Model Context Protocol (MCP) server for freee API integration
AfterFees 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
Crypto funding-rate arbitrage across 50 exchanges, net of fees and order-book slippage. Read-only.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http afterfees-mcp https://afterfees.xyz/mcp
# 2 — ask your agent for something these tools do
# best_opportunities, coin_overview, pair_breakdown and 24 more
AfterFees 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 afterfees-mcp https://afterfees.xyz/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Nothing is required, but it can take Authorization header (Optional. "Bearer <your AfterFees Pro token>" for your own size, every tool and Pro limits. Without it: the anonymous tier.) if you want to set it.
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.
27 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.
Ranked funding-rate arbitrage pairs (long one market, short another) with the net result after taker fees and order-book slippage at your size, max size, breakeven, settled 7-day replay, tier (actionable / watch) and reasons.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| notional | number | no | Position size per side in USD (default 10000) |
| holding_hours | number | no | Holding period in hours (default 168 = 7 days) |
| mode | string | no | perp = perp vs perp, spot = buy spot + short perp, rev = borrow-and-sell spot + long perp |
| actionable_only | boolean | no | Only pairs that pass every check right now (live books, positive net, capacity) |
| limit | integer | no | — |
| base | string | no | Only this coin (optional) |
Funding rate of one coin on every exchange (rate, interval, APR, predicted, OI, volume, settled 7-day sum) plus its best pairs, net after fees and slippage at your size.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| base | string | yes | Coin or ticker, e.g. BTC, ETH, SOL |
| notional | number | no | Position size per side in USD (default 10000) |
Full calculation of one pair: funding per leg and settlement count, taker fees, order-book VWAP and slippage per trade, carry, net, net if rates halve, breakeven, capacity, settled 7/30-day replay. pair_key comes from best_opportunities or coin_overview. Needs a Pro API token (Authorization: Bearer arb_…); not available on the anonymous tier.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pair_key | string | yes | pair_key from another tool |
| notional | number | no | Position size per side in USD (default 10000) |
| holding_hours | number | no | Holding period in hours (default 168 = 7 days) |
Current perpetual funding rates (gross, before costs). With base: that coin on every exchange, highest first. Without: the top N markets by absolute APR (OI filter applies).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| base | string | no | Coin (optional) |
| limit | integer | no | — |
| min_oi_usd | number | no | Skip markets with less open interest (top-N mode only) |
Margin borrow rates per coin and exchange (VIP0, current and 24 h / 7 d averages, limits, inventory) with the most negative perp funding: the two halves of a reverse spot-perp carry.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| base | string | no | Coin (optional) |
| limit | integer | no | — |
Pendle Boros markets: the fixed funding rate you can lock (net of Boros fees and fill at your size) against the term-matched floating benchmark, advantage, win rate, capacity. side=short locks an income, side=long locks a cost.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| side | string | no | — |
| base | string | no | Coin (optional) |
| notional | number | no | Position size per side in USD (default 10000) |
| limit | integer | no | — |
Taker fee + order-book slippage to buy or sell a given USD size of one coin on every exchange (perps and spot), cheapest first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| base | string | yes | Coin or ticker, e.g. BTC, ETH, SOL |
| size_usd | number | no | — |
Spot or perp against a dated future held to delivery, on one exchange or across two (perp on one, future on another), and two same-day futures on different exchanges: net to expiry after fees and slippage at your size, net APR, basis APR, max size, tier and reasons.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| base | string | no | Coin (optional) |
| notional | number | no | Position size per side in USD (default 10000) |
| actionable_only | boolean | no | — |
| scope | string | no | same exchange or cross-exchange rows only (optional) |
| limit | integer | no | — |
Buy a coin on one exchange, withdraw it on a network both exchanges share (same chain and contract, never matched by ticker), sell on another: real-transfer net after taker fees, order-book slippage and the withdrawal fee at your size, pre-funded net, capacity at net >= 0 / 0.3% / 1%, arrival estimate, hedge cost on a perp, status and reasons. view=traps lists spreads that exist only because depos
| Parameter | Type | Required | Notes |
|---|---|---|---|
| base | string | no | Coin (optional) |
| notional | number | no | Size in USD (Pro; free uses 10000) |
| include_hedge | boolean | no | — |
| view | string | no | — |
| status | string | no | — |
| limit | integer | no | — |
Funding actually settled on both legs over 7 / 30 / 90 / 180 / 365 days, applied to today's orientation at your size: net after the four trading costs, max drawdown, negative days, daily sign flips, how far back each exchange's history reaches. Ranges beyond 7 days need Pro.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pair_key | string | yes | pair_key from another tool |
| range | string | no | — |
| notional | number | no | Position size per side in USD (default 10000) |
Annualised basis of every delivery future of one coin on every exchange we cover, next to perp funding.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| base | string | yes | Coin or ticker, e.g. BTC, ETH, SOL |
Taker fee plus order-book slippage to enter $10k / $100k / $1M long and short on one exchange's biggest markets, in basis points.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| venue | string | yes | exchange id, e.g. binance |
| limit | integer | no | — |
Whether AfterFees data is live right now, which exchange feeds are down, and availability over 1 / 7 / 30 / 90 days.
No parameter schema on file.
The two orders to place by hand for one pair: action, exchange, symbol, quantity in the exchange's own unit (contracts where one contract is not one coin), notional, assumed leverage and a link to each contract's trading page (no referral parameters). AfterFees never trades.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pair_key | string | yes | pair_key from another tool |
| notional | number | no | Position size per side in USD (default 10000) |
Net after fees and slippage of one live pair held 8 h, 1 d, 3 d, 7 d and 30 d, optionally with your own assumed funding rate per leg (percent per funding period, keyed by instrument_id).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pair_key | string | yes | — |
| notional | number | no | Position size per side in USD (default 10000) |
| assumed_rates_pct | object | no | {instrument_id: rate per period in %} (optional) |
Net, net APR, breakeven and funding-halved case for two legs you describe (no live data): each leg {side: long|short, rate_pct per period, interval_hours, taker_bps, first_in_hours?}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| legs | array | yes | — |
| notional | number | no | Position size per side in USD (default 10000) |
| holding_hours | number | no | Holding period in hours (default 168 = 7 days) |
| slippage_bps | number | no | — |
| leverage | number | no | — |
Locked net (income) or cost APR on Pendle Boros at an implied APR you give, after the taker and settlement fees and the entry cost, its advantage over a floating APR you expect and the break-even floating rate. Percent inputs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| side | string | no | — |
| rate_pct | number | yes | — |
| days | number | yes | — |
| notional | number | no | Position size per side in USD (default 10000) |
| taker_pct | number | no | — |
| settle_pct | number | no | — |
| entry_usd | number | no | — |
| floating_pct | number | no | — |
Buy on exchange A, withdraw, sell on exchange B at prices you give: real-transfer and prefunded net, break-even premium. Fees in percent, withdrawal fee in coins.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| buy | number | yes | — |
| sell | number | yes | — |
| amount | number | no | — |
| fee_a_pct | number | no | — |
| fee_b_pct | number | no | — |
| withdraw_coin | number | no | — |
| usdt_back | number | no | — |
| trips | number | no | — |
Detail of one Boros market (id from fixed_vs_floating): fixed rate at your size net of fees, floating benchmarks, advantage, win rate, capacity, reasons.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| market_id | integer | yes | — |
| side | string | no | — |
| notional | number | no | Position size per side in USD (default 10000) |
Lock funding on Boros against a delivery future of the same maturity: implied APR vs basis APR, net after fees and slippage at your size.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| notional | number | no | Position size per side in USD (default 10000) |
| limit | integer | no | — |
Every exchange AfterFees reads: kind, fully calculated or watch-only, status, markets, taker / maker fee, open interest, 24 h volume.
No parameter schema on file.
One exchange: fees and their source, funding intervals, open interest, volume, highest and lowest funding and its best after-fee pairs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| venue | string | yes | exchange id, e.g. binance |
Coins with a perp on two or more exchanges: exchange count, open interest, highest and lowest funding APR and the best after-fee pair.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| group | string | no | — |
| limit | integer | no | — |
How AfterFees' daily top picks actually did: predicted net vs net realised from settled funding over the hold, hit rate, mean error, latest picks.
No parameter schema on file.
Tokens our exchanges list with a verified contract on Ethereum, BNB Chain, Base, Arbitrum or Solana whose DEX price is more than 1% away: net at $1k / $5k / $10k after aggregator price impact, swap gas, the token transfer gas and the exchange's withdrawal fee, status and reasons. Pro. Needs a Pro API token (Authorization: Bearer arb_…); not available on the anonymous tier.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| base | string | no | Token (optional) |
| limit | integer | no | — |
Candles of (A − B) / B between any two instruments (book mids where stored, else marks). Free: 1 h candles and longer over up to 7 days; Pro: 1 m and up, up to 365 days.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| leg_a | string | yes | instrument id, e.g. binance:um:BTCUSDT |
| leg_b | string | yes | instrument id |
| candle | string | no | — |
| days | integer | no | — |
| executable | boolean | no | — |
Your positions across the read-only exchange keys connected to your AfterFees account, grouped into hedges: delta drift, distance to liquidation, funding received, issues. Needs a Pro account token; AfterFees only accepts read-only keys. Needs a Pro API token (Authorization: Bearer arb_…); not available on the anonymous tier.
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 AfterFees 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 |
|---|---|---|
| best_opportunities | no tags | |
| coin_overview | no tags | |
| pair_breakdown | no tags | |
| funding_rates | no tags | |
| borrow_rates | no tags | |
| fixed_vs_floating | no tags | |
| execution_cost | no tags | |
| basis_trades | no tags | |
| transfer_routes | no tags | |
| pair_history | no tags | |
| term_structure | no tags | |
| venue_execution_cost | no tags | |
| service_status | no tags | |
| order_checklist | no tags | |
| holding_scenarios | no tags | |
| manual_calculator | no tags | |
| boros_lock_calculator | no tags | |
| transfer_calculator | no tags | |
| boros_market | no tags | |
| boros_futures_basis | no tags | |
| exchanges | no tags | |
| exchange_overview | no tags | |
| coins | no tags | |
| track_record | no tags | |
| dex_scan | no tags | |
| spread_chart | no tags | |
| my_positions | no tags |
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 0.18.9.
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 AfterFees 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.