Realtap
REMOTE · REALTAP.APP
Live Cardano data (token prices, DEX trades, pools, wallets, NFTs, staking, governance). Read-only.
Available components
Last scanned (5 hours ago)
Scores higher than 53% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Crypto and Web3
Recent critical change
Authorization (28 Oct 2026). See the changelog before you install this server.
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 Security51
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (delete_alert). See how to fix → View diagnostics → Fail
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability67
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 12940 tokens (~157/item across 82 items; 82 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 Management50
- Stability observed for 15 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
Tool Safety88
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 1 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "check_programmable_transfer" implies "transfer" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
- An AI judge read all 83 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
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.
- 5 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.
- 3 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 29 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Oct 26 −6
- Authorization: partial → fail ▼ critical
- The server rewrote its instructions, which are the text every model session reads security
- New tool “delete_alert”, which the server declares destructive security
- Schema quality: 11469 → 12940 ▼ functional
- Destructive annotations: 0% → 50% ▲ functional
- Server version: 1.4.0 → 1.5.0 functional
- New tool “create_alert” functional
- New tool “get_token_staking” functional
- New tool “get_wallet_risk” functional
- New tool “list_alerts” functional
- New tool “test_alert” functional
- 27 Oct 26 +51
- Authorization: unverified → partial ▲ security
- Injection markers: unverified → pass ▲ security
- HSTS header: fail → 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
- 26 Oct 26 −50
- 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
- HSTS header: pass → fail ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- 24 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
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 5 Nov 2026 · Probed https://realtap.app/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=realtap.app | CN=YE2,O=Let's Encrypt,C=US | 9 Oct 2026 | 7 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 668e17691808adb25c9021388a8bcee7fa1 |
| SANs: *.realtap.app, realtap.app | ||||||
| CN=YE2,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 4df3b15dd6c0784c507cd37b58e6f115 |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of realtap.app. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| app. | present | 23684 | 8 | Verified |
| realtap.app. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
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=31536000 |
| content-security-policy | default-src 'none'; frame-ancestors 'none'; base-uri 'none'; form-action 'none' |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=(), payment=(), usb=(), serial=(), bluetooth=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://realtap.app/api/mcp | Verified | 200 | |
| http (plaintext) | http://realtap.app/api/mcp | Inconclusive | 405 |
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 →
get_token_candles Token price candles (OHLCV) ~183
Open/high/low/close price candles and traded volume for a token, newest last, for charts, trend and volatility questions. Prices are per token in ADA (default) or USD; volume is in ADA. Returns compact rows: [time ISO, open, high, low, close, volumeAda, trades].
| Name | Type | Req | Description |
|---|---|---|---|
| allPools | boolean | – | true aggregates every pool of the token (volume-weighted price, summed volume); false uses its primary pool. |
| interval | string | – | Candle width. |
| limit | integer | – | How many most recent candles to return (1-500, default 100). |
| quote | string | – | Currency of the prices. |
| unit | string | yes | Token unit: 56-hex policy id followed by the asset name in hex (no separator). Get it from `search` or `list_tokens`. |
No output schema declared.
No examples provided.
get_token_distribution Token holder distribution ~160
How a token's supply is spread over its holders: share held by the top 10, 50 and 100 holders, holders by size, the rest of the supply, balances sitting in DEX pools and contracts. `coverage` says exactly what the list is: the largest balances of a complete read, or only the largest among the addresses read before the read stopped (then no "top N" share is given, and the holder count is a lower bound). Never quote a share as "top N" when `coverage.listIsTop` is false.
| Name | Type | Req | Description |
|---|---|---|---|
| unit | string | yes | Token unit: 56-hex policy id followed by the asset name in hex (no separator). Get it from `search` or `list_tokens`. |
No output schema declared.
No examples provided.
get_token_liquidity Token liquidity: depth and liquidity flow ~234
Liquidity of one token. Depth: for each constant-product pool paired with ADA, the ADA that moves the pool's price 2 % up (buying) and the ADA received when selling moves it 2 % down, by the pool's own curve and fee (pools of other kinds, other pairings or without a fee are listed with the reason and left out of the sums). Flow: liquidity added and removed over the window (value of both sides in ADA at the pool price before each order settled; withdrawals are estimates from their LP share), net flow per wallet and the latest orders. Every figure carries what it covers: `coverage` names the window, the pools measured and the DEXes with no liquidity orders recorded.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many wallets and orders to return (1-25, default 10). |
| unit | string | yes | Token unit: 56-hex policy id followed by the asset name in hex (no separator). Get it from `search` or `list_tokens`. |
| window | string | – | How far back the flow figures look. |
No output schema declared.
No examples provided.
get_token_prices Prices of several tokens ~213
Prices of up to 100 Cardano tokens in one call (ADA and USD per token), optionally with the change of the ADA price over windows from 5 minutes to 90 days (percent). Use it instead of calling `get_token` repeatedly when you hold a list of units. A null change means the token did not trade yet at the start of that window; 30d and 90d only reach back as far as our history. Prices come from DEX pools: check liquidity with `get_token` before quoting a thin token.
| Name | Type | Req | Description |
|---|---|---|---|
| units | string | yes | Comma separated token units (56-hex policy id + asset name in hex; "lovelace" for ADA), 1 to 100 of them. Get them from `search` or `list_tokens`. |
| windows | string | – | Optional comma separated windows for the price change: 5m, 1h, 6h, 24h, 7d, 30d, 90d. |
No output schema declared.
No examples provided.
get_token_safety Token safety check ("is this a rug?") ~107
Evidence-based risk check of one token: risk score and level (higher = riskier), fraud flags with their evidence, whether the mint policy is locked, liquidity depth and how much of the LP is locked or burned, holder concentration and what was not checked. Use it before calling a token safe.
| Name | Type | Req | Description |
|---|---|---|---|
| unit | string | yes | Token unit: 56-hex policy id followed by the asset name in hex (no separator). Get it from `search` or `list_tokens`. |
No output schema declared.
No examples provided.
get_token_staking Token staking programs ~196
Tokens staked in a project's own contracts: Iagon (IAG), Indigo INDY staking and Minswap yield farms (LP tokens). Without `token`: the programs with TVL in ADA, stakers, 24 h / 7 d change of the staked amount and the share held by the ten largest stakers. With `token` (a unit or a ticker such as IAG, INDY): top stakers, size distribution, 7 / 30 day inflows and outflows, lock states and the daily history. Rewards are paid off chain and are not part of the figures.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many programs to return (1-25, default 15). |
| token | string | – | A staked unit (56-120 hex) or a ticker / name fragment from the list (IAG, INDY, MIN). Leave out to list the programs. |
No output schema declared.
No examples provided.
get_transaction Transaction detail ~80
A Cardano transaction by hash: block, time, fee and total output (ADA), the net ADA and token change per address, minted or burned assets, certificates, withdrawals, and any DEX swaps or NFT sales it contains. Amounts are whole ADA and decimal-adjusted tokens.
| Name | Type | Req | Description |
|---|---|---|---|
| hash | string | yes | Transaction hash: 64 hex characters. |
No output schema declared.
No examples provided.
get_trending_tokens Trending tokens ~80
Tokens ranked by traded volume over a window (the site's Trending list), with price change, liquidity, trades and holders. Prices are in ADA, changes in percent.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many tokens to return (1-25, default 10). |
| window | string | – | Window of the volume ranking and of the price change. |
No output schema declared.
No examples provided.
get_wallet Wallet balances ~117
Current holdings of a Cardano wallet: ADA balance, native tokens with balances (decimal-adjusted) and their value in ADA and USD, total portfolio value and trades in the last 24 h. Accepts a payment address (addr1…), a stake address (stake1…, all its addresses combined) or an ADA Handle ($name).
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | addr1…, stake1… or $handle. |
| limit | integer | – | How many positions, largest value first, to return (1-50, default 15). |
No output schema declared.
No examples provided.
get_wallet_activity Wallet trading hours and liquidity history ~132
When a wallet trades: settled DEX swaps by weekday and hour (UTC) over the swaps the site holds (`from`, `to` say which span; a very busy wallet is cut to its newest 10,000), the busiest hour, and the liquidity the wallet added and removed by pool (executed orders only; value in ADA at the pool price of the moment). Wallets without a stake key cannot be counted.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | addr1…, stake1… or $handle. |
| limit | integer | – | How many pools to return (1-25, default 10). |
No output schema declared.
No examples provided.
get_wallet_handles ADA Handles owned by a wallet ~57
The ADA Handles ($names) held by an address or stake address. To find the owner of one handle use `resolve_handle`.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | addr1…, stake1… or a 56-hex stake key hash. |
No output schema declared.
No examples provided.
get_wallet_loans A wallet's loans ~54
Loans a wallet has lent or borrowed (open and active first): amounts, collateral, rate, status, with totals in ADA.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | Wallet: addr1…, stake1… or $handle. |
No output schema declared.
No examples provided.
get_wallet_pnl Wallet trading profit and loss ~128
Realised and unrealised profit and loss of a wallet's DEX trading (FIFO, in ADA and USD), win rate (percent), trade count, volume (ADA) and the tokens that contributed most. Only covers swaps since `coverageFrom`. Slower than other tools and limited to fewer calls per minute: call it only when PnL is actually asked for.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | addr1…, stake1… or $handle. |
| limit | integer | – | How many tokens, largest PnL first, to return (1-30, default 10). |
No output schema declared.
No examples provided.
get_wallet_risk Wallet risk score (a heuristic) ~145
A transparent 0-100 risk score for a wallet with named reasons and the evidence behind each: issuer block-list membership, tokens the wallet minted that are now rated danger, flagged tokens it bought (tokens merely sent to it never count), round trips with itself, bot-like trading, a very new wallet. `notChecked` lists what was not scored (mixers and sanctions lists, scam-labelled counterparties). It is a heuristic, not an accusation: quote `disclaimer` with the score and never present it as proof of wrongdoing. Wallets without a stake key get no score.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | addr1…, stake1… or $handle. |
No output schema declared.
No examples provided.
get_wrapped_card Cardano Wrapped 2026 card ~158
Cardano Wrapped 2026: one wallet's year on Cardano (trading, NFTs, staking, governance, an archetype and ranks) with a link to the shareable card. Opens 1 December 2026; before that the tool answers with the launch date and no card. A wallet can opt out, and then there is no card. The first request for a wallet computes the card, which can take a few seconds.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | The wallet: a $handle, a stake1… address or an addr1… address that has a stake part. |
| refresh | boolean | – | Recompute the card instead of reading the stored one (honoured at most about once an hour per wallet). |
No output schema declared.
No examples provided.
list_alerts List your alert rules and delivery targets ~151
The alert rules your API key created, the account's delivery targets (signing secrets are never shown) and the most recent deliveries with their status, so you can see whether a webhook is working. Only a key's own rules can be changed, deleted or tested; with `all` the account's other rules (made on the website or by other keys) are listed too, read-only (`own: false`), wallet addresses cut to a prefix and without their targets. Needs an API key.
| Name | Type | Req | Description |
|---|---|---|---|
| all | boolean | – | Also list the account's other rules, read-only and redacted. |
| deliveries | integer | – | How many recent deliveries to include (0-20, default 5). |
No output schema declared.
No examples provided.
list_dexes Cardano DEXes compared ~134
Every Cardano DEX the site indexes, side by side: volume, swaps, makers (distinct wallets) and trading fees of the last 24 hours with the share of all volume, the same over the last 7 and 30 full days where that many are stored, liquidity (ADA in its pools), number of pools and fee APR (trading fees of 7 full days scaled to a year, over the liquidity in pools that have liquidity providers; null for bonding curves, order books and pools whose fee is unknown). DEX versions are separate entries (Minswap and MinswapV2).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_governance_actions Cardano governance actions ~125
On-chain governance proposals (treasury withdrawals, parameter changes, hard forks, committee and constitution changes, info actions) with status, epochs, requested ADA and the current yes/no vote share (percent of voting power) of DReps and stake pools. Use it for questions about what Cardano is voting on.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many actions, newest first, to return (1-30, default 10). |
| query | string | – | Only actions whose title contains this text. |
| status | string | – | active = open for voting now. |
No output schema declared.
No examples provided.
list_market_trades Trades on all DEXes, large trades ~230
Settled swaps on every Cardano DEX, newest first, optionally only those of at least `minAda` ADA ("large trades", "whale trades") or on one DEX. `window` is how far back to look (default 24 hours). Each trade has the time, DEX, the token traded (see `tokenUnits` for units), amounts, price and value in ADA and USD, the trader's stake address, the app that built the order and the transaction hash. For the trades of one token, pool or wallet use `get_recent_trades`.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | Value of `nextCursor` from the previous call, to get the next page. |
| dex | string | – | Only this DEX, by its name as `list_dexes` returns it. |
| limit | integer | – | How many trades to return (1-50, default 10). |
| minAda | number | – | Only trades worth at least this many ADA (for example 10000). |
| window | string | – | How far back to look. |
No output schema declared.
No examples provided.
list_masumi_agents Find AI agent services on Cardano (Masumi) ~262
Search the AI agent services registered in the Masumi registry on Cardano: what each one does, its price, the address of its API, who registered it, and, read from Masumi's escrow contract, how many payments it actually received, from how many distinct buyers and when last. Use it to find an agent that offers a service, or to judge whether a listed agent is used at all. The answer also carries the network totals of the last 30 days. Entries are written by their owners and are not verified.
| Name | Type | Req | Description |
|---|---|---|---|
| kind | string | – | agent = services that are paid through Masumi's escrow; x402 = HTTP resources paid per call on another chain; all = both. |
| limit | integer | – | How many entries to return (1-50, default 10). |
| page | integer | – | Page number, from 1. |
| paidOnly | boolean | – | true lists only entries that received at least one payment in the indexed history. |
| query | string | – | Words to look for in the name, description, tags, author or endpoint, for example "research" or "image". |
| sort | string | – | payments = most payments received first; recent = newest registration first; price = cheapest first. |
No output schema declared.
No examples provided.
list_nft_collections Rank NFT collections ~121
Ranked list of Cardano NFT collections with floor price (ADA and USD), 24 h floor change (percent), volume (ADA, 24 h and 7 d), sales, listings, supply and holders. Use it for "top NFT collections" questions or to find a collection by name.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many collections to return (1-50, default 10). |
| query | string | – | Only collections whose name contains this text, or whose policy id starts with it. |
| sort | string | – | Ordering. |
No output schema declared.
No examples provided.
list_open_orders Open swap orders of a wallet ~104
Swap orders of a wallet that are still waiting at Minswap V2, SundaeSwap V3 or WingRiders V2 (unspent in the ledger right now), whichever app placed them: DEX, pool, amount sold, minimum to receive and when it was placed. Orders waiting at other DEXes are not listed; follow those with `get_swap_status`.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | Mainnet payment address (addr1…) of the wallet. |
No output schema declared.
No examples provided.
list_prediction_markets Prediction markets and their odds ~255
Prediction markets on Cardano (Bodega Market), read from the chain: each market's question, the probability its automated market maker currently gives YES and NO (percent), when trading ends, the funds in the market, traded volume and, once published, the outcome. Use it for "what are the odds of …" or "which prediction markets are open" questions. Amounts are in the market's payment token (ADA unless `paymentToken` says otherwise). Outcomes are published on chain by the Bodega team, not by a decentralised oracle; most markets are sports events. Odds are a market price, not a forecast you should present as fact: name the source and the time.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many markets to return (1-50, default 15). |
| query | string | – | Only markets whose question contains this text. |
| sort | string | – | Ordering. Default: deadline (soonest first for open markets, latest first otherwise). volume = all-time traded volume; activity = most recently traded. |
| status | string | – | open = trading now; awaiting = trading ended, no result published yet; resolved = result published, winners can claim; closed = wound up. |
No output schema declared.
No examples provided.
list_programmable_events Freeze, unfreeze and seizure history of programmable tokens ~226
What issuers of programmable tokens (CIP-113) have done, each with its transaction: wallets put on or taken off a block list (`freeze`, `unfreeze`), tokens moved out of a wallet by the issuer without the holder's signature (`third_party`: a seizure or forced transfer), mints and burns, pauses and other setting changes (`state_changed`), rule changes, new operators, registrations. Filter by token, by kind or by the wallet credential concerned. An empty list means none are indexed in the period the `coverage` field names, not that none happened before it.
| Name | Type | Req | Description |
|---|---|---|---|
| credential | string | – | Only events about this owner credential (56 hex): frozen, taken from, or given tokens. |
| kind | string | – | Only this kind of event. freeze/unfreeze = block-list changes; third_party = tokens moved by the issuer without the holder. |
| limit | integer | – | How many events to return (1-100, default 25). |
| token | string | – | Only events of this token: policy id or unit. |
No output schema declared.
No examples provided.
list_stake_pools Rank stake pools ~236
Ranked list of Cardano stake pools with ticker, live stake (ADA), saturation (percent), margin (percent), fixed cost (ADA per epoch), pledge (ADA), delegators, blocks this epoch, estimated yearly return at 100 % luck (percent) and, over its recent finished epochs, luck (blocks minted / blocks expected, percent) and the yearly return delegators got. Use it to compare pools or to find one by ticker or name.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many pools to return (1-50, default 10). |
| maxMarginPct | number | – | Only pools with a margin of at most this percent. |
| maxSaturationPct | number | – | Only pools at most this percent saturated (100 = full). |
| query | string | – | Ticker prefix, part of the name, or the start of a pool id. |
| sort | string | – | Ordering (margin, fixedCost and ticker ascend; the others descend). luck = recent blocks minted / expected, among pools expected to make at least a block an epoch; rosRecent = recent yearly return of… |
No output schema declared.
No examples provided.
list_tokens Rank Cardano tokens ~475
Ranked list of Cardano native tokens traded on DEXes, for questions such as "top tokens", "biggest gainers today", "trending now" or "new pairs". Prices are in ADA and USD, volume and liquidity in ADA (24 h), market cap in USD, changes in percent. `rank` (default) combines market cap with pool liquidity and is the best general ordering; `volume` is what the site calls Trending. The answer names the floors it applied (`minLiquidityAda`, `minHolders`).
| Name | Type | Req | Description |
|---|---|---|---|
| hideHighRisk | boolean | – | Leave out tokens the safety screen rates as high risk. |
| limit | integer | – | How many tokens to return (1-50, default 10). |
| minHolders | integer | – | Leave out tokens known to have fewer holders than this. Replaces the default floor of the ordering (100 for mcap and fdv); 0 = none. |
| minLiquidityAda | number | – | Leave out tokens with less pool liquidity than this many ADA (both sides of the pools). Replaces the default floor of the ordering; 0 = none. |
| order | string | – | Direction. Default: descending (age: ascending, youngest first). Ignored by rank, trending, new, gainers and losers. |
| page | integer | – | Page number, from 1. |
| period | string | – | Window of the volume, txns, change, gainers and losers orderings. |
| query | string | – | Only tokens whose ticker, name or unit starts with this text. |
| sort | string | – | Ordering. volume = traded volume over `period` (the site's Trending list); gainers/losers/change use the change of the USD price over `period` (24 h: change24hPct; change24hAdaPct is the change of th… |
No output schema declared.
No examples provided.
list_treasury_withdrawals Treasury withdrawals ~98
Treasury withdrawals approved (or proposed) through Cardano governance: totals paid out by year, what is still waiting, and a list of withdrawals with the epoch and date they were paid and their size in ADA.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many withdrawals to return (1-50, default 10). |
| status | string | – | paid = enacted, pending = open or ratified, rejected = expired or dropped. |
No output schema declared.
No examples provided.
plan_swap Swap plan with every fee (no trade is made) ~291
Plan a swap the way Realtap's own router places it: one order, or the amount split over several pools of Minswap V2, SundaeSwap V3 and WingRiders V2, with the expected and the minimum amount received at the given slippage, every fee in ADA (DEX batcher fees, interface fee, network fee), the refundable deposit, the price impact (percent) and the result net of fees. More exact than `get_swap_quote` (integer pool maths, fees included) but limited to those three DEXes. Nothing is built or signed: a person executes the plan at `swapUrl`; an agent that signs with its own key calls `build_swap_transaction`.
| Name | Type | Req | Description |
|---|---|---|---|
| amount | number | yes | Amount of tokenIn to sell, decimal-adjusted (100 = 100 ADA when tokenIn is ADA). |
| maxOrders | integer | – | Most orders the amount may be split over (1 = a single order). |
| slippagePct | number | – | How far the price may move against the trade before an order must not execute, in percent (1 = 1 %). |
| tokenIn | string | yes | What is sold: a token unit, or "lovelace" / "ADA" for ADA. |
| tokenOut | string | yes | What is bought: a token unit, or "lovelace" / "ADA" for ADA. |
No output schema declared.
No examples provided.
resolve_handle Resolve an ADA Handle ~88
Resolve an ADA Handle ($name, or sub@root for subhandles) to the address that currently holds it, with its stake address and whether a script (for example a marketplace listing) holds it. Use it before sending-related answers or to turn a $handle into an address for other tools.
| Name | Type | Req | Description |
|---|---|---|---|
| handle | string | yes | Handle with or without the leading $, e.g. "$snek". |
No output schema declared.
No examples provided.
search Search Cardano entities ~127
Find a Cardano token, liquidity pool, NFT collection, stake pool, ADA Handle, address, transaction, block or epoch by name, ticker or identifier. Use this first whenever you have a name or ticker rather than an exact id: each result names the tool to call next and the id to pass. Stake amounts in results are whole ADA.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many results to return (1-20, default 8). |
| query | string | yes | Name, ticker, `$handle`, address, pool id, policy id, transaction hash, block height or epoch number. |
No output schema declared.
No examples provided.
test_alert Send a test message to an alert target ~125
Queues a signed test message (event "test") to one delivery target, or to every target of one of your key's own rules, and waits a few seconds for the result: status sent, retry or dead with the HTTP status or error. A target can be tested a few times every 10 minutes. Needs an API key.
| Name | Type | Req | Description |
|---|---|---|---|
| ruleId | integer | – | Or: test every target of this rule. |
| targetId | integer | – | The delivery target to test (from `list_alerts` or the `webhook` block of `create_alert`). |
No output schema declared.
No examples provided.
what_changed What changed since a time ~237
Diff of the market since a time: tokens whose price moved by more than X %, tokens with a new first pool, new governance actions and large trades. Price moves cover at most the last 24 h (no older price snapshots), tokens below the liquidity floor are left out, and sections that could not be read are listed under `unavailable`. Also at /api/md/changes?since=.
| Name | Type | Req | Description |
|---|---|---|---|
| minChangePct | number | – | Smallest absolute price change in percent to list a token (default 10). |
| minLiquidityAda | number | – | Leave out tokens with less pool liquidity than this many ADA (default 10,000). |
| minTradeAda | number | – | Smallest trade in ADA to count as large (default 100,000; at least 1,000 is used). |
| since | string | yes | ISO 8601 time (2026-10-21T08:00:00Z), a date, or an age such as 90m, 6h or 2d (at most 30 days back; the diff itself covers at most the last 7 days). |
No output schema declared.
No examples provided.
How do I install the Realtap MCP server?
Realtap is a hosted endpoint at https://realtap.app/api/mcp, 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 · realtap.app
claude mcp add --transport http csteenkamp-realtap 'https://realtap.app/api/mcp'
What is the Realtap MCP server?
Realtap is an MCP server listed in the public MCP registry as io.github.CSteenkamp/realtap. Live Cardano data (token prices, DEX trades, pools, wallets, NFTs, staking, governance). Read-only. This page covers its hosted endpoint (https://realtap.app/api/mcp).
Is the Realtap MCP server safe to use?
Realtap scores 67 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 Realtap MCP server expose?
Realtap exposes 82 tools: search, list_tokens, get_token, get_token_candles, get_pool, and 77 more. Their descriptions and schemas cost roughly 12,562 tokens of context every time the server is loaded.
Does the Realtap MCP server require authentication?
No. We connected to Realtap without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Realtap MCP server still maintained?
Realtap is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.