io.github.gabrielmahia/mkopo-mcp
PYPI · MKOPO-MCP
Demo alternative credit scoring from M-PESA signals. Not a CRB product; synthetic, nothing stored.
Available components
Last scanned (18 hours ago)
Scores higher than 78% of PyPI servers
Category Finance and Payments
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 15 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to gabrielmahia/mkopo-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 1 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability65
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1305 tokens (~261/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 2 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 0.1.9 → 0.1.10 functional
- 31 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 30 Oct 26 −14
- Malware scan: pass → unverified ▼ security
- Stability: 0.97 → pass security
- 29 Oct 26 −1
- Stability: pass → 0.97 functional
- 25 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 24 Oct 26 0
- Package version: 0.1.8 → 0.1.9 functional
- 23 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 0.1.7 → 0.1.8 functional
- 22 Oct 26 +26
- Malware scan: unverified → pass ▲ security
- Provenance: unverified → pass ▲ security
- The attested source repository moved: gabrielmahia/mkopo-mcp security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Analysed pypi/mkopo-mcp@0.1.10
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | gabrielmahia/mkopo-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/gabrielmahia/mkopo-mcp/.github/workflows/publish.yml@refs/tags/v0.1.10 |
| Rekor log index | 3646475139 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:2b3ff4cd03924a044572ee639ad8289285f9314e82fa23ed1625ab4101da794f |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 15 packages
| Packages resolved | 15 |
|---|---|
| Stale | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
alternative_credit_score Alternative Credit Score ~328
Compute a DEMONSTRATION alternative credit score and tier (PRIME, NEAR_PRIME, SUBPRIME or THIN_FILE) from M-PESA usage signals such as months of use, regular deposits, on-time utility payments and Fuliza debt. Use when exploring how alternative data could inform credit. This is NOT a credit score and not a CRB product: a synthetic heuristic with no real data. Automated decisions about people are regulated (Data Protection Act 2019, s.35; the AI Bill 2026 is only proposed, not law). Returns the score, tier and the signals used, with a notice. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| has_fuliza_debt | boolean | yes | Currently has unpaid Fuliza (Safaricom overdraft) balance |
| has_loan_default_history | boolean | yes | Has defaulted on any previous loan (M-Shwari, KCB, bank, chama) |
| has_multiple_income_streams | boolean | yes | Receives income from more than one source (multiple employers, business + salary) |
| has_regular_income_deposits | boolean | yes | Receives regular deposits (salary, business income) at least twice monthly |
| has_savings_behaviour | boolean | yes | Makes regular small savings (M-Shwari, chama, SACCO, KCB M-PESA) |
| months_as_mpesa_user | integer | yes | How many months the person has used M-PESA (0-240) |
| pays_utilities_on_time | boolean | yes | Has paid KPLC or water bills via M-PESA in past 6 months |
Structured output declared, but exposes no named fields.
No examples provided.
credit_improvement_tips Credit Improvement Tips ~173
Practical steps to move up a credit tier, with an estimated timeline, based on the current tier, Fuliza debt, a CRB listing and months of saving. Use when someone asks how to improve their borrowing standing. An unrecognised tier gets the general timeline. Returns prioritised tips, the estimated improvement timeline and a notice. Educational guidance on DEMO assumptions: speak to a bank for personal advice. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| current_tier | string | yes | Current credit tier: PRIME, NEAR_PRIME, SUBPRIME, THIN_FILE |
| has_crb_listing | boolean | yes | Has CRB adverse listing |
| has_fuliza_debt | boolean | yes | Has unpaid Fuliza balance |
| months_saving | integer | yes | Months of consistent savings history (0-60) |
Structured output declared, but exposes no named fields.
No examples provided.
credit_report_summary Credit Report Summary ~282
Produce a DEMONSTRATION credit report summary for a made-up applicant. Use only to show the format; this is NOT a CRB product. Do not enter a real person's name or ID number: the ID is masked so only its last 4 digits appear, and nothing is stored. Returns a report header, a risk level, recommendations and a disclaimer pointing to the real credit reference bureaus (crbafrica.co.ke, metropol.co.ke). Automated assessments of people are regulated under the Data Protection Act 2019. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| employment_type | string | yes | Employment type: formal_employed, self_employed, casual_labour, farmer, gig_worker, unemployed |
| existing_loans_count | integer | yes | Number of active loans (digital, bank, chama, SACCO) |
| full_name | string | yes | Applicant name, shown in the report header only. DEMONSTRATION tool: use a placeholder, not a real person's name |
| has_crb_listing | boolean | yes | Has been listed with a Kenya Credit Reference Bureau (CRB) |
| id_number | string | yes | National ID number, only its last 4 digits appear in the output. DEMONSTRATION tool: use a placeholder, not a real ID number |
| monthly_income_kes | integer | yes | Declared monthly income in KES |
Structured output declared, but exposes no named fields.
No examples provided.
loan_eligibility Loan Eligibility ~212
Match an income, credit tier and loan purpose to illustrative lender products and check the requested amount against a 30%-of-income repayment capacity. Use when someone asks what they might qualify for. credit_tier must be PRIME, NEAR_PRIME, SUBPRIME or THIN_FILE; an unrecognised tier gets the THIN_FILE products and credit_tier_applied says so. Returns the loan request, an affordability check, the eligible products, a recommendation and a notice. NOT real offers: rates are market estimates labelled DEMO. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| credit_tier | string | yes | Credit tier from alternative_credit_score: PRIME, NEAR_PRIME, SUBPRIME, THIN_FILE |
| loan_purpose | string | yes | Loan purpose: business_working_capital, home_improvement, education, emergency, agriculture, equipment |
| monthly_income_kes | integer | yes | Monthly income in KES |
| requested_amount_kes | integer | yes | Requested loan amount in KES |
Structured output declared, but exposes no named fields.
No examples provided.
mpesa_creditworthiness Mpesa Creditworthiness ~235
Estimate a person's savings rate, Fuliza dependence and affordable 12-month loan from average M-PESA inflows and outflows, months analysed, Fuliza usage and whether they run a business paybill. Use when exploring cash-flow-based lending. A DEMO analysis using a 30% debt service ratio: real lenders run formal CRB checks and set their own policy. Returns the financial profile, the debt service capacity and affordable loan, the basis and a notice. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| avg_monthly_inflow_kes | integer | yes | Average monthly M-PESA inflows (deposits received) in KES |
| avg_monthly_outflow_kes | integer | yes | Average monthly M-PESA outflows (payments made) in KES |
| fuliza_usage_kes | integer | yes | Average monthly Fuliza (overdraft) usage in KES (0 if none) |
| has_business_paybill | boolean | yes | Receives payments to a business Paybill or Till number |
| months_analysed | integer | yes | Number of months of M-PESA history available (1-24) |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the io.github.gabrielmahia/mkopo-mcp server?
io.github.gabrielmahia/mkopo-mcp runs locally as a PyPI package, launched with uvx mkopo-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · mkopo-mcp
claude mcp add gabrielmahia-mkopo-mcp -- uvx mkopo-mcp
What is the io.github.gabrielmahia/mkopo-mcp server?
io.github.gabrielmahia/mkopo-mcp is listed in the public MCP registry as io.github.gabrielmahia/mkopo-mcp. Demo alternative credit scoring from M-PESA signals. Not a CRB product; synthetic, nothing stored. This page covers its PyPI package (mkopo-mcp).
Is the io.github.gabrielmahia/mkopo-mcp server safe to use?
io.github.gabrielmahia/mkopo-mcp scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.gabrielmahia/mkopo-mcp server expose?
io.github.gabrielmahia/mkopo-mcp exposes 5 tools: alternative_credit_score, mpesa_creditworthiness, credit_report_summary, loan_eligibility, credit_improvement_tips. Their descriptions and schemas cost roughly 1,230 tokens of context every time the server is loaded.
Is the io.github.gabrielmahia/mkopo-mcp server still maintained?
io.github.gabrielmahia/mkopo-mcp is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.gabrielmahia/mkopo-mcp server under?
io.github.gabrielmahia/mkopo-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.