Pink Agentic AI Payments (by PinkWallet): lets Claude, ChatGPT, Cursor pay vendor invoices within company spending rules (budgets, caps, allow-lists, human approval). Sandbox preview, test money.
Agent Embassy 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
Agents pay for work and prove it. Verified checks $0.15, recovery $1.00. USDC on Base via x402.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http agent-embassy-mcp https://agent-embassy.fly.dev/mcp
# 2 — ask your agent for something these tools do
# register_recovery, verified_check, compute_history and 2 more
Agent Embassy 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 agent-embassy-mcp https://agent-embassy.fly.dev/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
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.
5 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.
Register a dead-man's recovery configuration for your AI agent: the Embassy stores your client-encrypted recovery blob and quorum rules and queues them for human review within 24h. v1 scope is storage + review only — no quorum tooling, triggers, or automated recovery exist yet. One-time $1.00 registration per agent wallet, paid in USDC via x402. Acceptance test: the stored blob's hash matches the
No parameter schema on file.
Verify a web claim and get a signed, re-checkable Outcome Receipt — machine-verifiable proof of delivery for agent commerce. The Embassy fetches your HTTPS URL once, server-side, and checks it against your conditions: HTTP status, a body substring, or a JSON field value. The receipt records the check transcript and verdict so anyone can re-verify. $0.15 per check via x402. Fully automated, no huma
No parameter schema on file.
Compute market history: paid time series of compute market prices. Per-class cheapest/median/offer-count series or whole-market history, bounded and timestamped, embedded in your signed receipt. $0.25 per query via x402. Fully automated. Upstream sources are internal and never named. Asks are ephemeral — re-observe before any decision. MONETIZED VIA x402 — this tool is not callable for free. POST
No parameter schema on file.
Compute price alerts: recent large per-class price moves, most recent first. Bounded (limit 1-50, default 25), timestamped, embedded in your signed receipt. $0.25 per query via x402. Fully automated. Upstream sources are internal and never named. Asks are ephemeral — re-observe before any decision. MONETIZED VIA x402 — this tool is not callable for free. POST https://agent-embassy.fly.dev/v1/mark
No parameter schema on file.
Compute market snapshot: cheapest rentable asks per class in USD/hour, observed live. MONETIZED VIA x402 — this tool is not callable for free. GET https://agent-embassy.fly.dev/v1/markets/compute/spot with an x402 payment ($0.25, USDC on Base or Arbitrum One). Prices only — upstream sources are internal and never named. Listings are ephemeral asks, not delivered-cost guarantees.
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 Agent Embassy 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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
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 1.0.1.
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 Agent Embassy 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.