Check an x402 seller before paying: verdict, failure rate and evidence from paid calls on Base.
Nothing to run from here
IoMarkets.tech ISO 20022 Test Bench is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
23
tools declared
remote
at its publisher
—
calls last 7d
What it does
Check ISO 20022 messages (pacs.008, pain.001, camt.053, seev.031) against schema and rules.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http iomarkets-tech-iso-20022-test-bench-mcp https://iomarkets.tech/mcp
# 2 — ask your agent for something these tools do
# get_overview, get_guide, explain_term and 20 more
IoMarkets.tech ISO 20022 Test Bench costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
SEAll 2 servers
SergoVashakmadze2 servers
2 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http iomarkets-tech-iso-20022-test-bench-mcp https://iomarkets.tech/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
23 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
What IoMarkets.tech is and what is built: the ISO 20022 Test Bench, the Data API (market data for AI agents, paid per request over x402), the main pages, and what comes next.
No parameter schema on file.
Step-by-step instructions, with the exact button names, for one task on iomarkets.tech (checking a message, CI, verifying a proof, calling the Data API…). Without a task, lists the tasks.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task | string | no | Which task. Leave out to list them all. |
A plain-English meaning of a word used on the site (ISO 20022, schema, IBAN, BIC, LEI, ISIN, UETR, CBPR+, x402, signed proof, MCP…) or of an ISO 20022 XML tag abbreviation such as GrpHdr, CdtrAcct or IntrBkSttlmAmt. Without a term, lists the words.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| term | string | no | The word or tag to explain. |
The ISO 20022 message types and versions the Test Bench checks, with what each is for.
No parameter schema on file.
Check one ISO 20022 XML message (pacs.008.001.08, pacs.009.001.08, pacs.002.001.10, pacs.004.001.09, pain.001.001.09, camt.053.001.08, camt.054.001.08 or seev.031.001.14) against the official base schema, then business rules (check digits, totals, cross-element rules, market practice). Returns valid or not, and every problem with its line, element path, stable code and a plain reason. The message
| Parameter | Type | Required | Notes |
|---|---|---|---|
| xml | string | yes | The whole message, as XML text. A <Document> inside an envelope with an AppHdr is fine. |
| message | string | no | Check as this message type instead of the one its namespace names (optional). |
| schema_only | boolean | no | Skip business rules (optional, default false). |
What a Test Bench issue code (such as IBAN_CHECKSUM, BALANCE_MISMATCH or OUT_OF_ORDER) means and how to fix it. Without a code, lists every code.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| code | string | no | The issue code from a report. |
The Test Bench sample library: a valid message of each type and broken ones, each with the issue code it raises. Use get_sample for the XML.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| message | string | no | Only samples of this message type (optional). |
The XML of one sample message from list_samples, to use as a starting point or in tests. Every party and account in it is made up.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The sample id, from list_samples. |
The Data API routes at https://api.iomarkets.tech, what each returns and its price per call in USDC, with how an AI agent pays (x402 on Algorand mainnet, no account).
No parameter schema on file.
Whether the Data API at https://api.iomarkets.tech is answering right now, from its /health check.
No parameter schema on file.
What a monthly volume of Data API calls costs at the per-call x402 prices, against the indicative subscription plans. Give calls per month for each route; routes left out count as zero.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| signal_vwap | number | no | Calls a month to /v1/signal/vwap (VWAP signal). |
| signal_imbalance | number | no | Calls a month to /v1/signal/imbalance (Order imbalance). |
| candles | number | no | Calls a month to /v1/candles (Candles). |
| proof_price | number | no | Calls a month to /v1/proof/price (Price proof). |
| proof_execution | number | no | Calls a month to /v1/proof/execution (Execution proof). |
Check a signed proof (the { payload, signature } JSON a Data API proof route returns): that the ed25519 signature matches the published IoMarkets key, and that its USDC payment is confirmed on Algorand mainnet (looked up on a public indexer IoMarkets does not run).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| proof | string | yes | The proof as JSON text: { "payload": {…}, "signature": "…" }. |
Exactly how to call POST https://api.iomarkets.tech/v1/proof/execution, the paid best-execution audit: the body (pair, one of BTC-USDC, ETH-USDC, SOL-USDC, and fills: ts, fill_price, qty, side), the limits (fills per call, how old a fill may be, how close the market trade must be), the price, what comes back, and the answers that are not charged (400 for a bad body or an unsupported pair, 422 when
| Parameter | Type | Required | Notes |
|---|---|---|---|
| body | string | no | A draft request body as JSON text, { "pair": "BTC-USDC", "fills": [...] }, to check before paying (optional). |
Check the whole JSON that POST https://api.iomarkets.tech/v1/proof/execution returned ({ audit, summary, attestation }): that the ed25519 signature matches the published IoMarkets key, that its USDC payment is confirmed on Algorand mainnet (a public indexer IoMarkets does not run), that the rows hash to the signed audit_sha256, and that every row and the summary recompute with the API's own scorin
| Parameter | Type | Required | Notes |
|---|---|---|---|
| report | string | yes | The response body as JSON text, exactly as received: { "audit": [...], "summary": {...}, "attestation": { "payload": {...}, "signature": "…" } }. |
Check a token contract against the Tokenized Asset Map: is it the issuer's own contract for a tokenized fund or security on that chain? Verdicts: official, other-chain (the address is listed, but on another chain), impostor (a listed symbol on this chain, a different contract), unknown (not in the map, which says nothing either way).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chain | string | yes | The chain the contract is on. |
| address | string | yes | The contract: 0x address, Solana mint, Stellar CODE:ISSUER, Aptos/Sui type tag, … |
| symbol | string | no | The symbol the token shows (optional), to catch impostors. |
The securities in the Tokenized Asset Map with their identifiers (FIGI, ISIN where the issuer gives it) and the chains they are tokenized on. Optionally filter by issuer, name, symbol, ticker, ISIN or FIGI.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Filter text (optional). |
One Asset Map entry in full: the security, every token contract chain by chain, the issuer sources each comes from, and whether its IoMarkets signature verifies.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The entry id, from list_tokenized_assets. |
Fetch the issuer's own sources for one Asset Map entry now (its contracts page, its public API, or its stellar.toml) and confirm every listed contract is still there, so trust needn't rest on IoMarkets.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The entry id. |
Corporate actions of US-listed companies from their own SEC EDGAR filings (8-Ks of US companies, 6-Ks of foreign private issuers): cash dividends (amount in the stated currency, per share or per ADS, ex, record and payment dates), stock splits, reverse splits and completed mergers (cash or shares per share). Filter by holdings (tickers, CIKs or FIGIs), by days (any of an event's dates between from
| Parameter | Type | Required | Notes |
|---|---|---|---|
| holdings | array | no | Tickers, SEC CIKs or FIGIs (optional; none means every company). |
| from | string | no | First day, YYYY-MM-DD (optional). |
| to | string | no | Last day, YYYY-MM-DD (optional). |
| types | array | no | Kinds of event (optional). |
For a list of holdings (tickers, CIKs or FIGIs), every ex-date, record date, payment date and effective date in one week, day by day. The week holding day, Monday to Sunday; this week by default. Ends with an iCalendar (webcal) subscription URL for those holdings, to give the user for their calendar app.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| holdings | array | yes | Tickers, SEC CIKs or FIGIs. |
| day | string | no | Any day in the week, YYYY-MM-DD (optional; today by default). |
One event in full: every date and term, the filing and the sentence or table row it came from, tokenized versions in the Asset Map, and the event as an ISO 20022 seev.031.001.14 notification (checked by the Test Bench).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The event id, from list_corporate_actions or holdings_calendar. |
For a token contract that the Asset Map lists as a tokenized stock or ETF (such as an xStock): the security it tracks, and that security's dividends, splits and mergers from the corporate actions feed, each with what it does to the token. Answers 'I hold this token; what is coming?' in one call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chain | string | yes | The chain the token is on. |
| address | string | yes | The token contract. |
What IoMarkets.tech has built and is building next, in the same words as iomarkets.org/roadmap.
No parameter schema on file.
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install IoMarkets.tech ISO 20022 Test Bench or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.0.0 · scanned 31 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest7895ed31b9f263f500eef80fa6b34e9f263ee1940689a9979981addd9104962a
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_overview | no tags | |
| get_guide | no tags | |
| explain_term | no tags | |
| list_messages | no tags | |
| validate_message | no tags | |
| explain_issue | no tags | |
| list_samples | no tags | |
| get_sample | no tags | |
| list_data_endpoints | no tags | |
| get_api_status | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| estimate_data_api_cost | no tags | |
| verify_proof | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| explain_execution_request | no tags | |
| verify_execution_report | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| check_token_contract | no tags | |
| list_tokenized_assets | no tags | |
| get_tokenized_asset | sensitive-source | sensitive-source: keyword "get_token" |
| verify_asset_with_issuer | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| list_corporate_actions | no tags | |
| holdings_calendar | no tags | |
| get_corporate_action | no tags | |
| token_corporate_actions | no tags | |
| get_roadmap | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest7895ed31b9f263f5
Scanned2026-10-31
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish IoMarkets.tech ISO 20022 Test Bench can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.