Sato Hub
Trading Tool

Epsilon

Non-custodial limit, stop-loss, DCA and trailing-stop order venue on Robinhood Chain with a REST API, TS/Python SDKs and a hosted MCP server.

  • Sato Score76
  • ChainsRobinhood Chain
BetaSelf-ReportedRecent · 1mo ago

Epsilon is a partly open-source trading tool on Robinhood Chain, with last code activity on 2026-10-05 (Recent). Sato Score 76/100 (how open, active and verifiable it is, not a safety grade), as of 2026-11-07. How the score works →

Check what an install would ask of your keys, before you run it →

Last commit Oct 5, 2026

Listed from epsilon.exchange on 2026-09-23. Install: not attempted — no install path on record. Evidence →

Next step

Watch Epsilon

One email if what we observe changes — its repo goes quiet or disappears, or the listing is retired. Nothing else.

Check it from your agent

Add Sato Hub’s MCP server (no key), then ask:

https://satohub.ai/api/mcp
Run Sato Hub Preflight on alienbase-xyz/epsilon-plugin before I use it.
Full setup: Claude Code, Cursor, others →

Your project?

Prove you control the domain and correct this page — description, links, tags, chains. A claim proves control, not verification: it never changes the Sato Score.

Claim this listing →

Overview

Epsilon offers limit, stop-loss, DCA and trailing orders for memecoins and RWAs on Robinhood Chain, executed from the user's own wallet (https://www.epsilon.exchange). The developer platform documents a REST API at https://api.epsilon.exchange/v1, the SDKs @epsilon-exchange/sdk (npm) and epsilon-exchange (PyPI), a CLI, webhooks and an MCP package @epsilon-exchange/mcp with a hosted endpoint (https://developers.epsilon.exchange). Orders are EIP-712 messages signed locally. API keys (eps_…) were issued through a concierge during early access, with self-serve issuance described as planned. The MIT-licensed plugin repo bundles a 12-tool MCP server and two agent skills, with a per-order USD cap and a confirmation gate on by default (https://github.com/alienbase-xyz/epsilon-plugin).

Sato Score

76/100· High

How open, active & verifiable — not a safety or returns grade.

Maintenance & liveness
35/35
Code transparency
12/20
Interface verifiability
10/10
Docs & demo
6/10
Listing transparency & provenance
10/15
Independent verification
3/10

Live endpoint probed — we called the hosted MCP endpoint and it answered with its real tool inventory (proves the interface works, not runtime safety).

Evidence — listed vs checked · what the words mean

Listed from epsilon.exchange on 2026-09-23. Install: not attempted — no install path on record.

ClaimValueEvidenceSourceChecked
Chains supportedRobinhood Chainself-reporteddevelopers.epsilon.exchangeas of 2026-11-07
Verification statusSelf-Reported — not independently reviewedself-reportedepsilon.exchangeas of 2026-11-07
Recent activitylast commit 2026-10-05observedgithub.com/alienbase-xyz/epsilon-plugin2026-11-07
MCP endpoint answersanswered — 22 tools listedobservedapi.epsilon.exchange2026-11-07
Daily check record45 of 45 daily checks since 2026-09-23 succeededa success rate of our checks, not uptime; the source is this listing's own historyobserved—2026-11-06
Works withCursor, Claude Code, ChatGPT, Codex, Cline, LangChain, Vercel AI SDK, Telegramconfidence 0.80self-reporteddevelopers.epsilon.exchangeas of 2026-09-29
Tagsmcp, limit-orders, dca, non-custodial, eip-712, agent-skills, robinhood-chain, …confidence 0.80self-reportedepsilon.exchangeas of 2026-09-29
Sato Score76/100 (High)how open, active and verifiable — not a safety or quality gradecomputedsatohub.ai2026-11-07

Self-reported rows are the project’s own words, dated when we recorded them — not a check. Only reproduced and reviewed rows carry a mark. None of these rows is a safety or quality rating.

Tool inventory — 22 tools, probed live 2026-11-07

  • cancel_order — Ask the user to approve cancelling one of their open orders (hash from list_orders). Returns an approval link; the cancellation is signed by the user's wallet in the Epsilon app. Orders already filled
  • check_order — Check whether a resting order (limit, stop, DCA, trailing) for this pair and size would be executable: oracle support, liquidity, minimum size. Run this before signing any resting order; it does not p
  • get_approval — Status of an approval you created: pending (user hasn't decided), submitted (with orderHash or txHash — then use get_order to follow fills), rejected, failed, or expired (links live 30 minutes). Poll
  • get_error_catalog — Machine-readable catalog of every error code the Epsilon API returns, with meanings and retry guidance. Consult it when any other tool returns an error code you need to interpret or decide whether to
  • get_example — Full source code of one Epsilon integration example, by id from list_examples. No API key required.
  • get_grant — The signed-in account's agent grant for this channel, if any: the embedded wallet it signs with, per-order and daily caps, what remains today, allowed order kinds, and whether the Epsilon signer is ac
  • get_market_stats — Market-level numbers for Epsilon (Robinhood Chain DEX). scope=overview (default) is the best first call: top tokens by 30-day volume, 24h volume, and engine-wide order/fill stats in one response. scop
  • get_me — The signed-in Epsilon account behind this session: account id, handle, linked wallets (embedded first), the scopes this client was granted, and which client is connected. Call it first after sign-in t
  • get_order — One Epsilon order by hash: status (pending/active/filled/cancelled/expired), parameters, and its fills. Use list_orders to find orders by wallet first; use get_orderbook for the market's resting order
  • get_orderbook — The market's open (pending/active) limit orders on both sides of a token pair, largest first — liquidity you can rest against. For one wallet's own orders use list_orders instead.
  • get_quote — Best executable quote for swapping tokenIn → tokenOut on Epsilon (Robinhood Chain, id 4663): expected output and price. Use this for a quick price check; use get_route when you need the venue split, f
  • get_route — Full routing breakdown for a swap: best venue split, expected and minimum output, price impact (ppm), and the feeLegs a signed order must embed (pass orderType for a resting order so the right fee cel
  • list_examples — List runnable Epsilon integration examples (Python cron DCA, LangChain tools, Vercel AI SDK tools, Telegram bot). Fetch full source with get_example. No API key required.
  • list_fills — Executed trades (swaps and order fills) on Epsilon, newest first, optionally for one wallet — the trade history. For resting/open orders use list_orders. Amounts are RAW token units.
  • list_orders — A wallet's Epsilon orders filtered by status and/or type — the portfolio view, newest first. Use get_order for one order's fills; use list_fills for executed trades.
  • place_dca_order — Ask the user to approve a DCA program: sell amount of tokenIn for tokenOut in `executions` equal slices, one every `every` (15m, 1h, 1d…). Optionally gated by triggerPrice (only sells at or below it).
  • place_limit_order — Place a resting limit order: sell amount tokenIn for tokenOut once the market reaches limitPrice (tokenOut per tokenIn) or better. Keeper-executed — it keeps working with the chat closed. If the user
  • place_market_order — Ask the user to approve a market swap of amount tokenIn → tokenOut at the best current route. Returns an approval link, not a fill: the user signs in the Epsilon app. Use get_quote first to tell the u
  • place_stop_order — Place a stop-loss: sell amount tokenIn for tokenOut if the price falls to triggerPrice (tokenOut per tokenIn). Keeper-executed. Queued under an active agent grant that covers it, otherwise returns an
  • place_trailing_order — Ask the user to approve a trailing stop: sell amount tokenIn for tokenOut when price drops trailPercent below its running high since placement. Keeper-executed after signing; always returns an approva
  • search_docs — Search the Epsilon developer documentation (API, auth, order signing, webhooks, rev-share, SDKs, MCP). Returns the most relevant doc sections. No API key required.
  • search_tokens — Resolve a token symbol or name to its address and decimals — call this FIRST when the user names a token; every other tool takes addresses. volume30dUsd disambiguates same-symbol tokens: the real one
Answers a handshake
yes · 2026-11-07
Answers a call
yes — get_error_catalog returned in 188 ms

Live probe verifies the interface responds — not what the tools do, their safety, or their output quality. The call is one read-only tool named by this server's own list (list_/get_/search_, no mutating verb anywhere in the name, no required arguments and none that look like a key, an address or an amount), asked once a day with no arguments. Not asked is not a failure.

Observed record — 46 daily checks since 2026-09-23

100%of 46 checks since 2026-09-23 succeeded
Currently responding for 46 days
Succeeded
46
Failed
0
Their error
0
Unattributed
0

This is the share of our daily checks that succeeded — not an availability guarantee. A check can fail because the host was down, because our runner timed out, or because the network in between dropped it, and only the first of those is a fact about this project. Failures are split by what we can attribute; anything we cannot attribute is counted, not hidden.

Last 30 days — to 2026-11-07, one point per UTC day

Share of OUR checks that succeeded
100%
7-day rolling; unattributable days are gaps · 30/30 days
Tools listed
22
from the server's own tools/list · 29/30 days
Sato Score
76
as snapshotted that day · 29/30 days

A gap is a day we have no attributable observation — never a zero. Thirty points is the whole shape the free layer carries; the daily rows behind it stay in the snapshot series.

Tool inventory history — 22 now, peak 22, since 2026-09-23

  • 2026-10-07 13 → 22 +9 (cancel_order, get_approval, get_grant, get_me…)
  • 2026-10-05 15 → 13 +5 (check_order, get_error_catalog, get_market_stats, get_order…) −7 (error_catalog, get_market_overview, get_order_status, market_stats…)

Recorded from our own daily tools/list handshake. A shrinking toolset is a real signal for an agent choosing a server; a gap in the series means the probe did not succeed that day, not that the tools disappeared.

Details

Chains
Robinhood Chain
Agent types
Trading Venue, MCP Server
Open source
Partial
Works with
Cursor, Claude Code, ChatGPT, Codex, Cline, LangChain, Vercel AI SDK, Telegram
Last checked
2026-11-07

Marketplace Signals

No marketplace signals recorded for this resource yet.

Verification status reflects evidence reviewed by Sato Hub. Self-reported claims are never presented as verified.

#mcp#limit-orders#dca#non-custodial#eip-712#agent-skills#robinhood-chain#sdk#stop-loss#trailing-stop#rest-api#webhooks
See something inaccurate or outdated?Submit a correction →

Listing History

Recorded changes to Epsilon's listing — status, verification, Sato Score, and recent releases. Full history is kept in the listing record.

  1. Sep 29, 2026
    Auto-enriched: supported integrations, tags
  2. Sep 23, 2026
    Listed on Sato Hub
  3. Sep 23, 2026
    Sato Hub began tracking this listing

Compared with

Appears in

Related Resources

Reference

QuestionsShowHide

Questions people ask about Epsilon

Is Epsilon open source?
Partly. Some of Epsilon is published as source (https://github.com/alienbase-xyz/epsilon-plugin) and some is not. Checked as of 2026-11-07.
Which chains does Epsilon support?
Epsilon lists support for Robinhood Chain as of 2026-11-07.
Is Epsilon still maintained?
The most recent code activity Sato Hub observed was on 2026-10-05 (last commit 2026-10-05), which Sato Hub labels "Recent". Posts on X are not counted as maintenance. Activity is a recency signal, not a quality judgment.
How do I install or run Epsilon?
Sato Hub has no deploy spec for Epsilon; follow the project's own documentation at https://developers.epsilon.exchange.
Is Epsilon verified on Sato Hub?
Sato Hub holds one earned check for Epsilon: Live endpoint probed — we called the hosted MCP endpoint and it answered with its real tool inventory (proves the interface works, not runtime safety). Its Sato Score is 76 of 100, a measure of how open, active and verifiable the project is, not a safety, quality or returns grade.
Cite this pageShowHide

Cite this page

Sato Hub. "Epsilon — Sato Hub." Sato Hub, updated 2026-11-07, accessed 2026-11-07. https://satohub.ai/resources/epsilon

Data last refreshed 2026-11-07; this page is rebuilt daily. Citations carry the date so a reader can tell which snapshot a claim came from. Catalog data is licensed CC-BY-4.0.

Join the Sato Hub Briefing

Sign up for the Briefing: the agents, tools, and infrastructure that actually shipped, and why they matter.