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 Deals 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
Pay less for x402 APIs: free pre-payment checks, cheapest working service finder, web/PDF reader.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http agent-deals-mcp https://agent-deals.gm-tools.workers.dev/mcp
# 2 — ask your agent for something these tools do
# preflight_x402_payment, check_x402_service, find_cheapest_x402_service and 2 more
Agent Deals 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-deals-mcp https://agent-deals.gm-tools.workers.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.
FREE. Run this before paying any x402 (HTTP 402) service. Pass the service URL and the PAYMENT-REQUIRED value it sent you (or price_usd and pay_to). Returns GO / CAUTION / STOP with reasons: is the service working, is the price fair (vs its public listing, what our monitor saw, and similar services), is the wallet it asks you to pay safe and the one it normally uses?
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | no | The service you're about to pay (optional when payment_required names it) |
| method | string | no | HTTP method the service uses |
| payment_required | no | The PAYMENT-REQUIRED header value the service sent (base64), or its decoded JSON / 402 body | |
| price_usd | number | no | Price asked, if you don't pass payment_required |
| pay_to | string | no | Wallet you're asked to pay, if you don't pass payment_required |
| max_price_usd | number | no | Optional: STOP when the price is above this |
FREE. Before paying an x402 (HTTP 402) API, check it: is it up right now, does its real price match its listing, and is there a cheaper service that does the same job? Covers ~25,000 paid agent APIs, re-checked continuously.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | The paid service's URL |
| method | string | no | HTTP method the service uses |
Describe what you need; get the cheapest WORKING paid APIs for it, ranked by live price, uptime and speed, with example inputs. 20 free calls per day per client, then $0.002 per call via x402 (USDC on Base).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task | string | yes | What you need done, in plain words |
| max_price_usd | number | no | Ignore services above this price per call |
| limit | integer | no | Number of results (default 5) |
Fetch a public web page or PDF and return clean Markdown of the main content, plus title, author, date, JSON-LD and links. $0.003 per call via x402. Failed reads are not charged.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Public http(s) URL |
| max_chars | integer | no | Max Markdown characters (default 50000) |
| selector | string | no | Optional CSS selector to convert only part of the page |
Title, description, canonical URL, language, site name, author, publish date, image and JSON-LD of a public page. $0.002 per call via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Public http(s) URL |
- 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 Deals 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 1.0.0.
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 Deals 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.