Alpaca Trading API integration for Model Context Protocol (MCP)
Nothing to run from here
Hostdefi X402 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
15
tools declared
remote
at its publisher
—
calls last 7d
What it does
Free token-safety scans + paid x402 verdicts, signals, radar & EVM swap quotes for AI agents.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http hostdefi-x402-mcp https://hostdefi.com/api/v1/mcp
# 2 — ask your agent for something these tools do
# scan_token, get_x402_pricing, token_risk_verdict and 12 more
Hostdefi X402 costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
VEAll 2 servers
verixiaapps2 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 hostdefi-x402-mcp https://hostdefi.com/api/v1/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
15 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.
FREE. HostDeFi token-safety scan — pass any token contract address (Solana mint or EVM address), or an exact token name/ticker: structured risk read with concerning/legitimate on-chain signals (authority state, liquidity, holder concentration, contract flags). No payment, no signup — fair use 100 checks/day per IP (the same free scanner as https://hostdefi.com/scan).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| token | string | yes | token contract address / Solana mint, or an exact token name/ticker |
FREE. The HostDeFi machine-payable price catalog: every paid resource, its USD price and settlement rails.
No parameter schema on file.
PAID ($0.02/call). HostDeFi A+–F token safety verdict by chain + address: grade, score, verdict prose, liquidity/holders/authority signals. Call once WITHOUT x402_payment to receive the x402 payment requirements (an accepts array); pay one of them with any x402 client/wallet, then call again with x402_payment set to the base64 X-PAYMENT payload. You are only charged when a result actually come
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chain | string | yes | solana, ethereum, base, arbitrum, … |
| address | string | yes | token contract address / mint |
| x402_payment | string | no | base64 X-PAYMENT payload (omit on the first call to get payment requirements) |
PAID ($0.25/call). Deep HostDeFi report in one call: the current A+-F verdict with authority/holder signals, the FULL dated safety history for the token, and a derived trend block (grade movement, liquidity trajectory, worst drawdown, days tracked). All figures are computed from recorded rows — no projections. History depth accrues from 2026-08-16. Call once WITHOUT x402_payment to receive the x40
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chain | string | yes | solana, ethereum, base, arbitrum, … |
| address | string | yes | token contract address / mint |
| limit | integer | no | history rows returned, oldest first (default 365) |
| x402_payment | string | no | base64 X-PAYMENT payload (omit on the first call to get payment requirements) |
PAID ($0.05/call). Pre-graduation on-chain signals for a Solana mint: bundled-launch detection, curve-aware holder concentration, Token-2022 traps, authority state. Call once WITHOUT x402_payment to receive the x402 payment requirements (an accepts array); pay one of them with any x402 client/wallet, then call again with x402_payment set to the base64 X-PAYMENT payload. You are only charged wh
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mint | string | yes | Solana mint address |
| x402_payment | string | no | base64 X-PAYMENT payload |
PAID ($0.01/call). Recent HostDeFi trend-radar alerts: big dated movers with real market cap, structured JSON. Call once WITHOUT x402_payment to receive the x402 payment requirements (an accepts array); pay one of them with any x402 client/wallet, then call again with x402_payment set to the base64 X-PAYMENT payload. You are only charged when a result actually comes back.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| x402_payment | string | no | base64 X-PAYMENT payload |
PAID ($0.02/call). Vet an x402 seller BEFORE paying it: A–F grade from observable signals (402-spec fidelity, price sanity, payTo presence, TLS, latency), dated crawl snapshot. Call once WITHOUT x402_payment to receive the x402 payment requirements (an accepts array); pay one of them with any x402 client/wallet, then call again with x402_payment set to the base64 X-PAYMENT payload. You are onl
| Parameter | Type | Required | Notes |
|---|---|---|---|
| resource | string | yes | resource URL or provider origin |
| x402_payment | string | no | base64 X-PAYMENT payload |
PAID ($5, one payment). Mint a 30-day HostDeFi Agent-plan API key (5,000 calls, batch enabled) — the key arrives in the paid response; no account, no signup. Call once WITHOUT x402_payment to receive the x402 payment requirements (an accepts array); pay one of them with any x402 client/wallet, then call again with x402_payment set to the base64 X-PAYMENT payload. You are only charged when a re
| Parameter | Type | Required | Notes |
|---|---|---|---|
| x402_payment | string | no | base64 X-PAYMENT payload |
PAID ($0.01/call). Executable EVM swap: a firm KyberSwap-routed quote plus a ready-to-sign transaction for the taker's OWN wallet — non-custodial, no key, no account. A 1% platform fee in the chain's native coin is priced into the returned transaction, on top of the swap. Call once WITHOUT x402_payment to receive the x402 payment requirements (an accepts array); pay one of them with any x402 cli
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | string | yes | EVM chain id (e.g. 8453 = Base, 1 = Ethereum, 137 = Polygon, 42161 = Arbitrum, 43114 = Avalanche) |
| sellToken | string | yes | 'native' or the 0x… address of the token being sold |
| buyToken | string | yes | 'native' or the 0x… address of the token being bought |
| sellAmount | string | yes | integer amount in the sell token's base units |
| taker | string | yes | the wallet (0x…) that will sign and broadcast the returned transaction |
| ref | string | no | optional referrer 0x… address (splits the platform fee) |
| x402_payment | string | no | base64 X-PAYMENT payload (omit on the first call to get payment requirements) |
PAID ($0.002/call). EVM swap price preview: expected and minimum output for a pair/amount before committing to a firm quote — the cheap look-before-you-swap call. Call once WITHOUT x402_payment to receive the x402 payment requirements (an accepts array); pay one of them with any x402 client/wallet, then call again with x402_payment set to the base64 X-PAYMENT payload. You are only charged when
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | string | yes | EVM chain id (e.g. 8453 = Base) |
| sellToken | string | yes | 'native' or the 0x… address of the token being sold |
| buyToken | string | yes | 'native' or the 0x… address of the token being bought |
| sellAmount | string | yes | integer amount in the sell token's base units |
| x402_payment | string | no | base64 X-PAYMENT payload |
PAID ($0.35/call). HostDeFi full due-diligence report — one document: the A+–F verdict, on-chain signals (authority state, bundled-launch read, holder concentration, Token-2022 traps on Solana), the dated verdict-history series, trend-radar mentions and a rug-ledger cross-check. Call once WITHOUT x402_payment to receive the x402 payment requirements (an accepts array); pay one of them with any x
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chain | string | yes | solana, ethereum, base, arbitrum, … |
| address | string | yes | token contract address / mint |
| x402_payment | string | no | base64 X-PAYMENT payload (omit on the first call to get payment requirements) |
PAID ($0.10/call). Wallet risk-exposure read for a Solana wallet: its largest holdings graded through the full verdict path, exposure counts by risk tier, and a rug-ledger symbol cross-check. Holdings exposure heuristics — NOT AML attribution or sanctions screening. Call once WITHOUT x402_payment to receive the x402 payment requirements (an accepts array); pay one of them with any x402 client/wa
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wallet | string | yes | Solana wallet address (base58) |
| x402_payment | string | no | base64 X-PAYMENT payload |
PAID ($0.02/call). Fresh token launches with HostDeFi safety pre-reads baked in: newest token profiles annotated with authority state, bundled-launch flag, holder concentration and market depth — the clean flag is fail-closed (true only when every check is provably good). Call once WITHOUT x402_payment to receive the x402 payment requirements (an accepts array); pay one of them with any x402 cli
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chain | string | no | chain filter (default solana) |
| limit | integer | no | — |
| x402_payment | string | no | base64 X-PAYMENT payload |
PAID ($0.005/call). Polymarket prediction markets HostDeFi tracks (top ~100 by 24h volume): market ids, questions, latest yes/no odds and sampling stats from HostDeFi's own recorded series. Call once WITHOUT x402_payment to receive the x402 payment requirements (an accepts array); pay one of them with any x402 client/wallet, then call again with x402_payment set to the base64 X-PAYMENT payload
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| x402_payment | string | no | base64 X-PAYMENT payload |
PAID ($0.02/call). 24h odds history for one tracked Polymarket market: [ts, yesUsd, noUsd] points sampled ~1/min into a normalized series — one call, no auth juggling. An untracked market is an uncharged 404. Call once WITHOUT x402_payment to receive the x402 payment requirements (an accepts array); pay one of them with any x402 client/wallet, then call again with x402_payment set to the base6
| Parameter | Type | Required | Notes |
|---|---|---|---|
| marketId | string | yes | Polymarket market id (conditionId, from predict_markets) |
| x402_payment | string | no | base64 X-PAYMENT payload |
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 Hostdefi X402 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 1.3.1 · 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 score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digesta298d5cf3756c6544052020c99898ab2dc7f2a5ab7d46429a0c4fec5eb1c2a19
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 |
|---|---|---|
| scan_token | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_x402_pricing | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| token_risk_verdict | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| token_risk_deep | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| pregrad_signals | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| radar_alerts | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| x402_provider_risk | untrusted-input | untrusted-input: keyword "crawl", declares openWorldHint: true (interacts with entities outside the server) |
| buy_api_key | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| swap_evm_quote | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| swap_evm_price | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| token_report | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| wallet_exposure | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| token_launches | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| predict_markets | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| predict_history | 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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digesta298d5cf3756c654
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 1.3.1.
1.3.1
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 Hostdefi X402 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.