospect, grade and analyze off- or on-market real estate deals with deterministic, auditable math.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables creditworthiness analysis for non-traditional borrowers using rule-based scoring, financial behavior assessment, and underwriting report generation via MCP tools.1-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to parse and analyze mortgage documents (Loan Estimates & Closing Disclosures), converting them into structured MISMO-compliant JSON and checking for TRID compliance violations.2MIT
- FlicenseNot gradedqualityCmaintenanceEnables a Digital Banking Assistant to calculate debt-to-income ratios, generate amortization schedules, and flag explainable, rules-based risk factors during conversations.-
- AlicenseAqualityCmaintenanceEnables agents to analyze contract excerpts and receive calibrated risk annotations across 10 default risk classes, including presence probabilities, overall risk levels, and human review recommendations.1MIT