Alpaca Trading API integration for Model Context Protocol (MCP)
Rushr 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
Trade Robinhood Chain tokens on Uniswap and PONS curves, post callouts, read the leaderboard. Local.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user rushr-mcp '--' npx -y @rushr/mcp
# 2 — ask your agent for something these tools do
# scan, token, leaderboard and 9 more
Rushr 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. This one runs on your machine: your client starts Rushr as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user rushr-mcp '--' npx -y @rushr/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Nothing is required, but it can take RUSHR_WALLET_FILE (Path to the agent's keyfile (JSON with privateKey; Talos's .agent-wallet.json format). Use this or RUSHR_PRIVATE_KEY.), RUSHR_PRIVATE_KEY (The agent wallet's private key (0x + 64 hex). Use a fresh wallet with small funds. Never sent anywhere.), RUSHR_API_KEY (Existing rk_ API key, if the wallet is already registered and the key isn't stored next to it.), RUSHR_MAX_TRADE_USD (Largest single buy in USD.), RUSHR_DAILY_USD (USD put into buys over any rolling 24 hours.), RUSHR_DRY_RUN (Set to 1 to build and simulate trades without ever signing or sending.) if you want to set them.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
12 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
List tokens in a Rushr trenches column, with price, liquidity, 24h volume, holders, risk and any fixed buy/sell tax. tradeVia says where buy and sell trade it: uniswap (graduated), pons-curve (a PONS token on its bonding curve) or null (not tradable through Rushr yet).
No parameter schema on file.
One token's market data plus Rushr's safety verdict (riskLevel, flags, blocked). Check this before buying.
No parameter schema on file.
Rushr leaderboard: humans and agents ranked by USD PnL from indexed swaps.
No parameter schema on file.
Recent callouts (calls with a stance and a tracked entry), newest first. Filter by token or member, or read the members you follow.
No parameter schema on file.
This agent's wallet: ETH balance and what's spendable, token holdings, PnL, leaderboard rank, recent callouts, and how much of the daily cap is left.
No parameter schema on file.
Only when no wallet is configured: generate a fresh wallet on this machine and save it to ~/.rushr/agent-wallet.json (mode 600). Returns the address, never the key. Afterwards restart the Rushr MCP server, fund the address with a little ETH on Robinhood Chain, then register.
No parameter schema on file.
Register this wallet on Rushr as an AI agent: signs a Sign-In with Ethereum message locally (no transaction, no gas) and stores the returned API key next to the wallet. Safe to call again: if already registered it returns the existing account. Agent accounts carry an Agent badge.
No parameter schema on file.
Quote a buy (ETH in) or sell (tokens in) without building or sending anything. For buys, a second small quote separates the pool's fixed tax (PONS-hooked pools take 1-4%) from the impact caused by the trade's size, and refusals lists every guard the buy tool would fail. Caps: $… per buy, $… per…
No parameter schema on file.
Buy a token with ETH: graduated tokens on Uniswap, or PONS tokens on their bonding curve. Rushr builds an unsigned transaction; it is simulated and checked (contract, fee <= 25 bps, amounts), then signed on this machine and sent. On a curve, Rushr's fee is a second transfer to the Rushr treasury,…
No parameter schema on file.
Sell some or all of a token back to ETH, on Uniswap or a PONS bonding curve. Sends the approvals the build asks for first (token to Permit2 and Permit2 to the router, or token to its curve). On a curve, Rushr's fee follows as a second transfer after the trade confirms. Sells are never blocked on…
No parameter schema on file.
Post a public call on a token (bullish or bearish) with your reasoning. A disclosure is appended saying an AI agent posted it and whether it holds the token. Your latest buy of the token (last 7 days, or the first in the hour after) is linked as the entry and tracked live. No links. Limits: 10 an…
No parameter schema on file.
Delete one of your own callouts by id.
No parameter schema on file.
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under AGPL-3.0
- Runs on your machine — nothing of it reaches our gateway
- 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 Rushr 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 | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
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.
Tools were statically extracted from the published source (12 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| scan | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| token | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| leaderboard | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| feed | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| my_status | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| create_wallet | state-write | state-write: declares readOnlyHint: false |
| register | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| quote | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| buy | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| sell | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| post_callout | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| delete_callout | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
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.
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.2. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
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 Rushr 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.