Money Sums
REMOTE · KWEKUANANSI.AI
True yearly cost of flat-rate and app loans, margin and markup, break-even, and susu fees.
Available components
Last scanned (23 hours ago)
Scores higher than 67% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Finance and Payments
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security83
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability63
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1395 tokens (~279/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 Management33
- Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
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.
- 20 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Nov 26 +49
- Authorization: unverified → partial ▲ security
- Injection markers: unverified → pass ▲ security
- Transport: fail → pass ▲ security
- Endpoint reachability: not serving MCP → reachable ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- Stability: unverified → 0.20 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- 16 Nov 26 −48
- Endpoint reachability: reachable → not serving MCP ▼ security
- Stability: 0.13 → unverified ▼ security
- Authorization: partial → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Transport: pass → fail ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- 14 Nov 26 +2
- DNSSEC: fail → pass ▲ security
- 12 Nov 26 +1
- Stability: unverified → 0.03 ▲ functional
- 11 Nov 26 71
First indexed and scored.
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 21 Nov 2026 · Probed https://kwekuanansi.ai/mcp/money-sums
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=kwekuanansi.ai | CN=YR1,O=Let's Encrypt,C=US | 17 Oct 2026 | 15 Jan 2027 | RSA 2048 | SHA256-RSA | 5a9703a2d747be131c28ec7c7c14426de31 |
| SANs: kwekuanansi.ai | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of kwekuanansi.ai. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | DS published | 1814 | 8 | Verified |
| kwekuanansi.ai. | DS published | 2371 | 13 | Verified |
| kwekuanansi.ai. | Verified address RRset verified with the apex keys |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000; includeSubDomains; preload |
| content-security-policy | default-src 'self'; base-uri 'self'; object-src 'none'; frame-ancestors 'none'; form-action 'self'; img-src 'self' data: https://fal.media https://*.fal.media; media-src 'self' data: blob:; font-src 'self' data:; style-src 'self'; script-src 'self'; connect-src 'self' https://anansi.cashplanet.io https://fal.media https://*.fal.media; upgrade-insecure-requests |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(self), geolocation=(), payment=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://kwekuanansi.ai/mcp/money-sums | Verified | 200 | |
| http (plaintext) | http://kwekuanansi.ai/mcp/money-sums | HTTPS enforced | 308 | https://kwekuanansi.ai/mcp/money-sums |
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 →
business.break_even Sales needed to cover fixed costs ~201
Use this when someone running a business gives their fixed costs for a period (rent, wages, power for a month), what one item costs them and what they sell it for, and asks how many they must sell to cover their costs (break even). Do not use it for a business plan's forecasts or to judge whether a business will succeed.
| Name | Type | Req | Description |
|---|---|---|---|
| cost_per_item | number | yes | What one item costs to buy or make. |
| currency | string | – | The currency, as its three-letter code (GHS, NGN, KES, ZAR...). Only labels the answer; leave out if unknown. |
| fixed_costs | number | yes | Costs that do not change with how much is sold, for the period (for example a month's rent, wages and power). |
| period | string | – | The period the fixed costs are for. Leave out for a month. |
| sale_per_item | number | yes | What one item is sold for. |
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | – |
| explore_url | string | – | – |
| fixed_costs | number | yes | – |
| items_to_break_even | integer | yes | – |
| left_per_item | number | yes | – |
| left_per_item_percent | number | – | – |
| note | string | yes | – |
| period | string | – | – |
| sales_to_break_even | number | yes | – |
No examples provided.
business.margin Profit margin and markup on a sale ~246
Use this when a trader gives what an item costs them and either what they sell it for, the margin they want, or the markup they want, and asks for the profit, the margin, the markup or what to sell it for (for example "I buy a bag of rice for 800 and want a 20% margin"). It keeps margin (a share of the sale) and markup (a share of the cost) apart, which are often confused. Do not use it for tax on a sale (use a VAT tool), for exchange rates, or to suggest what the market will pay.
| Name | Type | Req | Description |
|---|---|---|---|
| cost | number | yes | What one item costs the seller to buy or make. |
| currency | string | – | The currency, as its three-letter code (GHS, NGN, KES, ZAR...). Only labels the answer; leave out if unknown. |
| margin_percent | number | – | The profit wanted as a per cent of the sale amount. |
| markup_percent | number | – | The profit wanted as a per cent of the cost. |
| sale_amount | number | – | What one item is sold for. Give this, or margin_percent, or markup_percent. |
| Name | Type | Req | Description |
|---|---|---|---|
| cost | number | yes | – |
| currency | string | – | – |
| explore_url | string | – | – |
| margin_percent | number | yes | – |
| markup_percent | number|null | yes | – |
| note | string | yes | – |
| profit | number | yes | – |
| sale_amount | number | yes | – |
No examples provided.
loan.instalments Repayments and yearly cost of a loan ~389
Use this when someone gives a loan amount, an interest rate and a number of weekly, fortnightly or monthly repayments, and asks what each repayment is, what the loan costs in total, or what the rate really is a year, for example "a microfinance loan of 5,000 at 5% flat a month for 6 months". It handles a flat rate (interest on the whole amount for the whole term, common with microfinance and hire purchase) and a reducing-balance rate, and fees taken at the start. Do not use it for a loan repaid in one sum (use loan.one_repayment), for a mortgage with a changing rate, or to say whether a loan is a good idea.
| Name | Type | Req | Description |
|---|---|---|---|
| amount | number | yes | The amount borrowed. |
| currency | string | – | The currency, as its three-letter code (GHS, NGN, KES, ZAR...). Only labels the answer; leave out if unknown. |
| method | string | – | "flat" when interest is charged on the whole amount for the whole term; "reducing" when it is charged only on what is still owed. Leave out if unknown, and both are worked out. |
| rate_per | string | yes | Whether the quoted rate is a month or a year. |
| rate_percent | number | yes | The interest rate as quoted, in per cent, for example 5 for 5%. |
| repay_every | string | – | How often a repayment is made. Leave out for every month. |
| repayments | integer | yes | How many repayments there are. |
| upfront_fee_percent | number | – | Fees taken when the loan is paid out, as a per cent of the amount. Leave out if none. |
| upfront_fees | number | – | Fees taken when the loan is paid out (processing, insurance, commitment), as an amount. Leave out if none. |
| Name | Type | Req | Description |
|---|---|---|---|
| amount_borrowed | number | yes | – |
| amount_received | number | – | – |
| currency | string | – | – |
| explore_url | string | – | – |
| how_counted | array | yes | – |
| method_known | boolean | yes | – |
| note | string | yes | – |
| quoted_rate_per | string | – | – |
| quoted_rate_percent | number | – | – |
| repay_every | string | yes | – |
| repayments | integer | yes | – |
| results | array | yes | – |
| term_months | number | – | – |
| upfront_fees | number | – | – |
No examples provided.
loan.one_repayment Yearly cost of a short loan repaid at once ~225
Use this when someone borrows an amount and repays a single larger sum after some days, as with a phone or app loan, a salary advance or a loan from a moneylender, and asks what rate that is a month or a year (for example "I borrowed 1,000 and must repay 1,150 in 30 days"). Do not use it for a loan repaid in instalments (use loan.instalments), and do not use it to judge a lender.
| Name | Type | Req | Description |
|---|---|---|---|
| amount | number | yes | The amount borrowed. |
| currency | string | – | The currency, as its three-letter code (GHS, NGN, KES, ZAR...). Only labels the answer; leave out if unknown. |
| days | integer | yes | How many days until it must be repaid. |
| repay | number | yes | The whole amount to be paid back, including interest and any fees added to it. |
| upfront_fees | number | – | Fees taken from the loan when it is paid out, as an amount. Leave out if none. |
| Name | Type | Req | Description |
|---|---|---|---|
| amount_borrowed | number | yes | – |
| amount_received | number | – | – |
| cost | number | yes | – |
| cost_percent_of_amount | number | – | – |
| currency | string | – | – |
| days | integer | yes | – |
| explore_url | string | – | – |
| how_counted | array | yes | – |
| monthly_rate_percent | number|null | – | – |
| note | string | yes | – |
| repay | number | yes | – |
| yearly_rate_compounded_percent | number|null | yes | – |
| yearly_rate_simple_percent | number|null | yes | – |
No examples provided.
savings.collector_fee What a susu or ajo collector's fee costs ~240
Use this when someone saves with a collector who takes regular deposits and keeps some of them as a fee (susu in Ghana, ajo or esusu in Nigeria, a daily contribution card), and asks how much they get back, what the fee is, or what it costs as a rate. A common arrangement is a daily deposit for 31 days with one day's deposit kept as the fee. Do not use it for a rotating group where members take turns to collect (a chama or rotating susu), for a bank savings account, or to judge a collector.
| Name | Type | Req | Description |
|---|---|---|---|
| collections | integer | – | How many deposits make one cycle before the pay-out. Leave out for 31. |
| currency | string | – | The currency, as its three-letter code (GHS, NGN, KES, ZAR...). Only labels the answer; leave out if unknown. |
| deposit | number | yes | The amount paid in at each collection. |
| every_days | integer | – | Days between deposits. Leave out for every day. |
| fee_deposits | integer | – | How many of those deposits the collector keeps as the fee. Leave out for 1. |
| Name | Type | Req | Description |
|---|---|---|---|
| collections | integer | – | – |
| currency | string | – | – |
| cycle_days | integer | – | – |
| deposit | number | – | – |
| explore_url | string | – | – |
| fee | number | yes | – |
| fee_percent_of_saved | number | yes | – |
| how_counted | array | yes | – |
| note | string | yes | – |
| paid_out | number | yes | – |
| saved | number | yes | – |
| yearly_rate_percent | number | yes | – |
No examples provided.
How do I install the Money Sums MCP server?
Money Sums is a hosted endpoint at https://kwekuanansi.ai/mcp/money-sums, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · kwekuanansi.ai
claude mcp add --transport http ai-kwekuanansi-money-sums 'https://kwekuanansi.ai/mcp/money-sums'
What is the Money Sums MCP server?
Money Sums is an MCP server listed in the public MCP registry as ai.kwekuanansi/money-sums. True yearly cost of flat-rate and app loans, margin and markup, break-even, and susu fees. This page covers its hosted endpoint (https://kwekuanansi.ai/mcp/money-sums).
Is the Money Sums MCP server safe to use?
Money Sums scores 77 out of 100 on VerifyMCP. 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 Money Sums MCP server expose?
Money Sums exposes 5 tools: loan.instalments, loan.one_repayment, business.margin, business.break_even, savings.collector_fee. Their descriptions and schemas cost roughly 1,301 tokens of context every time the server is loaded.
Does the Money Sums MCP server require authentication?
No. We connected to Money Sums without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Money Sums MCP server still maintained?
Money Sums is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Money Sums MCP server?
VerifyMCP ran 13 checks on Money Sums, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.