Dexpaprika MCP vs X402 Trust MCP
A side-by-side look at the Dexpaprika MCP and X402 Trust MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Dexpaprika MCP for finance & fintech work as a local process; choose X402 Trust MCP for finance & fintech as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Dexpaprika MCP when
- You need dedicated capabilities in the Finance & Fintech domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You have the keys it needs:
DEXPAPRIKA_API_KEY, DEXPAPRIKA_API_BASE_URL. - You want tools like
getKeyStatus, getNetworks, getCapabilities.
Choose X402 Trust MCP when
- You need dedicated capabilities in the Finance & Fintech domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You have the keys it needs:
X402_PRIVATE_KEY, X402_MAX_USD. - You want tools like
x402_ecosystem_stats, x402_trust_leaderboard, x402_trust_preview.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Finance & Fintech | Finance & Fintech |
| Quality signal | 68/100 · Great | 64/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | No auth required |
| Pricing | Free | Freemium |
| Required env vars | DEXPAPRIKA_API_KEYDEXPAPRIKA_API_BASE_URL | X402_PRIVATE_KEYX402_MAX_USD |
| Verified owner | Community listing | Community listing |
| GitHub stars | 108 | 1 |
| Directory activity | 2 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | 17 | 13 |
| Full listing | View Dexpaprika MCP | View X402 Trust MCP |
Tools & capabilities
Dexpaprika MCP tools 17
getKeyStatusReport whether this server is sending an API key and which plan the API sees. Use when calls are being rate limited or refused, or when the user asks whether their DexPaprika key is working. Takes no arguments and reads no market data.getNetworksList every blockchain network DexPaprika indexes, each row carrying its network id (slug), 24h volume, transaction count, and pool count. Read-only and keyless. Start here (or getCapabilities) to get the exact network slug that nearly every other tool requires as its 'network' argument. Use for 'which chains do you support?', 'is Base/Solana/Arbitrum covered?', or 'what is the slug for Polygon?'. Returns the full array with no pagination or sorting; takes no parameters beyond a short rationale. For platform-wide totals rather than a per-network list use getStats.getCapabilitiesGet the static agent onboarding guide for this server: supported workflows, network name synonyms (mapping words like 'eth' to the canonical slug 'ethereum'), recommended call sequences, and common pitfalls. Read-only and keyless. Read it once at the start of a session before your first query, or when asked 'how do I use this API?', 'what order should I call things in?', or 'which slug maps to eth?'. This returns onboarding docs, not live market data; for the actual list of network slugs use getNetworks, and for coverage totals use getStats. Takes no parameters beyond a short rationale.getNetworkDexesList the DEXes (exchanges) operating on one network, such as Uniswap on ethereum or Raydium on solana, returned under 'dexes' with page_info (page, total_pages). Read-only and keyless. Use for 'which DEXes are on Base?', 'does Solana have Orca?', or to get a dex id to feed into getDexPools. Scope is a single network; call getNetworks first for the slug. Params: network (required slug); limit (default 10, max 100); page (default 1, 1-indexed); sort_by (only 'pool'; legacy alias order_by); sort_dir 'asc' or 'desc' (default 'desc'; legacy alias sort).getNetworkPoolsGet the top liquidity pools across a whole network, ranked by 24h volume by default, returned under 'results' with has_next_page and next_cursor. Read-only and keyless. This is the primary chain-wide pool discovery tool. Use for 'biggest pools on ethereum', 'top trading pairs on Base', or 'most active pools on Solana'. Narrow to one exchange with getDexPools, or apply numeric/time filters with getNetworkPoolsFilter. Params: network (required slug); limit (default 10, max 100); cursor (pass previous next_cursor to page); sort_by (default 'volume_usd_24h', canonical *_24h fields, alias order_by); sort_dir 'asc' or 'desc' (default 'desc', alias sort).getDexPoolsGet the pools belonging to one specific DEX on one network, e.g. all Uniswap v3 pools on ethereum. Proxies /networks/{network}/pools/search with a dex_name filter (the old /networks/{network}/dexes/{dex}/pools endpoint was removed): rows come back under 'results' with cursor pagination (has_next_page + next_cursor), and the 24h volume field is volume_usd_24h. Read-only and keyless. Narrower than getNetworkPools (a single exchange, not the whole chain). Use for 'show me Raydium pools', 'top pairs on PancakeSwap', or 'liquidity on Orca'. Get the dex id from getNetworkDexes or search first, and pass that response's dex_id field ('uniswap_v3'), matched case-insensitively. Do not pass its dex_name field ('Uniswap V3'): a human display name returns HTTP 200 with an empty results[] rather than an error, so an empty answer here usually means the wrong form of the name was sent. Params: network (required slug); dex (required id, e.g. 'uniswap_v3'; the REST API calls this query parameter dex_name); limit (default 10, max 100); cursor (pass previous next_cursor to page); sort_by (default 'volume_usd_24h', canonical *_24h fields, short legacy names still accepted, alias order_by); sort_dir 'asc'/'desc' (default 'desc', alias sort). The old page number is gone: page 2 and above return an error pointing at cursor.getNetworkPoolsFilterGet pools on one network filtered by numeric thresholds, returned under 'results' with has_next_page and next_cursor. Read-only and keyless. Choose this over getNetworkPools when the user gives numeric constraints or a time window. Use for 'pools over $1M liquidity on Base', 'pools created in the last 24h', or 'high-volume low-liquidity pairs'. Optional filters (AND-combined): volume_24h_min/max, volume_7d_min/max, liquidity_usd_min/max, txns_24h_min, created_after/created_before (Unix timestamps). Also network (required); limit (default 50, max 100); cursor to page; sort_by (default 'volume_usd_24h', alias order_by); sort_dir asc/desc (default 'desc', alias sort).getPoolDetailsGet the full current snapshot for one pool by address: its two tokens, current price, liquidity/TVL, 24h volume, and transaction counts, returned as a single pool object (not a list). Read-only and keyless. Use after search or getNetworkPools surfaces a pool, or for 'price/TVL of this pool?' or 'details for pool 0x...'. Returns live values only; for historical candles use getPoolOHLCV, and for the raw swap feed use getPoolTransactions. Params: network (required slug); pool_address (required, e.g. '0x88e6a0c2ddd26feeb64f039a2c41296fcb3f5640'); inversed (optional bool, default false, flips the token price ratio to token1/token0).getPoolOHLCVGet historical OHLCV candles (open, high, low, close, volume) for one pool over a time range, returned as a time-series array. Read-only and keyless. Use for 'price history of this pair', 'hourly chart for the last week', 'candles since Jan 1', or backtesting; for the single current price use getPoolDetails instead. Params: network (required); pool_address (required); start (required; Unix timestamp, RFC3339, or yyyy-mm-dd); end (optional, capped to 1 year after start); interval one of '1m','5m','10m','15m','30m','1h','6h','12h','24h' (default '24h'); limit (default 100, max 366 candles); inversed (optional bool, default false).getPoolTransactionsGet one pool's recent individual swap transactions, newest first, returned under 'transactions' (paginate with page, or a cursor). Read-only and keyless. These are per-trade records, not aggregated candles (use getPoolOHLCV) or a summary snapshot (use getPoolDetails). Use for 'recent trades on this pool', 'who swapped in the last hour', or 'raw transaction feed'. Params: network (required); pool_address (required); limit (default 10, max 100); page (default 1, up to 100 pages) or cursor (a transaction id); from (optional Unix seconds, inclusive, capped to the last 7 days); to (optional Unix seconds, exclusive, must be after from).getTokenDetailsGet one token's data and metadata by contract address on one network: multi-timeframe price and volume metrics, plus name, website, Twitter, and Telegram links, returned as a single token object. Read-only and keyless. Use for 'price and volume for 0x... on Base' or 'tell me about this token'. If you only have a symbol like WETH, call search first to resolve the address and network. For many tokens' prices at once use getTokenMultiPrices; for the pools holding this token use getTokenPools. Params: network (required slug); token_address (required contract address, e.g. 'JUPyiwrYJFskUPiHa7hkeR8VUtAeFoSYbKedZNsDvCN' on solana).getTokenPoolsGet the liquidity pools that contain a specific token on one network, returned under 'results' with has_next_page and next_cursor. Read-only and keyless. Use for 'which pools hold WETH on ethereum?' or 'liquidity venues for 0x...'. Network-scoped, so run search first if unsure of the network; unknown addresses return empty results, not an error. For the token's own price use getTokenDetails. Params: network (required); token_address (required); limit (default 10, max 100); cursor to page; sort_by (default 'volume_usd_24h', alias order_by); sort_dir asc/desc (default 'desc', alias sort). Extra params such as inversed or paired_token_address are unsupported and error.- +5 more on the listing page
X402 Trust MCP tools 13
x402_ecosystem_statsFree aggregate snapshot of the entire x402 ecosystem (Base + Solana): how many endpoints are listed/active/delisted, what fraction are reachable and spec-compliant, and real on-chain USDC settlement volume / receivers / payers over the last 30 days. Use this to gauge market health before transacting.x402_trust_leaderboardFree top-25 most trustworthy x402 hosts (providers), ranked by a deterministic trust score. Each host's score is the probe-weighted mean of its listed endpoints' scores, so providers are judged by their whole measured surface instead of one provider flooding the board with path variants. The per-endpoint score blends uptime, envelope compliance, latency, age, on-chain settlement activity and price stability. Latency is measured from a single EU vantage point and includes network distance to the endpoint (so it is only lightly weighted). Use this to discover reliable paid endpoints.x402_trust_previewFREE showcase of what x402_trust_score returns. You do NOT choose the endpoint: this returns the COMPLETE paid-grade trust report (every field — exact score, scoreRange, full component breakdown, advertised price, on-chain settlement figures, all flags) for THREE endpoints picked from the current population — the best-scored, the median, and the worst-scored ('samples' each carry 'role', 'populationRank', and the full 'report'). Use it to see exactly what the paid output looks like across the entire quality range BEFORE paying. It cannot score an endpoint you choose — to evaluate YOUR OWN endpoint, call x402_trust_score (paid). Takes no arguments.x402_trust_scoreTrust score (0-100, grade A-F, or '?' when unmeasured) for a SPECIFIC x402 endpoint -- cataloged or not (uncataloged endpoints are live-probed on first query, auto-adopted, score carries a low-confidence first-contact flag). PLUS a machine-readable verdict ('recommendation': proceed|caution|avoid|parameterize|unverified|not-payable|free), the advertised price ('advertised.amountUsd'), a confidence-adjusted band ('scoreRange'), and structured flags ('flagsDetailed' with code/severity/message; any severity 'error' means avoid). The 'parameterize' verdict (with 'templated':true) means the resource URL still contains an unresolved template placeholder (e.g. {slug}, :slug or %7B…%7D) but we DO have a real signal (scored probes or a discovery fallback): substitute a valid value first, then the health metrics apply to the resolved URL. The 'unverified' verdict (grade '?') means we have NO measurement at all (every probe excluded and no discovery payment requirements to fall back on): it is unknown, not bad, so verify the endpoint yourself before paying. The 'not-payable' verdict (grade '?') means the URL answers a 402 with an EMPTY accepts[] (an auth/API-key gate such as sign-in-with-x), or answers a bare 401/403 with no payment envelope, so it is not an x402-payable resource at all and there is nothing to settle. The 'free' verdict (grade '?') means the endpoint answers plain requests with data (HTTP 200, no payment envelope) and has never presented a payment challenge: a free resource with no payment flow to grade, unmeasured by design, not a negative verdict. For templated per-item endpoints that ARE payable, a varying payTo/price is EXPECTED (one wallet/price per item): the report surfaces 'stats.payToVaries'+'payToDistinct30d' and 'advertised.amountRange30d' as a 'payto-varies'/'price-varies' note rather than a 'payto-changed-recently' hijack error; always pay the payTo in the live 402 quote, not a cached listing. 'stats.scoredProbes30d' vs 'stats.excluded30d' show how many probes actually back the score. When the endpoint's host completed provider verification (domain control proven with a public key in /.well-known/x402-trust.txt plus a confirmed contact email), the report carries 'providerVerified': true, 'providerName' (the provider's own organization name) and 'providerContact' (the confirmed contact address); verified endpoints also carry the 'provider-verified' info flag; verification never changes the score. Includes the full component breakdown, the provider-advertised 'serviceName' and 'description' (unverified provider claims, shown next to our independent metrics), and 30-day on-chain stats. Note: 'stats.avgLatencyMs' is measured from a single EU vantage point and includes network distance to the endpoint (see 'stats.latencyVantage'), so a geographically distant endpoint reads slower even when its server is fast. One call answers WHETHER and at WHAT PRICE to use an endpoint. Call this BEFORE paying an unknown x402 endpoint to avoid dead, fraudulent, or recently-hijacked services. Each paid call also refreshes the endpoint's free public snapshot (page, badge, card) immediately. Pay-per-call over x402; auto-pays if a wallet is configured, otherwise returns the price quote.x402_endpoint_historyRaw observation time-series for a SPECIFIC x402 endpoint: listing/delisting/relisting events, advertised price changes, payTo changes, and probe results over the requested window (1-90 days). Each probe carries 'ts', 'ok', 'latencyMs', 'amount' plus its outcome 'status' (success, dns_error, timeout, http_error, ...), 'httpStatus', an 'error' detail and an 'excluded' flag; excluded probes carry no endpoint signal (rate limits, unresolved URL templates, resolver outages on our side) and never count as downtime. A 'probeSummary' aggregates the window: counts by status, longest failure streak, per-day failure breakdown. Per-probe 'latencyMs' is measured from a single EU vantage point and includes network distance to the endpoint. Pay-per-call over x402; auto-pays if a wallet is configured, otherwise returns the price quote.x402_find_alternativesGiven an x402 endpoint URL, returns the top semantically-similar endpoints (matched on advertised purpose via description embeddings) that currently OUT-SCORE it on the deterministic trust score. Use this to route away from a mediocre/dead/expensive endpoint toward a more reliable, better-settled one serving the SAME function — e.g. before paying, check if a higher-graded equivalent exists. Each alternative carries its trust 'score', 'grade', 'recommendation', cosine 'similarity' (0-1), 'amountUsd' price, 'priceCeiling' (true when amountUsd is an x402 'upto' authorization ceiling, not a fixed per-call price), and a free 'endpointPage' URL. It also carries 'hasDescription': false means the endpoint advertises no description, so its similarity was computed from service name + URL path tokens only, a weaker signal worth more skepticism than a description-based match. Same-host siblings and 'avoid'-flagged endpoints are excluded. An empty 'alternatives' array is a valid answer meaning nothing beats the subject. Similarity is independent of latency/geography. Pay-per-call over x402 (~$0.005); auto-pays if a wallet is configured, otherwise returns the price quote.x402_semantic_searchFree-text SEMANTIC SEARCH across the entire monitored x402 endpoint catalog. Given a plain-language query (e.g. "weather forecast", "image generation", "EVM gas price oracle"), returns the up to 25 endpoints whose advertised purpose is semantically closest. Ranking is deterministic and fully specified: cosine similarity bucketed to whole percentage points first (80.3% and 80.5% are the same bucket, so sub-percent noise never outranks a better endpoint), then trust score (0-100), then described-before-undescribed, then endpoint id as a stable final tiebreak. Matches below a 0.5 cosine-similarity floor are dropped entirely, so a query can return fewer than the requested limit (or none). Endpoints that advertise no description are still matched: they are embedded from their service name and URL path tokens instead of a written description (host name as a last resort). The EXACT effect of a missing description: no fixed point deduction, and no direct similarity malus either; the only deterministic penalty is the described-before-undescribed tiebreak (at equal similarity bucket AND equal trust score, a described endpoint ranks first). Beyond that the effect is purely indirect: the shorter fallback text typically yields lower cosine similarity than a prose description, so undescribed endpoints tend to land in lower similarity buckets, by a query-dependent (never fixed) amount. Use this for DISCOVERY: find candidate endpoints for a capability before checking any of them in depth. Each match carries 'id', 'resource' URL, trust 'score' (0-100), 'grade' (A-F), raw cosine 'similarity' (0-1; ranking buckets it to whole percents), 'amountUsd' price (null when not advertised), 'priceCeiling' (true when amountUsd is an x402 'upto' authorization ceiling, not a fixed per-call price), 'description' when advertised, and a free 'endpointPage' URL. 'score'/'grade' are null for endpoints not yet scored. Deliberately NO verdict/recommendation or flag detail: the per-endpoint trust report (x402_trust_score) carries those. Pay-per-call over x402 (~$0.001); auto-pays if a wallet is configured, otherwise returns the price quote.x402_trust_bulkScore up to 500 x402 endpoints in a SINGLE paid call. Returns the authoritative full-density trust score (0-100, grade A-F or '?' when unmeasured, recommendation proceed|caution|avoid|parameterize|unverified|not-payable|free), confidence, `probed_at`, `computed_at`, and a `recomputed` flag for each requested resource. Cache rows older than ~15 minutes are recomputed on-demand from the latest stored probes and settlements (no live network re-probe), so bulk scores typically reflect reality within minutes. Each recomputed row also refreshes that endpoint's free public snapshot (page, badge, card) immediately. Per-request recompute limits apply: at most 50 endpoints / 8 seconds are recomputed; the response includes `recompute_limit_hit` and `recompute_limit` so you know if the cap was reached. The smallest tier that fits your request is selected automatically (10/50/100/200/500 endpoints; ~$0.045/$0.20/$0.325/$0.40/$0.50). Resources not in our observation set return `found:false`; you still pay for the batch. For a fresh live probe, use `x402_trust_score`. Pay-per-call over x402; auto-pays if a wallet is configured, otherwise returns the price quote.x402_watch_createStart monitoring ONE x402 endpoint for 30 days. Get alerted on changes that break autonomous payment: payTo changes (possible takeover/rug — but for a templated per-item endpoint a payTo move is expected variance and is delivered as severity 'warn', not 'critical'), price changes, asset/network changes, 402-spec regressions, delisting, and liveness down/recovered. A self-healing endpoint that repeatedly blips is auto-detected as `liveness_flapping` and its individual down/up alerts are coalesced into a single flapping notice (plus one 'stopped flapping' notice when it stabilizes) so you are not spammed. Returns a one-time bearer secret + poll URL + renew URL + edit URL + cancel URL + machine-readable `next_steps`. Use x402_watch_events to poll the append-only log, or configure push delivery to one or more signed HTTPS webhooks and/or Slack/Discord incoming webhooks (max 5 each). `webhook_url`/`slack_url` accept a single URL string or an array of URLs. All URLs are connection-tested BEFORE payment — unreachable URLs are rejected with no charge (retry with a corrected URL). On success the response reports per-URL delivery in `delivery.connection_test`. Webhook signature: `x-signature` = 'sha256=' + HMAC-SHA256(body) keyed by hex(sha256(secret)), NOT the raw secret. Pay-per-call over x402 (~$0.20); auto-pays if a wallet is configured, otherwise returns the price quote.x402_watch_eventsRead the append-only event log for an active x402 watch. Returns two streams: `events` (endpoint changes — payTo/price/asset/spec/delisting/liveness) and `watch_events` (lifecycle feedback — created/edited/cancelled/renewed/expiring/expired). Nothing between two polls is lost. Provide the watch_id and the one-time secret from x402_watch_create. Advance `since` with the returned `next_cursor` (endpoint events) and `watch_since` with `watch_events_cursor` (lifecycle events). Cursors/ids are GLOBAL sequences shared across watches (a watch's first event id may be >1); always page by the returned cursor rather than assuming they start at 1. Cancelled watches remain READABLE until expires_at (no new events accrue). If the watch has push delivery, still poll to reconcile missed webhooks.x402_watch_editEdit an active watch: change webhook/Slack URLs, liveness sensitivity, or subscribed events. Bearer-authed with the secret from x402_watch_create. Newly-added URLs are connection-tested before the change is persisted; if any new URL fails, the existing config is unchanged. Delivery fields are full-replace per channel (omit to leave that channel unchanged). Returns the updated watch view.x402_watch_cancelSoft-cancel a watch immediately: no new events accrue, but the event log stays READABLE via x402_watch_events until the original expires_at (cancel is not a delete). Probing drops back to normal cadence as soon as no active watches cover the endpoint. Bearer-authed with the secret from x402_watch_create. Free and idempotent.- +1 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Dexpaprika MCP
{
"mcpServers": {
"coinpaprika-dexpaprika-mcp": {
"command": "npx",
"args": [
"dexpaprika-mcp@latest"
],
"env": {
"DEXPAPRIKA_API_KEY": "YOUR_DEXPAPRIKA_API_KEY_HERE",
"DEXPAPRIKA_API_BASE_URL": "YOUR_DEXPAPRIKA_API_BASE_URL_HERE"
}
}
}
}
X402 Trust MCP
{
"mcpServers": {
"x402-trust-mcp": {
"command": "npx",
"args": [
"-y",
"x402-trust-mcp"
],
"env": {
"X402_PRIVATE_KEY": "YOUR_X402_PRIVATE_KEY_HERE",
"X402_MAX_USD": "YOUR_X402_MAX_USD_HERE"
}
}
}
}
Frequently asked questions
Dexpaprika MCP is categorized under Finance & Fintech and uses a local stdio subprocess. X402 Trust MCP belongs to Finance & Fintech and uses a local stdio subprocess. Pick Dexpaprika MCP for finance & fintech work and X402 Trust MCP for finance & fintech.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Dexpaprika MCP is listed as free. Auth: no auth required. X402 Trust MCP is listed as freemium — a free tier with paid plans. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add coinpaprika-dexpaprika-mcp and x402-trust-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Dexpaprika MCP has a quality signal of 68/100 (Great) with 2 views, 0 installs and 108 GitHub stars. X402 Trust MCP has 64/100 (Good) with 4 views, 0 installs and 1 GitHub stars.