Alpaca Trading API integration for Model Context Protocol (MCP)
Nothing to run from here
XRPLHub — XRPLScore & XRPL actions 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.
96/100
tool-list score
21
tools declared
remote
at its publisher
—
calls last 7d
What it does
XRPL wallet scores, wallet permissions, batch send, MPT risk, screening, pre-checks. Never signs.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http xrplhub-xrplscore-xrpl-actions-mcp https://www.xrplhub.io/api/mcp
# 2 — ask your agent for something these tools do
# issue_score_credential, check_xrpl_score, get_account_credentials and 18 more
XRPLHub — XRPLScore & XRPL actions costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
DCAll 2 servers
Dcroyalty2 servers
1 category
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 xrplhub-xrplscore-xrpl-actions-mcp https://www.xrplhub.io/api/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
21 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.
Get a certificate of a wallet's XRPLScore, signed by XRPLHub, with the score computed fresh at issuance. A counterparty checks it by asking XRPLHub's verify URL — the signature is an HMAC under a key only XRPLHub holds, so this is XRPLHub's own attestation, not independently verifiable proof, and the buyer need not control the wallet. Two calls: first returns a Xaman payment request (1 XRP or 1 RL
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wallet_address | string | yes | XRP Ledger wallet address the credential will attest to (starts with r) |
| currency | string | no | Payment currency. Defaults to XRP. |
| uuid | string | no | Only for the second call: the payment uuid returned by the first call, after the user has signed in Xaman. |
Get a 300–850 creditworthiness score for any XRP Ledger wallet before you pay, lend to, trade with, or onboard it. You get back: the score, a letter grade, peer percentile, a per-signal breakdown (account age, lifetime tx history, financial health, token engagement, DEX activity, AMM participation, security config, NFTs), and ranked tips to raise it. Params: wallet_address (r... classic address, 2
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wallet_address | string | yes | XRP Ledger classic address to score (starts with r, 25–35 characters) |
Get every XLS-70 credential an XRPL account holds — issuer, type, whether it has been accepted, whether it's expired, and its expiry date. Live against a validated mainnet ledger (never stale). Use this before trusting a counterparty who claims to hold a credential. Default walks the owner directory (bounded ~20s; response has coverage "complete"/"partial" — for an exchange-scale account it can be
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wallet_address | string | yes | XRPL classic address to look up (starts with r) |
| issuer | string | no | Optional — restrict to one issuer via a direct ledger lookup (no owner-directory walk) |
| credential_type | string | no | Optional — credential type (plain name or hex); required with issuer unless the issuer is XRPLHub's |
Get everything an issuer account has issued: every credential type, distinct subject count, and acceptance rate. Served from a network-wide census rebuilt on a schedule — the response includes coverage ("complete" or "partial") so a mid-walk answer is never mistaken for a finished count. Params: issuer_address (r..., required). Free, no signup.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| issuer_address | string | yes | XRPL classic address of the credential issuer (starts with r) |
Get the risk view of one XLS-33 Multi-Purpose Token issuance before touching it: what the issuer CAN DO to a holder (clawback, freeze, require-auth, whether it's transferable at all) plus the issuer's XRPLScore. Free. For the full issuer picture — account age, xrp-ledger.toml-verified domain, credentials held (live ledger reads) — GET /api/x402/usdc/mpt/{id} pays $0.01 USDC on Base via x402. Every
| Parameter | Type | Required | Notes |
|---|---|---|---|
| issuance_id | string | yes | The MPTokenIssuanceID — 48 hexadecimal characters (XLS-33, 192-bit) |
Search the XRPL Multi-Purpose Token (XLS-33) registry index by issuer address, MPTokenIssuanceID (or a hex prefix of one), or token name / ticker. Returns each match with issuer powers (clawback, freeze, require-auth, transferable), supply, holder count and source. Served from the index — the response carries coverage ('complete' or 'partial') and lastCompletedPassAt; treat 'partial' as a floor, n
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Issuer address (r...), MPTokenIssuanceID or hex prefix, or token name/ticker |
Everything one issuer has put out as Multi-Purpose Tokens (XLS-33), from the registry index, plus the issuer's own XRPLScore. Each issuance lists the issuer's powers over a holder. Response carries coverage ('complete-per-known-issuer'/'partial'). Params: issuer_address (r..., required). Free, no signup.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| issuer_address | string | yes | XRPL issuer address (starts with r) |
Check whether the XRPLHub money path is working BEFORE you pay: database, Xaman, both x402 facilitators (t54 RLUSD + CDP USDC-on-Base), the on-ledger anchor config, the credential signing secret, and alerting. Returns overall "ok" | "warn" | "down" plus a per-component list. Poll this if a prior paid call failed. No params. Free, no signup.
No parameter schema on file.
Get the latest on-ledger anchor of the MPT registry (BIS Working Paper 1374 pattern): a Merkle root over the canonicalised index, committed in a Memo on a transaction from a dedicated anchor wallet (not the credential issuer). Returns the root, its tx hash, ledger index, issuance/issuer counts, coverage, and the exact canonicalisation + Merkle scheme so you can reproduce the root from the publishe
No parameter schema on file.
Check whether an XRPL account holds a credential that satisfies a PermissionedDomain (XLS-80d) — the question every domain operator and every would-be participant actually asks before a real transaction. Live against a validated mainnet ledger. Eligibility is OR: any ONE accepted, unexpired credential matching the domain's AcceptedCredentials is enough. Params: wallet_address (r..., required), dom
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wallet_address | string | yes | XRPL classic address to check (starts with r) |
| domain_id | string | yes | The PermissionedDomain's ledger index — 64 hex characters |
Apply for a community micro-grant ($25–$100) paid wallet-to-wallet from the XRPLHub on-chain treasury for rent, utilities, groceries, medical, transport, or childcare. Returns a grant id and status. A person reviews every application and makes every decision — no automated triage, no middleman. Params: wallet_address (r..., required), category (RENT|UTILITIES|GROCERIES|MEDICAL|TRANSPORT|CHILDCARE|
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wallet_address | string | yes | XRPL wallet address where the grant will be sent if approved |
| category | string | yes | Grant category: RENT, UTILITIES, GROCERIES, MEDICAL, TRANSPORT, CHILDCARE, or OTHER |
| amount | number | yes | Amount requested in RLUSD (1–100) |
| description | string | yes | Clear description of the need, situation, and urgency (2–4 sentences). Be specific — vague applications are harder for the reviewer to verify. |
| currency | string | no | Payout currency. Default and recommended: RLUSD |
Donate XRP or RLUSD to the XRPLHub Community Grant Treasury — a transparent on-chain fund that pays approved applicants wallet-to-wallet with zero overhead. Returns the treasury address and, if you pass donor_wallet, a ready-to-sign Payment txjson; every donation and payout is recorded on the XRP Ledger and publicly verifiable. Params: amount (number, required), currency (XRP|RLUSD, default XRP),
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount | number | yes | Amount to donate. Minimum 1. Any size welcome — even 1-5 XRP helps fund a real grant. |
| currency | string | no | XRP or RLUSD. Default: XRP. Use RLUSD for a stable USD-equivalent donation. |
| donor_wallet | string | no | Optional. XRPL wallet address of the donor. Providing this allows building a ready-to-sign Payment transaction. |
| message | string | no | Optional. A short dedication or message to attach to the donation record. |
Compare one XRPL address against a vintage-pinned snapshot of the US Treasury OFAC SDN list (exact address-string match only) and get a factual, Merkle-anchored receipt. ATTESTS TO PROCESS, NOT GROUND TRUTH: the receipt records that the address was compared against a named list snapshot (its OFAC publish date + the SHA-256 of the exact file) at a stated time, and what the comparison found. A "no m
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | XRPL classic address (r..., 25–35 chars) to compare against the OFAC SDN list |
Describe XRPLHub's continuous-monitoring service so an agent can decide whether to use it: what it watches for a list of wallets (score drops against a threshold YOU set, OFAC SDN list hits, and — once XLS-66 activates — first loan / overdue / impaired / defaulted), how it is delivered (HMAC-signed webhooks, once-a-day checks, attested Merkle-anchored history), per-plan watch slots, the shared cap
No parameter schema on file.
Given a queryId from screen_address_ofac OR get_lending_exposure, return everything needed to verify that receipt WITHOUT trusting XRPLHub: the canonical leaf, its Merkle inclusion proof, the on-ledger anchor transaction hash + ledger close time, and the SHA-256 of the source data (the OFAC SDN snapshot, or — for lending — the exact list of Loan ids observed). Rebuild the leaf, fold the proof to t
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query_id | string | yes | The queryId (UUID) from screen_address_ofac or get_lending_exposure |
A borrower's TOTAL XLS-66 lending exposure across ALL loan brokers in one call — the XRP Ledger has no aggregate borrower-debt object, so a broker carrying first-loss capital cannot see a borrower's total leverage elsewhere. Returns: outstanding by asset, loan count, distinct broker count, defaults / impairments / overdue, XRPLHub's XRPLScore, and an observation history summary. IMPORTANT: XLS-66
| Parameter | Type | Required | Notes |
|---|---|---|---|
| borrower | string | yes | XRPL classic address (r..., 25–35 chars) of the borrower |
The full underwriting-inputs bundle a LoanBroker needs for an XLS-66 decision, in one call: cross-broker exposure, XRPLScore + grade, OFAC SDN screening (with its own verifiable receipt), observation history + gaps, and one Merkle-anchored attestation over the whole bundle. FACTS ONLY — it never returns a recommended principal, rate, approve/decline, or probability of default; the broker decides.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| borrower | string | yes | XRPL classic address (r...) of the borrower |
Before your agent pays an XRPL address: one verdict (block / caution / proceed) by fixed published rules — the destination's XRPLScore, a sanctions screen against every list XRPLHub holds (with a verifiable receipt), account age and ledger flags, and whether the ledger would REJECT the payment (missing destination tag, Deposit Authorization, no RLUSD trust line, unfunded account). This is a PAID x
| Parameter | Type | Required | Notes |
|---|---|---|---|
| destination | string | yes | The XRPL address (r...) you are about to pay |
| amount | string | no | Optional: the amount you intend to send (plain decimal) |
| currency | string | no | Optional: XRP (default when amount is given) or RLUSD |
| destination_tag | integer | no | Optional: the destination tag you will use |
| from | string | no | Optional: your paying address — lets the check test Deposit Authorization preauth |
Who can move money out of an XRPL wallet: its master key, a regular key, a multi-sign signer list, permission delegations (given and received — live on mainnet since 2026-10-08), and money others can pull without a new approval (checks, payment channels, escrows, open DEX and NFT offers, tickets). One plain-English sentence per finding plus the raw ledger facts. This is a PAID x402 call: $0.02 in
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | The XRPL account (r...) to check |
Pay 2 to 8 XRPL addresses with ONE signature, all or nothing (XRPL Batch, tfAllOrNothing — live on mainnet since 2026-10-09). Checks every payment on the live ledger first (destination exists or will be created, destination tag, Deposit Authorization, RLUSD trust line, sender balance + fee) and refuses a batch that would fail. Returns the UNSIGNED Batch transaction and a Xaman sign link. FREE. XRP
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | yes | The paying XRPL account (r...) |
| recipients | array | yes | — |
Every loan XRPLHub has EVER observed for a borrower, built from append-only exposure snapshots — the credit file the XRP Ledger can't keep. Per loan: first/last observed ledger, last-known status, monotonic everDefaulted / everImpaired / everOverdue flags, and for loans since deleted from the ledger, the ledger window in which they vanished. A borrower who defaulted and then deleted the loan shows
| Parameter | Type | Required | Notes |
|---|---|---|---|
| borrower | string | yes | XRPL classic address (r...) of the borrower |
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 XRPLHub — XRPLScore & XRPL actions 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 96 / 100
Release 1.18.0 · scanned 20 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 score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digest40d76aa4c7a42fc9d6bfd3bcf373dd24c7affef3e4abd5e93b63a0e028dd3d27
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| issue_score_credential | no tags | |
| check_xrpl_score | no tags | |
| get_account_credentials | no tags | |
| get_issuer_credentials | no tags | |
| check_mpt_risk | no tags | |
| search_mpts | no tags | |
| get_issuer_mpts | no tags | |
| check_service_health | no tags | |
| verify_mpt_registry | no tags | |
| check_domain_eligibility | no tags | |
| submit_grant_application | no tags | |
| donate_to_community_fund | no tags | |
| screen_address_ofac | no tags | |
| get_monitoring_info | no tags | |
| verify_attestation | no tags | |
| get_lending_exposure | no tags | |
| get_underwriting_inputs | no tags | |
| precheck_payment | no tags | |
| check_wallet_permissions | no tags | |
| prepare_batch_send | no tags | |
| get_lending_history | 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 digest40d76aa4c7a42fc9
Scanned2026-10-20
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 1.18.0.
1.18.0
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 XRPLHub — XRPLScore & XRPL actions 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.