
xrpldashboard MCP server
Which servers in the official MCP registry are xrpldashboard's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-21
- Registry namecom.xrpldashboard/xrpldashboard-mcpverified in the MCP registry
The registry name sits under xrpldashboard.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-21
- Tools19
- Server calls itselfxrpldashboard-mcp
- Server version1.30.0
- Protocol version2025-06-18
On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 216 ms.
- Its tools do none of the product's use cases we checked: Look up an XRPL address's balances and recent activity; Inspect price oracle feeds published directly on the ledger.
- Checked on 4 of the 7 days it takes to judge reliability.
Once connected
- Parameters are untyped or undescribed in 9 of 19 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
- What an agent can do with it0 of 2 use cases
- Answeredmeasuring4 of the 7 daily checks it takes to print a share
- Median first answer256 ms
- Space in an agent's context≈ 1,890 tokensthe definitions of all its tools (19), which an agent carries on every turn
- Tool definitionsB · 75 of 100
- Typed results0 of 19 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 9 of 19
- Not saying whether it only reads or can destroy: 19 of 19
What an agent can do with it
- cannot · Look up an XRPL address's balances and recent activity
- not sure · Check a token issuer's identity claims before partnering
- cannot · Inspect price oracle feeds published directly on the ledger
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
get_ledger_statsReturn the last-validated ledger stats (index, close time, server state, load factor, complete range, build). Wrapped in the xrpldashboard proof envelope; envelope source is derived from the actual URL host (`local_rippled` for loopback /…
get_amendment_statusReturn the current amendments state (enabled / in-flight / superseded / unrecognized-enabled) with `cross_check_status` derived from the responding node's feature-RPC vs Amendments ledger-object concurrence. Wrapped in the proof envelope.
get_unl_statusReturn the current UNL composition (both published lists, overlap, expiry-days). Honest-partial when a list fetch fails. Wrapped in the proof envelope.
get_whale_eventsReturn the last N XRP-denominated whale events + tagged-watchlist events (trustset excluded). Same feed the homepage globe pulse reads. Wrapped in the proof envelope.
get_whale_watchlistReturn the last N tagged-watchlist events (type='tagged'), floored at TAGGED_XRP_FLOOR_DROPS for XRP-denominated rows. Wrapped in the proof envelope.
get_rlusd_supplyReturn the current cross-chain RLUSD supply (Ethereum + XRPL) from the same PG mirror /rlusd reads. Honest-partial when either chain errored. Wrapped in the proof envelope.
get_rlusd_flow_24hReturn the last finalized 24h XRPL net-change from rlusd_supply_history. freshness_contract='finalized_only' is the machine-readable form of the R1/R2 finalized-window rule. cross_check_status derived from stored vs supply-diff pair…
get_amm_poolReturn the single ranked-pool row for one AMM account from the amm_ranked_pools snapshot. Raises when the account is absent (unranked, below thresholds, or newer than the last snapshot). Wrapped in the proof envelope.
get_amm_top_by_tvlReturn the top-N ranked AMM pools by tvl_usd from the same snapshot /pools reads. NULL-tvl rows sort last. Wrapped in the proof envelope.
get_token_attestationReturn the attestation tier (verified / self-described / null) for one (currency, issuer) pair. Data payload includes `dispute_contact_url` — first tool to name a third party. Wrapped in the proof envelope.
get_rwa_familiesReturn every rwa_family row with attributed pool count. Data payload includes `dispute_contact_url`. Wrapped in the proof envelope.
get_rwa_poolsReturn every attributed RWA pool with provenance + TVL. Data payload includes `dispute_contact_url`. Wrapped in the proof envelope.
get_mpt_snapshotReturn the MPT snapshot dict (issuances / by_class / total). Not third-party-naming — no dispute_contact_url. Wrapped in the proof envelope.
get_signed_snapshotReturn the Ed25519-signed daily snapshot for `date_str` (ISO YYYY-MM-DD) wrapped in the proof envelope. Absence raises — the walker has not produced this date yet, or the date predates the chain start.
verify_snapshot_signatureStateless verification: re-derive the leaf hash, check the Ed25519 signature against the pinned pubkey, check the audit path against the claimed chain root. Accepts full MCP envelope or bare signed payload. Wrapped in the proof envelope.
get_tokensReturn the top-N tokens by trades_30d, joined against attestation tier + warning flags. Mirrors /tokens.json's data path (token_category_current JOIN token_facts). Third-party- naming — data payload includes `dispute_contact_url`. Wrapped…
get_whalesReturn the whales_summary rollup cells (per-tier × per-filter body metadata). Mirrors /whales.json. Live stream on wss://wss.xrpldashboard.com — this tool returns generation stats + body length, not the live payload. Third-party-naming…
get_poolsReturn AMM pools ranked by TVL, broader list contract than get_amm_top_by_tvl (default limit=50 vs 10). Mirrors /pools.json. Same source snapshot (amm_ranked_pools). Third-party-naming — data payload includes `dispute_contact_url`…
get_amendmentsReturn the amendments block with per-amendment vote tallies. Mirrors /amendments.json. Distinct from get_amendment_status (state-only) — this tool adds live vote counts vs UNL-threshold per amendment. Not third-party-naming. Wrapped in…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"xrpldashboard-mcp": {
"type": "http",
"url": "https://mcp.xrpldashboard.com/mcp?ref=anthropic"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http xrpldashboard https://mcp.xrpldashboard.com/mcp?ref=anthropicclaude.ai, ChatGPT and other clients: add https://mcp.xrpldashboard.com/mcp?ref=anthropic as a custom connector in the settings.
OpenAPI spec
12 paths, read 2026-10-21. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.