# Agent Utilities Hosted (remote · agent-utilities.agent-utilities.workers.dev)

Product identity, pack sizes and feed/page checks. Free small trials; paid calls from $0.0003.

- Trust score: 71/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-27

## Components

- remote · `agent-utilities.agent-utilities.workers.dev`: 71/100 (this document), [markdown](https://verifymcp.io/servers/dev-workers-agent-utilities-agent-utilities-agent-utilities/mcp-remote.md), [page](https://verifymcp.io/servers/dev-workers-agent-utilities-agent-utilities-agent-utilities/mcp-remote)

## Channel facts

- Endpoint: `https://agent-utilities.agent-utilities.workers.dev/mcp/remote`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.6.0`

## 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 2026-09-27.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - 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**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 7033 tokens (~75/item across 93 items; 48 tools + 45 resources), lean.
  - Tools include usage examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 88/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 58% of tool parameters carry a description.
  - Structured output schemas are declared (92% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 48 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 50 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 Agent Utilities Hosted MCP server?

Agent Utilities Hosted is a hosted endpoint at https://agent-utilities.agent-utilities.workers.dev/mcp/remote, 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 dev-workers-agent-utilities-agent-utilities-agen 'https://agent-utilities.agent-utilities.workers.dev/mcp/remote'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-workers-agent-utilities-agent-utilities-agen": {
      "url": "https://agent-utilities.agent-utilities.workers.dev/mcp/remote"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-workers-agent-utilities-agent-utilities-agen": {
      "type": "http",
      "url": "https://agent-utilities.agent-utilities.workers.dev/mcp/remote"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-workers-agent-utilities-agent-utilities-agen]
url = "https://agent-utilities.agent-utilities.workers.dev/mcp/remote"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-workers-agent-utilities-agent-utilities-agen": {
      "type": "remote",
      "url": "https://agent-utilities.agent-utilities.workers.dev/mcp/remote",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-workers-agent-utilities-agent-utilities-agen --url 'https://agent-utilities.agent-utilities.workers.dev/mcp/remote' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-workers-agent-utilities-agent-utilities-agen:
    url: "https://agent-utilities.agent-utilities.workers.dev/mcp/remote"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-workers-agent-utilities-agent-utilities-agen": {
      "Transport": "http",
      "Url": "https://agent-utilities.agent-utilities.workers.dev/mcp/remote"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-workers-agent-utilities-agent-utilities-agen -t streamable-http -u 'https://agent-utilities.agent-utilities.workers.dev/mcp/remote'
```

### Other

```json
{
  "mcpServers": {
    "dev-workers-agent-utilities-agent-utilities-agen": {
      "type": "http",
      "url": "https://agent-utilities.agent-utilities.workers.dev/mcp/remote"
    }
  }
}
```

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.

### 2026-09-27 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-25 (score 70, 0)

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

### 2026-09-24 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-22 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-21 (score 68, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “agent_utilities_pack_preview” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 6097 → 7033
- [functional] New resource “commerce_feed_page_compare fixed example”
- [functional] New resource “commerce_main_product fixed example”
- [functional] New resource “commerce_pack_size_normalize fixed example”
- [functional] Server version: 1.5.0 → 1.6.0
- [functional] New tool “agent_utilities_feed_page_compare_preview”
- [functional] New tool “agent_utilities_main_product_preview”
- [functional] New tool “agent_utilities_pack_size_normalize_preview”
- [functional] New tool “commerce_feed_page_compare”
- [functional] New tool “commerce_main_product”
- [functional] New tool “commerce_pack_size_normalize”

### 2026-09-20 (score 68, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 1.4.0 → 1.5.0
- [functional] Server version: 1.3.2 → 1.4.0
- [functional] New tool “agent_utilities_payment_options”
- [functional] New tool “agent_utilities_offer_preview”

### 2026-09-19 (score 67)

First indexed and scored.

## MCP tools (48)

### `agent_utilities_main_product_preview` (~85 tokens)

FREE, no key. Identify the main Product or ProductGroup from supplied JSON-LD HTML using identity, mainEntity and canonical evidence; abstain on ambiguity. Entire JSON input: 16384 UTF-8 bytes. Supplied data only; no fetch, payment or automatic paid fallback.

Input parameters:

- `html` (string, required)
- `pageUrl` (string)

Output parameters:

- `chargedMicroUsd`
- `executionPerformed`
- `limits` (object)
- `mode`
- `result` (object)

### `agent_utilities_pack_size_normalize_preview` (~89 tokens)

FREE, no key. Normalize locale-explicit pack-size expressions and multipacks to exact grams, millilitres or counts; reject ambiguous text. Entire JSON input: 4096 UTF-8 bytes, at most 5 quantities. Supplied data only; no fetch, payment or automatic paid fallback.

Input parameters:

- `locale` (string, required)
- `quantities` (array, required)

Output parameters:

- `chargedMicroUsd`
- `executionPerformed`
- `limits` (object)
- `mode`
- `result` (object)

### `agent_utilities_feed_page_compare_preview` (~98 tokens)

FREE, no key. Compare supplied feed identity, price, currency and availability with selected JSON-LD product evidence; preserve conflicts and unknown fields. Entire JSON input: 16384 UTF-8 bytes. Supplied data only; no fetch, payment or automatic paid fallback.

Input parameters:

- `feed` (object, required)
- `html` (string, required)
- `offerUrl` (string)
- `pageUrl` (string)

Output parameters:

- `chargedMicroUsd`
- `executionPerformed`
- `limits` (object)
- `mode`
- `result` (object)

### `agent_utilities_offer_preview` (~113 tokens)

FREE, no key. Extract declared Product/Offer JSON-LD from supplied HTML only. No page fetch, JavaScript execution, live-price verification or orders. At most 3 offers; inspect truncated and warnings. No paid fallback. Entire JSON input is limited to 16384 UTF-8 bytes; maxOffers defaults to 3. Larger HTML uses commerce_offer_extract after separate spending approval.

Input parameters:

- `baseUrl` (string)
- `html` (string, required)
- `maxOffers` (integer)

Output parameters:

- `chargedMicroUsd` (string)
- `executionPerformed` (boolean)
- `limits` (object)
- `mode` (string)
- `result` (object)
- `scope` (string)

### `agent_utilities_pack_preview` (~114 tokens)

FREE custom pack planning. Up to 3 interchangeable offers, 1000 required units, 1000 units per pack and 50 packs per offer; 4096 input bytes. Exact item subtotal only; excludes shipping, tax and fees. No key, payment, network fetch or paid fallback. Larger tasks may use commerce_pack_plan after separate spending approval.

Input parameters:

- `currency` (string, required)
- `minorUnitDigits` (integer, required)
- `offers` (array, required)
- `requiredUnits` (integer, required)

Output parameters:

- `chargedMicroUsd` (string)
- `executionPerformed` (boolean)
- `limits` (object)
- `mode` (string)
- `result` (object)
- `scope` (string)

### `agent_utilities_example` (~70 tokens)

FREE, no API key. Read a fixed handler-generated input/output example for a listed non-network tool before deciding whether to pay. Accepts only a tool name; cannot run custom input, access a wallet or spend credits. Examples are synthetic, not customer activity.

Input parameters:

- `name` (string, required)

### `agent_utilities_prepare` (~72 tokens)

FREE. Validate input and return a new requestId, current per-call price ceiling and exact arguments for one paid call. No execution, funding or reservation. Save the prepared call before execution. Do not prepare again to recover an uncertain payment.

Input parameters:

- `input` (object, required)
- `name` (string, required)

### `agent_utilities_payment_options` (~54 tokens)

FREE, no key. Read current credit packs, live/test configuration and the funding link. Explains how to enable paid MCP calls after a free trial. Creates no account, checkout or payment; accepts no credentials.

### `agent_utilities_balance` (~62 tokens)

FREE authenticated read of your current service-credit balance and live/test mode. Uses only the private Authorization header; takes no arguments or credentials. No charge, purchase, reservation or total spending limit. Balance can change after this snapshot. Does not read wallet USDC.

### `html_main_text` (~115 tokens)

Extract article text from supplied HTML. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `method` (string)
- `text` (string)
- `title` (string)

### `html_jsonld` (~121 tokens)

Parse up to 50 JSON-LD blocks from supplied HTML. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `invalidBlocks` (number)
- `items` (array)

### `html_tables` (~115 tokens)

Extract source table cells without expanding spans. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `spanPolicy` (string)
- `tables` (array)

### `web_readable_fetch` (~120 tokens)

Fetch readable text from an approved public HTTPS host. PAID: 2000 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `method` (string)
- `status` (number)
- `text` (string)
- `title` (string)
- `url` (string)

### `web_redirect_trace` (~120 tokens)

Trace up to four redirects across approved public HTTPS hosts. PAID: 1000 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `redirects` (array)
- `status` (number)
- `url` (string)

### `web_robots_evaluate` (~125 tokens)

Evaluate supplied robots.txt for a URL and user agent; no network fetch. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `allowed` (boolean|null)
- `crawlDelay` (number|null)
- `scope` (string)
- `sitemaps` (array)

### `contracts_openapi_lint` (~123 tokens)

Validate OpenAPI 3.0 JSON structure and internal references. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `issues` (array)
- `scope` (string)
- `valid` (boolean)

### `contracts_openapi_diff` (~123 tokens)

Detect selected direct breaking changes between OpenAPI 3.0 documents. PAID: 800 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `breakingChangesDetected` (boolean)
- `changes` (array)
- `scope` (string)

### `contracts_jsonschema_validate` (~123 tokens)

Validate data using a bounded JSON Schema 2020-12 subset. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `issues` (array)
- `scope` (string)
- `valid` (boolean)

### `security_secret_scan` (~119 tokens)

Detect five families of credential patterns with fully masked findings. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `caveat` (string)
- `findings` (array)
- `limitReached` (boolean)
- `rulesVersion` (string)

### `security_secret_redact` (~118 tokens)

Replace detected credential patterns with redaction markers. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `caveat` (string)
- `findings` (array)
- `limitReached` (boolean)
- `rulesVersion` (string)
- `text` (string)

### `agents_config_audit` (~120 tokens)

Review agent configuration text with five fixed risk heuristics. PAID: 800 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `caveat` (string)
- `findings` (array)
- `rulesVersion` (string)

### `data_json_patch` (~136 tokens)

Apply up to 100 RFC 6902 operations transactionally to supplied JSON, with strict pointers, safe object properties and bounded intermediate results. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `data`
- `documentExists` (boolean)
- `operationsApplied` (number)
- `scope` (string)

### `html_metadata` (~123 tokens)

Extract title, description, canonical URL, language and social metadata from supplied HTML. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `canonicalUrl` (string|null)
- `description` (string)
- `language` (string)
- `robots` (string)
- `social` (array)
- `title` (string)

### `html_links` (~125 tokens)

Extract up to 200 links and resolve HTTP(S) destinations against the supplied page URL. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `links` (array)
- `total` (number)
- `truncated` (boolean)

### `html_headings` (~122 tokens)

Extract up to 200 headings with parent indices and skipped-level indicators. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `headings` (array)
- `total` (number)
- `truncated` (boolean)

### `html_forms` (~124 tokens)

Describe up to 30 forms and their controls without returning field values or submitting anything. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `forms` (array)
- `scope` (string)
- `truncated` (boolean)

### `html_images` (~126 tokens)

Extract up to 200 image URLs, alt text and source attributes; does not fetch images. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `images` (array)
- `scope` (string)
- `total` (number)
- `truncated` (boolean)

### `html_feeds` (~125 tokens)

Discover up to 50 RSS, Atom and JSON Feed links declared in supplied HTML. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `feeds` (array)
- `truncated` (boolean)

### `data_json_pointer` (~128 tokens)

Select JSON values with up to 100 RFC 6901 pointer strings, preserving missing versus null. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `selections` (array)

### `data_json_diff` (~120 tokens)

Compare JSON structures and return bounded changes at JSON Pointer paths. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `changes` (array)
- `equal` (boolean)
- `scope` (string)
- `truncated` (boolean)

### `data_json_canonical` (~126 tokens)

Serialize JSON with sorted object keys for deterministic comparison; not RFC 8785 certification. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `profile` (string)
- `text` (string)

### `security_jwt_inspect` (~125 tokens)

Decode untrusted JWT claims and optionally compare timestamps; never verifies a signature. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `claims` (object)
- `expired` (boolean|null)
- `header` (object)
- `notYetValid` (boolean|null)
- `scope` (string)
- `signatureVerified`
- `warnings` (array)

### `security_csp_audit` (~124 tokens)

Parse a supplied Content Security Policy and flag selected risky or missing directives. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `directives` (array)
- `findings` (array)
- `scope` (string)

### `security_header_audit` (~125 tokens)

Review supplied response headers for selected security and CORS issues without echoing values. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `findings` (array)
- `headerNames` (array)
- `scope` (string)

### `security_cookie_audit` (~129 tokens)

Check up to 50 Set-Cookie headers for security attributes and prefix rules; masks cookie values. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `cookies` (array)
- `scope` (string)

### `agents_env_template_check` (~122 tokens)

Compare environment-variable names against a template; never returns assignment values. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `duplicateNames` (array)
- `extra` (array)
- `missing` (array)
- `scope` (string)
- `templateDuplicateNames` (array)
- `unrecognizedLines` (object)

### `agents_tool_name_conflicts` (~125 tokens)

Find duplicate or easily confused tool names after Unicode, case and separator normalization. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `conflicts` (array)
- `scope` (string)

### `text_chunk` (~126 tokens)

Split text into at most 200 overlapping chunks with offsets and intact UTF-16 surrogate pairs. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `chunks` (array)
- `count` (number)
- `offsetUnit` (string)

### `commerce_gtin_validate` (~141 tokens)

Validate GTIN-8, UPC/GTIN-12, EAN/GTIN-13 and GTIN-14 check digits; no product lookup. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `expectedCheckDigit` (string|null)
- `format` (string)
- `scope` (string)
- `valid` (boolean)

### `commerce_variant_compare` (~124 tokens)

Compare requested product attributes with an offered variant and list missing or mismatched fields. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `extra` (array)
- `matches` (boolean)
- `mismatched` (array)
- `missing` (array)
- `scope` (string)

### `commerce_pack_plan` (~134 tokens)

Choose the lowest-cost whole-pack combination for a required count with exact prices and explicit pack limits; up to 20 interchangeable offers. PAID: 800 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `currency` (string)
- `excessUnits` (integer|null)
- `feasible` (boolean)
- `itemSubtotal` (string|null)
- `lines` (array)
- `minorUnitDigits` (number)
- `packCount` (integer|null)
- `requiredUnits` (number)
- `scope` (string)
- `totalUnits` (integer|null)

### `commerce_money_parse` (~134 tokens)

Normalize up to 50 displayed prices with explicit locale, currency and decimal scale; exact amounts, strict grouping and per-price errors. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `acceptedCurrencyTokens` (array)
- `allValid` (boolean)
- `amounts` (array)
- `currency` (string)
- `locale` (string)
- `minorUnitDigits` (number)
- `scope` (string)

### `commerce_offer_extract` (~130 tokens)

Extract bounded Product offers from supplied JSON-LD HTML with source pointers, missing-price warnings and separate aggregate ranges. PAID: 800 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `invalidBlocks` (number)
- `offers` (array)
- `productsFound` (number)
- `productsWithoutOffers` (number)
- `scope` (string)
- `truncated` (boolean)
- `unresolvedReferences` (number)
- `unsupportedOffers` (number)

### `commerce_unit_price` (~132 tokens)

Compare up to 50 explicit pack prices with exact arithmetic across compatible mass, volume or count units; no currency conversion. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `cheapestIds` (array)
- `currency` (string)
- `offers` (array)
- `reference` (object)
- `scope` (string)

### `commerce_price_components` (~135 tokens)

Reconcile item, discount, shipping, tax and fee amounts using exact decimals; missing costs stay unknown and declared totals can be checked. PAID: 500 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `currency` (string)
- `difference` (string|null)
- `itemSubtotal` (string)
- `knownTotal` (string)
- `lineDiscounts` (string)
- `lines` (array)
- `matchesDeclaredTotal` (boolean|null)
- `minorUnitDigits` (number)
- `missingComponents` (array)
- `orderDiscount` (string)
- `scope` (string)
- `total` (string|null)

### `commerce_main_product` (~135 tokens)

Identify the main Product or ProductGroup from supplied JSON-LD HTML using identity, mainEntity and canonical evidence; abstain on ambiguity. PAID: 800 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `candidates` (array)
- `canonicalUrl` (string|null)
- `distinctProducts` (number)
- `pageTypes` (array)
- `reason` (string)
- `scope` (string)
- `selected`
- `selectedId` (string|null)
- `status` (string)
- `warnings` (array)

### `commerce_pack_size_normalize` (~134 tokens)

Normalize locale-explicit pack-size expressions and multipacks to exact grams, millilitres or counts; reject ambiguous text. PAID: 300 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `allNormalized` (boolean)
- `locale` (string)
- `quantities` (array)
- `scope` (string)

### `commerce_feed_page_compare` (~134 tokens)

Compare supplied feed identity, price, currency and availability with selected JSON-LD product evidence; preserve conflicts and unknown fields. PAID: 1000 micro-dollar service credits per successful call. First use agent_utilities_prepare for this tool. Requires existing credits and a private Authorization header. Reuse prepared arguments for recovery; a new requestId is a new billable operation.

Input parameters:

- `input` (object, required)
- `maxPriceMicroUsd` (integer, required): Explicit maximum new debit; 0 means recovery only.
- `requestId` (string, required): Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty.

Output parameters:

- `checks` (array)
- `evidence`
- `identityStatus` (string)
- `scope` (string)
- `selection` (object)
- `status` (string)
- `warnings` (array)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-workers-agent-utilities-agent-utilities-agent-utilities/mcp-remote#diagnostics

## Score history

- 2026-09-27: 71
- 2026-09-26: 70
- 2026-09-25: 70
- 2026-09-24: 70
- 2026-09-23: 69
- 2026-09-22: 69
- 2026-09-21: 68
- 2026-09-20: 68
- 2026-09-19: 67

## Common questions

### What is the Agent Utilities Hosted MCP server?

Agent Utilities Hosted is an MCP server listed in the public MCP registry as dev.workers.agent-utilities.agent-utilities/agent-utilities. Product identity, pack sizes and feed/page checks. Free small trials; paid calls from $0.0003. This page covers its hosted endpoint (https://agent-utilities.agent-utilities.workers.dev/mcp/remote).

### Is the Agent Utilities Hosted MCP server safe to use?

Agent Utilities Hosted scores 71 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 Agent Utilities Hosted MCP server expose?

Agent Utilities Hosted exposes 48 tools: agent_utilities_main_product_preview, agent_utilities_pack_size_normalize_preview, agent_utilities_feed_page_compare_preview, agent_utilities_offer_preview, agent_utilities_pack_preview, and 43 more. Their descriptions and schemas cost roughly 5,663 tokens of context every time the server is loaded.

### Does the Agent Utilities Hosted MCP server require authentication?

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

### Is the Agent Utilities Hosted MCP server still maintained?

Agent Utilities Hosted is still listed as active in the MCP registry. We last reached this channel on 27 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agent-utilities.agent-utilities.workers.dev/mcp/remote
- Website: https://agent-utilities.agent-utilities.workers.dev/integrations/agents?utm_source=mcp-registry
- Changelog RSS feed: https://verifymcp.io/servers/dev-workers-agent-utilities-agent-utilities-agent-utilities/mcp-remote.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-workers-agent-utilities-agent-utilities-agent-utilities/mcp-remote.json
- HTML version of this page: https://verifymcp.io/servers/dev-workers-agent-utilities-agent-utilities-agent-utilities/mcp-remote