Alpaca Trading API integration for Model Context Protocol (MCP)
Criptonlabs Agent APIs 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.
What it does
Read-only XRPL and Solana data for agents: fees, slippage, readiness. Free /mcp; x402 /mcp/pro.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http criptonlabs-agent-apis-mcp https://api.criptonlabs.com/mcp
# 2 — ask your agent for something these tools do
# xrpl_fee, xrpl_network_health, xrpl_orderbook and 13 more
Criptonlabs Agent APIs costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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.
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 criptonlabs-agent-apis-mcp https://api.criptonlabs.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
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.
16 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.
Current XRPL fee tiers in drops with a congestion score. When to use: Before submitting a transaction, to choose a Fee and to decide whether the network is congested. Prefer another tool: Not a price feed and not a historical series; it describes the latest validated ledger only. Example: xrpl_fee {}
No parameter schema on file.
Overall and per-node health of the upstream XRPL nodes. When to use: To decide whether to trust or retry data, or to explain a 503 from another endpoint. Prefer another tool: Not a probe of your own connectivity; it reports the service's upstream nodes. Example: xrpl_network_health {}
No parameter schema on file.
CLOB order book for a currency pair with unfunded offers removed. When to use: To read executable liquidity for a pair on the XRPL central limit order book (CLOB). Prefer another tool: Not for AMM liquidity (use the amm page) and not for a cost estimate (use the slippage page). Example: xrpl_orderbook {"base":"XRP","quote":"USD.rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh"}
| Parameter | Type | Required | Notes |
|---|---|---|---|
| base | string | yes | Base currency: XRP (no issuer) or CODE.issuer with a valid classic-address issuer (e.g. USD.rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh) |
| quote | string | yes | Quote currency: XRP (no issuer) or CODE.issuer with a valid classic-address issuer (e.g. USD.rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh) |
| depth | string | no | Levels per side: a positive integer, rounded up to 10, 50, 100 or 200 (max 200) |
Slippage and average price for buying an amount of base currency. When to use: Before placing a market-style trade, to size it against available depth and to see whether the CLOB or the AMM pool is the cheaper venue. Prefer another tool: It is an estimate, not a quote, and it does not split an amount across venues or route through other pairs. To read pool reserves, use the amm page. Example: xrpl
| Parameter | Type | Required | Notes |
|---|---|---|---|
| base | string | yes | Base currency: XRP (no issuer) or CODE.issuer with a valid classic-address issuer (e.g. USD.rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh) |
| quote | string | yes | Quote currency: XRP (no issuer) or CODE.issuer with a valid classic-address issuer (e.g. USD.rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh) |
| amount | string | yes | Positive decimal amount of base to buy |
| depth | string | no | Levels per side: a positive integer, rounded up to 10, 50, 100 or 200 (max 200) |
AMM pool reserves and trading fee for an asset pair. When to use: To read AMM pool depth and fee for a pair. Prefer another tool: It does not estimate slippage or compare venues (use the slippage page for the CLOB vs AMM comparison); a pair without a pool returns 404. Example: xrpl_amm {"a":"XRP","b":"USD.rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh"}
| Parameter | Type | Required | Notes |
|---|---|---|---|
| a | string | yes | First asset: XRP (no issuer) or CODE.issuer with a valid classic-address issuer (e.g. USD.rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh) |
| b | string | yes | Second asset: XRP (no issuer) or CODE.issuer with a valid classic-address issuer (e.g. USD.rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh) |
XRP balance, sequence, owner count, transfer rate and trust lines (capped) for an account. When to use: To inspect an account before building a transaction for it. Prefer another tool: Not for transaction history, reserves or account flags; it is a summary, not a full account dump. Example: xrpl_account_summary {"address":"rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh"}
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | Valid classic XRPL account address (r..., checksum verified) |
One page of an account's trust lines, with an opaque cursor for the next page. When to use: To list every trust line of an account (balances, limits, freeze and authorization flags), page by page. Prefer another tool: For a quick capped overview with the XRP balance, use /v1/xrpl/account/{address}/summary; for issued totals of a token, use the token endpoint. Example: xrpl_account_lines {"addres
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | Valid classic XRPL account address (r..., checksum verified) |
| limit | string | no | Lines per page: an integer from 10 to 400 (default 100) |
| peer | string | no | Only lines with this counterparty (classic address) |
| marker | string | no | Opaque cursor from the previous page's marker, for the same address |
One page of an account's most recent validated transactions, newest first. When to use: To check what an account did recently (payments sent or received, offers, trust line changes) and whether each transaction succeeded. Prefer another tool: For balances and trust lines, use /v1/xrpl/account/{address}/summary or /v1/xrpl/account/{address}/lines; for full archival history, use a full-history n
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | Valid classic XRPL account address (r..., checksum verified) |
| limit | string | no | Transactions per page: an integer from 1 to 50 (default 20) |
| marker | string | no | Opaque cursor from the previous page's marker, for the same address |
Issuer data for an issued asset: flags, domain, transfer fee and total issued. When to use: Before accepting or sending an issued token: check that the issuer exists, is not frozen, whether holders need authorization, and the transfer fee charged on every transfer between non-issuer accounts. Prefer another tool: For XRP (not an issued asset; 400), for one account's own balances use `/v1/xrpl/acco
| Parameter | Type | Required | Notes |
|---|---|---|---|
| asset | string | yes | Issued asset as CODE.issuer (3-character or 40-hex code, classic issuer address); not XRP |
Pre-payment check: can this payment from source to destination succeed now? When to use: Right before sending a payment: to catch a missing or unfunded destination, a required destination tag, deposit authorization, missing or frozen trust lines, insufficient balance and issuer freezes, in one call. Prefer another tool: To find a multi-hop route or the source amount needed for a cross-currency pay
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source | string | yes | Sending account: valid classic XRPL address (r..., checksum verified) |
| destination | string | yes | Receiving account: valid classic XRPL address, different from source |
| asset | string | no | XRP (default) or CODE.issuer (3-character or 40-hex code, classic issuer) |
| amount | string | no | Positive decimal amount of asset; omit to skip amount-dependent checks |
| destination_tag | string | no | Destination tag you will send: an integer from 0 to 4294967295 |
Multi-hop payment paths and their source cost. When to use: Before a cross-currency or multi-hop payment: to see whether a route exists and how much the source would spend to deliver the amount. A call can take up to about 20 seconds and paths may be non-optimal. Prefer another tool: To check whether a direct payment can succeed (use /v1/xrpl/payment-readiness), or for the single-hop cost of a t
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source | string | yes | Sending account: valid classic XRPL address (r..., checksum verified) |
| destination | string | yes | Receiving account: valid classic XRPL address |
| asset | string | yes | Asset delivered: XRP or CODE.issuer (3-character or 40-hex code, classic issuer) |
| amount | string | yes | Positive decimal amount of asset the destination receives |
| send_max_asset | string | no | Asset of send_max: XRP or CODE.issuer; give it with send_max |
| send_max | string | no | Most the source may spend, in send_max_asset; not with source_assets |
| source_assets | string | no | Comma-separated assets the source may spend (1 to 4); not with send_max |
Latest validated ledger index, hash and close time. When to use: To anchor other readings to a ledger or to check how current the network view is. Prefer another tool: Not for transaction data or account state; use the account endpoint for those. Example: xrpl_latest_ledger {}
No parameter schema on file.
Will this Solana transfer succeed? A verdict for SOL or an SPL or Token-2022 token. When to use: Before building or signing a Solana transfer, to learn whether it will fail and what it will cost in rent and fees. Prefer another tool: Not a simulation of the exact transaction (no priority fee, no program logic), not a token price or holder lookup, and not a way to read raw accounts. Example: solana
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source | string | yes | Sending wallet: Solana wallet address: a base58 string that decodes to exactly 32 bytes |
| destination | string | yes | Receiving wallet (not its token account): Solana wallet address: a base58 string that decodes to exactly 32 bytes |
| mint | string | yes | SOL for native SOL, or the mint address of an SPL Token or Token-2022 token |
| amount | string | yes | Positive decimal amount in UI units (SOL or tokens, not lamports or raw units) |
Is this Solana token safe to hold or receive? A SAFE, WARN or DANGER verdict. When to use: Before accepting or swapping into an unfamiliar token, to see whether its mint can freeze, mint more, move or tax balances. Prefer another tool: Not a price, liquidity or holder lookup and not an audit of the token's project; it reads only the mint account. Example: solana_token {"mint":"EPjFWdd5AufqSSqeM2qN
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mint | string | yes | Mint address of an SPL Token or Token-2022 token (base58, 32 bytes) |
Latest finalized Solana slot and its block time. When to use: To check how fresh the finalized view of Solana is, or to anchor a read to a slot. Prefer another tool: Not a tip-of-chain feed: it is finalized, not processed or confirmed, and it is cached for 2 seconds. Example: solana_latest_slot {}
No parameter schema on file.
Whether Solana data is currently being served: latest probe status and finalized slot. When to use: Before relying on the Solana verdict endpoints, or to explain a 503 from them. Prefer another tool: Not a measure of the Solana network itself, only of this service's access to it; use the latest-slot endpoint to see chain progress. Example: solana_network_health {}
No parameter schema on file.
- 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 Criptonlabs Agent APIs or to call it, at any volume.
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.
| 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 |
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.
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 |
|---|---|---|
| xrpl_fee | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| xrpl_network_health | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| xrpl_orderbook | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| xrpl_slippage | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| xrpl_amm | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| xrpl_account_summary | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| xrpl_account_lines | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| xrpl_account_transactions | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| xrpl_token | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| xrpl_payment_readiness | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| xrpl_paths | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| xrpl_latest_ledger | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| solana_transfer_readiness | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| solana_token | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| solana_latest_slot | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| solana_network_health | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
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
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 0.19.2.
No release note was published with this version.
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.
Any signed-in account that does not publish Criptonlabs Agent APIs can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.