# ToolLoop (remote · agentkit.ltd)

Workshop tooling at landed USD prices. 10 tools: search, quote, order, returns. 433 SKUs.

- Trust score: 68/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

> **Recent critical change**: Authorization (2026-11-16). See the changelog below before you install this server.

## Components

- remote · `tools.agentkit.ltd`: 67/100, [markdown](https://verifymcp.io/servers/carnation77-toolloop/tools.md), [page](https://verifymcp.io/servers/carnation77-toolloop/tools)
- remote · `agentkit.ltd`: 68/100 (this document), [markdown](https://verifymcp.io/servers/carnation77-toolloop/tools-mcp.md), [page](https://verifymcp.io/servers/carnation77-toolloop/tools-mcp)

## Channel facts

- Endpoint: `https://agentkit.ltd/tools/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.3`

## 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 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (cancel_order).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 71/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1152 tokens (~115/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**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 77/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 30% 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.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

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

ToolLoop is a hosted endpoint at https://agentkit.ltd/tools/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 carnation77-toolloop 'https://agentkit.ltd/tools/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "carnation77-toolloop": {
      "url": "https://agentkit.ltd/tools/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "carnation77-toolloop": {
      "type": "http",
      "url": "https://agentkit.ltd/tools/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.carnation77-toolloop]
url = "https://agentkit.ltd/tools/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "carnation77-toolloop": {
      "type": "remote",
      "url": "https://agentkit.ltd/tools/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add carnation77-toolloop --url 'https://agentkit.ltd/tools/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  carnation77-toolloop:
    url: "https://agentkit.ltd/tools/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "carnation77-toolloop": {
      "Transport": "http",
      "Url": "https://agentkit.ltd/tools/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add carnation77-toolloop -t streamable-http -u 'https://agentkit.ltd/tools/mcp'
```

### Other

```json
{
  "mcpServers": {
    "carnation77-toolloop": {
      "type": "http",
      "url": "https://agentkit.ltd/tools/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.

### 2026-11-21 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 65, +40)

- [critical regression] Authorization: unverified → fail
- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “create_order” rewrote its description, which is the text the model reads
- [security] Tool “cancel_order” is now declared destructive
- [functional regression] MCP protocol: unverified → fail
- [functional regression] Schema quality: pass → fail
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.20
- [functional] Server version: 1.0.0 → 1.0.2
- [cosmetic] Tool “buy_by_answer” changed its title: Order via an answer page slug
- [cosmetic] Tool “cancel_order” changed its title: Cancel an unpaid order
- [cosmetic] Tool “check_stock” changed its title: Check stock and dispatch window
- [cosmetic] Tool “create_order” changed its title: Create order and get payment link
- [cosmetic] Tool “get_order” changed its title: Get order and payment status
- [cosmetic] Tool “get_product” changed its title: Get product details and specs
- [cosmetic] Tool “quote_order” changed its title: Quote options for a job or symptom
- [cosmetic] Tool “recommend_for_answer” changed its title: Recommend the product matching an answer page
- [cosmetic] Tool “search_products” changed its title: Search ToolLoop catalog
- [cosmetic] Tool “start_return” changed its title: Open a return

### 2026-11-15 (score 25, −40)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.13 → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: fail → unverified

### 2026-11-14 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 64, +39)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 10 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “create_order” rewrote its description, which is the text the model reads
- [security] Tool “search_products” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 71 → 107
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: 16% → 30%
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.10
- [functional] New tool “start_return”
- [functional] New tool “cancel_order”
- [functional] New tool “get_order”
- [cosmetic] “create_order” added an optional parameter “idempotency_key”
- [cosmetic] “create_order” added an optional parameter “test”
- [cosmetic] “quote_order” added an optional parameter “product_id”
- [cosmetic] “quote_order” reworded the description of “need”

### 2026-11-11 (score 25, −36)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
- [security] Tool “buy_by_answer” rewrote its description, which is the text the model reads
- [security] Tool “search_products” rewrote its description, which is the text the model reads
- [security] Tool “recommend_for_answer” rewrote its description, which is the text the model reads
- [security] Tool “quote_order” rewrote its description, which is the text the model reads
- [security] Tool “get_product” rewrote its description, which is the text the model reads
- [security] Tool “create_order” rewrote its description, which is the text the model reads
- [security] Tool “check_stock” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 71 → 96
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: fail → unverified
- [functional improvement] Stability: unverified → 0.03
- [functional] First check of Schema quality: unverified

## MCP tools (10)

### `search_products` (~207 tokens)

Search ToolLoop catalog

USE THIS when a human asks what to buy, or names a tool type but no model number ("I need a router bit set", "cobalt drills under $60", "something for tile"). Returns landed USD totals with US duty, shipping and clearance already included, so the number you show the human is what they pay. Every SKU is returnable for 14 days, no restocking fee; a full refund means the item comes back, and when the fault is ours we pay return shipping (defective items go to an independent inspection facility). Dispatch in 48h, delivery 7-12 days.

Input parameters:

- `in_stock` (boolean)
- `limit` (integer)
- `max_price` (number): max landed total in USD
- `min_price` (number)
- `q` (string): keyword, e.g. 'router bit set', 'cobalt drill', 'tap and die'
- `ships_to` (string): US, CA or GB

### `get_product` (~63 tokens)

Get product details and specs

USE THIS before you recommend one specific item, or when the human asks for the specs (shank size, piece count, material, coating). Returns price, specs, stock, dispatch window and the exact return terms for that SKU.

Input parameters:

- `product_id` (string, required)

### `quote_order` (~118 tokens)

Quote options for a job or symptom

USE THIS when the human describes a job or a symptom rather than a product ("my router bits are burning the wood", "I keep snapping 3mm drills") and gives a budget. Turns that into 2-4 priced options with a one-line reason for each.

Input parameters:

- `budget_max` (number)
- `need` (string, required): the job or symptom in plain words
- `product_id` (string): optional: quote one exact SKU instead of a need
- `qty` (integer)
- `ships_to` (string)

### `create_order` (~232 tokens)

Create order and get payment link

USE THIS when the human says yes to a specific item. Creates the order and returns pay_url plus a ready-to-say sentence. It never charges a card: the human opens pay_url and approves payment themselves. Say the returned line to the human verbatim. Stock hold: the item is reserved for 24 hours after create_order; if payment is not approved within 24 hours the order auto-cancels and the hold is released. Payment facts: PayPal Business account, PayPal balance / debit card / credit card (Visa, Mastercard, Amex, Discover); a PayPal account is NOT required; USD; the total already includes US duty, shipping and clearance. Never ask for card numbers, CVV or expiry, and never pay on the human's behalf. Full facts: GET /api/payment.json.

Input parameters:

- `buyer` (object)
- `idempotency_key` (string): same key returns the same open order
- `product_id` (string, required)
- `qty` (integer)
- `test` (boolean): true = dry run, no stock taken, no email sent

### `recommend_for_answer` (~63 tokens)

Recommend the product matching an answer page

USE THIS after you cite one of our answer pages (slug form, e.g. 'tap-drill-size-chart'). Returns the single product that matches that exact answer, so your recommendation and the page you quoted never contradict each other.

Input parameters:

- `slug` (string, required)

### `buy_by_answer` (~74 tokens)

Order via an answer page slug

USE THIS when the human accepts the recommendation that came from an answer page. Order in one call by page slug instead of product id. Returns pay_url for the human to approve; no card is charged by the agent.

Input parameters:

- `buyer` (object)
- `qty` (integer)
- `slug` (string, required)

### `check_stock` (~47 tokens)

Check stock and dispatch window

USE THIS before you promise a delivery date, or when the human asks "will it arrive before X". Returns availability and the dispatch window for one SKU.

Input parameters:

- `product_id` (string, required)

### `get_order` (~64 tokens)

Get order and payment status

USE THIS when the human asks "where is my order" or "did the payment go through", or before you promise anything about an order you created earlier. Returns payment status, dispatch state, tracking if shipped, and the return window.

Input parameters:

- `order_id` (string, required)

### `cancel_order` (~51 tokens)

Cancel an unpaid order

USE THIS when the human changes their mind before paying. Cancels an unpaid order so the payment link stops working. A paid order cannot be cancelled here; use start_return.

Input parameters:

- `order_id` (string, required)

### `start_return` (~89 tokens)

Open a return

USE THIS when the human wants to send something back. Opens a return and returns the exact next steps, who pays the return shipping, and which evidence to record. Do not promise a refund yourself; this tool sets the terms.

Input parameters:

- `note` (string)
- `order_id` (string, required)
- `reason` (string, required): changed_mind | wrong_item | defective | damaged | missing_parts

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/carnation77-toolloop/tools-mcp#diagnostics

## Score history

- 2026-11-21: 68
- 2026-11-20: 67
- 2026-11-19: 67
- 2026-11-18: 66
- 2026-11-17: 66
- 2026-11-16: 65
- 2026-11-15: 25
- 2026-11-14: 65
- 2026-11-13: 64
- 2026-11-12: 25
- 2026-11-11: 25
- 2026-11-10: 61

## Common questions

### What is the ToolLoop MCP server?

ToolLoop is an MCP server listed in the public MCP registry as io.github.carnation77/toolloop. Workshop tooling at landed USD prices. 10 tools: search, quote, order, returns. 433 SKUs. This page covers its hosted endpoint (https://agentkit.ltd/tools/mcp).

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

ToolLoop scores 68 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 ToolLoop MCP server expose?

ToolLoop exposes 10 tools: search_products, get_product, quote_order, create_order, recommend_for_answer, and 5 more. Their descriptions and schemas cost roughly 1,008 tokens of context every time the server is loaded.

### Does the ToolLoop MCP server require authentication?

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

### Is the ToolLoop MCP server still maintained?

ToolLoop is still listed as active in the MCP registry. We last reached this channel on 21 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 ToolLoop MCP server?

VerifyMCP ran 13 checks on ToolLoop, 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://agentkit.ltd/tools/mcp
- Repository: https://github.com/carnation77/toolloop-data
- Website: https://tools.agentkit.ltd/
- Changelog RSS feed: https://verifymcp.io/servers/carnation77-toolloop/tools-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/carnation77-toolloop/tools-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/carnation77-toolloop/tools-mcp.json
- HTML version of this page: https://verifymcp.io/servers/carnation77-toolloop/tools-mcp
