mkopo-mcp
mkopo-mcp is a demo MCP server for estimating alternative credit scores and loan-related insights from self-reported M-PESA-style signals, not a real credit bureau.
Estimate a 300–850 alternative credit score from M-PESA behavioural signals.
Assess M-PESA inflow/outflow patterns for creditworthiness and loan capacity.
Generate a structured loan-officer-style credit report summary.
Estimate loan eligibility across Kenya lender types.
Get personalised credit-improvement tips by tier and risk flags.
The README also advertises Kenya macro indicators via IMF/World Bank data, though that tool is not in the provided schema.
All outputs are synthetic/demo, carry automated-decision notices, and should not be used for real credit decisions or real personal data.
💳 mkopo-mcp — Alternative Credit Scoring MCP Server
Install: pip install mkopo-mcp · Use with any MCP client.
Most East Africans transacting heavily on mobile money have no formal credit file — the data exists in M-PESA history, but no scoring model reads it as an agent-callable tool.
70%+ of Kenyan adults are "credit invisible" — no formal credit history means no access to capital. M-PESA is a de facto financial history record that predicts repayment behaviour. mkopo-mcp makes that intelligence accessible to AI agents.
The Structural Problem
In mature economies, credit bureaus have 30+ years of credit card, mortgage, and auto loan data per person. That data machine took 50 years to build. In Kenya, most people's financial lives happen in cash and mobile money — invisible to formal credit systems.
M-PESA is the credit bureau that doesn't know it is one.
Regular income deposits → income stability
Utility payment regularity → discipline signal
Savings behaviour (M-Shwari, chama) → future orientation
Fuliza usage ratio → short-term distress indicator
Business Paybill receipts → verifiable commercial activity
Related MCP server: PayLink MCP Server
Tools
Tool | What it does |
| Score from M-PESA behavioural signals (300–850 scale) |
| Analyse inflow/outflow patterns for loan capacity |
| Generate structured report like a loan officer would review |
| Match to appropriate Kenya lender types |
| Personalised steps to improve credit tier |
| Kenya inflation (IMF, projections flagged) and lending and deposit rates (World Bank) |
Quick Start
pip install mkopo-mcp # coming soon to PyPI
mkopo-mcp # starts on stdioResearch Basis
World Bank "Expanding Access to Finance" (2022)
Breza & Kinnan "Measuring the Equilibrium Impacts of Credit" (2021)
CBK Prudential Guidelines (2022)
Kenya CRB Act (Cap. 44A)
⚠️ DEMO data — not a real CRB product. Consult Metropol or CRB Africa for official reports.
© 2026 Gabriel Mahia / AI Kung Fu LLC · MIT License
Live data
kenya_macro_indicators: Kenya's annual inflation (IMF, projections flagged) and lending and deposit rates (World Bank, CC BY 4.0).
Each live answer names its source, attribution and retrieval time; if a service does not answer, the tool returns an error instead of a number. The other tools are unchanged.
Part of the East Africa Coordination Stack
This MCP server is part of the Kenya coordination infrastructure.
Connect it to africa-coord-bus —
the coordination event bus that routes signals between domains automatically.
pip install africa-coord-busAll servers: pypi.org/user/gmahia Live demo: coord-cascade-demo
IP & Collaboration
MIT licensed. Feedback via GitHub Issues only — pull requests are not accepted. Demo data is labeled DEMO and is not suitable for operational decisions. Full policy: docs/architecture/IP_POLICY.md. Security reports: see SECURITY.md.
Part of the East Africa coordination stack
Install & run:
pip install reli-cli && reli list— the MCP servers on the official MCP Registry underio.github.gabrielmahiaEvaluate any model on Swahili agent tasks: kipimo · dataset · leaderboard
Coordinate across servers: africa-coord-bus — offline-first event bus with a built-in Kenya routing table
Datasets: huggingface.co/gmahia · Docs hub: nairobi-stack
Model-agnostic by design: closed APIs, open-weight models, and small distilled models are all first-class citizens.
Demonstration only, and Kenya's rules on automated decisions
These tools produce synthetic demonstration results, not credit decisions, and they are not a Credit Reference Bureau product. Do not pass a real person's name or ID number to them.
If you build something real on a score like this, note the law: in Kenya the Data Protection Act 2019 is in force, including its provisions on decisions made solely by automated processing (section 35). The Artificial Intelligence Bill 2026 is a Senate bill and is not law: a Senate committee recommended abandoning it in October 2026, so as of 2026-10-23 Kenya has no dedicated AI law and the Data Protection Act is what applies. The bill would have added a right to an explanation and to human review of significant automated decisions such as a loan rejection, and commentators expected credit scoring to be treated as high-risk under such a law. Every scoring answer from this server carries an automated_decision_notice saying so. The lender examples are generic lender types, not named companies: an earlier version listed real lenders by tier, which this synthetic score cannot support.
Available Tools
5 toolsalternative_credit_scoreARead-only
Estimate an alternative credit score from M-PESA behavioural signals. Western parallel: FICO score / Nova Credit for immigrants with no US history. Inputs are self-reported for demo purposes — a real implementation would connect to licensed M-PESA data-sharing APIs with customer consent. DEMO — not a real credit bureau product.
Inputs: has_fuliza_debt (required), months_as_mpesa_user (required), has_savings_behaviour (required), pays_utilities_on_time (re… Returns: object
credit_improvement_tipsARead-only
Generate actionable credit improvement tips personalised to the user's situation. Western parallel: Credit Karma improvement recommendations. DEMO educational content.
Inputs: current_tier (required), months_saving (required), has_crb_listing (required), has_fuliza_debt (required). Returns: object
credit_report_summaryARead-only
Generate a structured credit report summary — the document a loan officer would review. Western parallel: Experian or Equifax credit report. DEMO — not a real CRB product.
Inputs: full_name (required), id_number (required), employment_type (required), has_crb_listing (required), +2 more. Returns: object
loan_eligibilityARead-only
Estimate loan eligibility across Kenya lender types. Western parallel: LendingTree loan comparison, Bankrate. DEMO — not actual loan offers.
Inputs: credit_tier (required), loan_purpose (required), monthly_income_kes (required), requested_amount_kes (required). Returns: object
mpesa_creditworthinessARead-only
Analyse M-PESA transaction patterns to assess creditworthiness. Takes simplified transaction summary inputs (no raw transaction data). Western parallel: Plaid income verification, Finicity, Experian Boost. DEMO — requires informed customer consent in production.
Inputs: months_analysed (required), fuliza_usage_kes (required), has_business_paybill (required), avg_monthly_inflow_kes (require… Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Tools are mostly distinct: alternative_credit_score and mpesa_creditworthiness both use M-PESA data but one yields a score and the other analyzes patterns; credit_report_summary overlaps slightly but is a different product. Overall, an agent can differentiate them with clear descriptions.
All tool names follow a consistent snake_case pattern using descriptive noun phrases (e.g., loan_eligibility, credit_report_summary). No mixing of conventions or verb styles.
5 tools is an ideal scope for a credit assessment server, covering score estimation, improvement tips, report summary, eligibility check, and transaction pattern analysis without unnecessary bulk.
For a demo product, the tool set covers the full lifecycle of credit assessment: analysis, scoring, reporting, eligibility, and improvement. There are no obvious gaps for the stated purpose.
Maintenance
Related MCP Connectors
828 MCP tools across 1276 fintech tools: ChainGraph AP2 decisions, execution_hash. Zero PII.
African intelligence infrastructure for AI apps, developers, and data products via MCP.
MCP server for VC pitch-deck scoring, thesis-fit matching, and deal-flow management.
113 MCP tools: oracle, escrow, compliance, remittance, AI. 12 free tools, PAYG $0.001/call.
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server for East African fintech APIs — trigger M-Pesa STK Push payments, check transaction status, send SMS to 20+ African networks, and top up airtime via Africa's Talking.5213 PyPI6MIT

PayLink MCP Serverofficial
FlicenseNot gradedqualityDmaintenanceOpen-source MCP server that streamlines payment integration for AI agents and financial apps in Africa, providing unified tools for providers like M-Pesa.1-- AlicenseAqualityBmaintenanceMCP server for Kenya insurance intelligence, providing tools to query insurance products, NHIF coverage, and parametric crop risk scoring.6140 PyPIMIT
- AlicenseAqualityBmaintenanceMCP server for portable reputation and skills passports in East Africa — worker profiles, verified service records, trust scores, and professional references for economic mobility. 6 tools.671 PyPIMIT