# agentPickup (remote · agentpickup.app)

Find pickup shops near you, order, pay by card or USDC (x402), and get the QR to collect in person.

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- remote · `agentpickup.app`: 70/100 (this document), [markdown](https://verifymcp.io/servers/dav3trad3r-agentpickup/agentpickup.md), [page](https://verifymcp.io/servers/dav3trad3r-agentpickup/agentpickup)
- npm · `@agentpickup/mcp`: 61/100, [markdown](https://verifymcp.io/servers/dav3trad3r-agentpickup/agentpickup-mcp.md), [page](https://verifymcp.io/servers/dav3trad3r-agentpickup/agentpickup-mcp)

## Channel facts

- Endpoint: `https://agentpickup.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-06.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1358 tokens (~135/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 91/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 74% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the agentPickup MCP server?

agentPickup is a hosted endpoint at https://agentpickup.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http dav3trad3r-agentpickup 'https://agentpickup.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dav3trad3r-agentpickup": {
      "url": "https://agentpickup.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dav3trad3r-agentpickup": {
      "type": "http",
      "url": "https://agentpickup.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dav3trad3r-agentpickup]
url = "https://agentpickup.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dav3trad3r-agentpickup": {
      "type": "remote",
      "url": "https://agentpickup.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dav3trad3r-agentpickup --url 'https://agentpickup.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dav3trad3r-agentpickup:
    url: "https://agentpickup.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dav3trad3r-agentpickup": {
      "Transport": "http",
      "Url": "https://agentpickup.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dav3trad3r-agentpickup -t streamable-http -u 'https://agentpickup.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dav3trad3r-agentpickup": {
      "type": "http",
      "url": "https://agentpickup.app/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-06 (score 70, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-11-04 (score 68, −1)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] HSTS header: fail → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] TLS certificate: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-11-03 (score 69)

First indexed and scored.

## MCP tools (10)

### `find_shops` (~200 tokens)

Find pickup shops

Find agentPickup shops to order from: near a point (lat/lng), in a suburb or city (place), or selling something (query). Returns each shop's shop_url, pickup address, hours, whether it's open now, distance, and matching menu items.

Input parameters:

- `lat` (number): Where the user is: latitude. Send with lng.
- `limit` (integer)
- `lng` (number): Where the user is: longitude. Send with lat.
- `open_now` (boolean): Only shops open now (shops without listed hours stay in).
- `place` (string): A suburb, street or city to match against shop addresses, e.g. "Surry Hills".
- `query` (string): What the user wants, e.g. "flat white" or "croissant". Leave out to list everything.
- `radius_km` (number): With lat/lng: how far to look. Default 10.

### `get_shop` (~57 tokens)

See what a shop sells

What the shop sells (item ids and prices), where to collect, and which payments it takes.

Input parameters:

- `shop_url` (string): An agentPickup shop's URL, as find_shops returns it. Defaults to https://agentpickup.app.

### `create_pickup_order` (~185 tokens)

Order for pickup

Create an order to collect in person. Returns the order id and total; pay it with pay_order. The shop emails the pickup QR to `email` once it's paid. Where the shop takes cards, `payment: "card"` returns a checkout link for the user to pay on instead.

Input parameters:

- `email` (string, required): The user's email. The pickup QR goes here.
- `items` (array, required)
- `name` (string): Name for the order, shown to staff
- `payment` (string): Who pays: agent (USDC over x402, or a test payment at a test shop) or card (the user pays on a checkout link). Default: agent where the shop takes it, else card.
- `shop_url` (string): An agentPickup shop's URL, as find_shops returns it. Defaults to https://agentpickup.app.

### `pay_order` (~107 tokens)

Pay for an order

Pay an order in USDC over x402 from wallet 0xd253e213cE143Aa0E1e1cAfc92f7AE82c98aB3bB. This spends money: confirm the items and total with the user first. Returns the pickup pass link.

Input parameters:

- `order_id` (string, required)
- `shop_url` (string): An agentPickup shop's URL, as find_shops returns it. Defaults to https://agentpickup.app.

### `order_status` (~63 tokens)

Check an order

Whether an order is waiting for payment, paid, ready to collect, collected or expired.

Input parameters:

- `order_id` (string, required)
- `shop_url` (string): An agentPickup shop's URL, as find_shops returns it. Defaults to https://agentpickup.app.

### `get_pickup_pass` (~75 tokens)

Get the pickup pass

The pass link, pickup code and QR content for an order this wallet paid, by signing in with the wallet (Sign-In-With-X).

Input parameters:

- `order_id` (string, required)
- `shop_url` (string): An agentPickup shop's URL, as find_shops returns it. Defaults to https://agentpickup.app.

### `start_group_order` (~143 tokens)

Start a group order

Start a group order (a coffee run) at a shop. Returns a code to share: each person's agent joins with it and pays for their own items. When it closes, the shop gets one combined order and the organiser is emailed its pickup QR.

Input parameters:

- `closes_in_minutes` (integer): Default 15
- `organiser_email` (string, required): Where the group's pickup QR goes
- `organiser_name` (string, required): Who collects, shown to staff
- `shop_url` (string): An agentPickup shop's URL, as find_shops returns it. Defaults to https://agentpickup.app.
- `title` (string): e.g. "Friday coffee run"

### `join_group_order` (~129 tokens)

Join a group order

Add the user's items to a group order with its code. Returns the order id; pay it with pay_order before the group closes. The organiser collects everything, so the user gets a receipt, not a QR.

Input parameters:

- `code` (string, required): The group's code
- `email` (string, required): The user's email, for their receipt
- `items` (array, required)
- `name` (string, required): The user's name, shown to staff on their items
- `shop_url` (string): An agentPickup shop's URL, as find_shops returns it. Defaults to https://agentpickup.app.

### `group_order_status` (~69 tokens)

Check a group order

Who's in a group order, what they ordered, who has paid, and whether it has closed and been collected.

Input parameters:

- `code` (string, required)
- `shop_url` (string): An agentPickup shop's URL, as find_shops returns it. Defaults to https://agentpickup.app.

### `close_group_order` (~79 tokens)

Close a group order now

Close a group order early, as its organiser. Unpaid shares are left out; the shop gets the rest as one order.

Input parameters:

- `code` (string, required)
- `organiser_key` (string, required)
- `shop_url` (string): An agentPickup shop's URL, as find_shops returns it. Defaults to https://agentpickup.app.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dav3trad3r-agentpickup/agentpickup#diagnostics

## Score history

- 2026-11-06: 70
- 2026-11-05: 68
- 2026-11-04: 68
- 2026-11-03: 69

## Common questions

### What is the agentPickup MCP server?

agentPickup is an MCP server listed in the public MCP registry as io.github.dav3trad3r/agentpickup. Find pickup shops near you, order, pay by card or USDC (x402), and get the QR to collect in person. This page covers its hosted endpoint (https://agentpickup.app/mcp).

### Is the agentPickup MCP server safe to use?

agentPickup scores 70 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the agentPickup MCP server expose?

agentPickup exposes 10 tools: find_shops, get_shop, create_pickup_order, pay_order, order_status, and 5 more. Their descriptions and schemas cost roughly 1,107 tokens of context every time the server is loaded.

### Does the agentPickup MCP server require authentication?

No. We connected to agentPickup without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the agentPickup MCP server still maintained?

agentPickup is still listed as active in the MCP registry. We last reached this channel on 6 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the agentPickup MCP server?

VerifyMCP ran 13 checks on agentPickup, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://agentpickup.app/mcp
- Website: https://agentpickup.app/
- Changelog RSS feed: https://verifymcp.io/servers/dav3trad3r-agentpickup/agentpickup.xml
- Changelog JSON feed: https://verifymcp.io/servers/dav3trad3r-agentpickup/agentpickup/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/dav3trad3r-agentpickup/agentpickup.json
- HTML version of this page: https://verifymcp.io/servers/dav3trad3r-agentpickup/agentpickup