# Agent Utility Network (AveDaris) (remote · api.avedaris.com)

Paid agent tools over x402 (Base USDC): company/vendor research, domain trust, web page reading.

- Trust score: 76/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.avedaris.com`: 76/100 (this document), [markdown](https://verifymcp.io/servers/com-avedaris-agent-utility-network/api.md), [page](https://verifymcp.io/servers/com-avedaris-agent-utility-network/api)

## Channel facts

- Endpoint: `https://api.avedaris.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.6.0`

## 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 2026-11-21.

- **Endpoint Security**: 66/100
  - 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 enforcement could not be verified: the plaintext port answered with HTTP 406, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1627 tokens (~116/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 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 Utility Network (AveDaris) MCP server?

Agent Utility Network (AveDaris) is a hosted endpoint at https://api.avedaris.com/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 com-avedaris-agent-utility-network 'https://api.avedaris.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-avedaris-agent-utility-network": {
      "url": "https://api.avedaris.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-avedaris-agent-utility-network": {
      "type": "http",
      "url": "https://api.avedaris.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-avedaris-agent-utility-network]
url = "https://api.avedaris.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-avedaris-agent-utility-network": {
      "type": "remote",
      "url": "https://api.avedaris.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-avedaris-agent-utility-network --url 'https://api.avedaris.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-avedaris-agent-utility-network:
    url: "https://api.avedaris.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-avedaris-agent-utility-network": {
      "Transport": "http",
      "Url": "https://api.avedaris.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-avedaris-agent-utility-network -t streamable-http -u 'https://api.avedaris.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-avedaris-agent-utility-network": {
      "type": "http",
      "url": "https://api.avedaris.com/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 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 74, +44)

- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.40
- [functional improvement] MCP protocol: unverified → pass

### 2026-11-16 (score 30, −43)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.33 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Authorization: partial → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-11-15 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 72, +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.

### 2026-11-10 (score 71, +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.

### 2026-11-08 (score 70, +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.

## MCP tools (14)

### `json_repair` (~82 tokens)

Repair malformed JSON

Repair common malformed JSON (single quotes, trailing commas, unquoted keys) and return valid structured JSON. Paid: $0.005 USDC per call via x402 on Base. Calling without payment returns the payment requirement; invalid input is not charged.

Input parameters:

- `input` (string, required): Malformed JSON text to repair, e.g. {'hello':'world',}

### `entity_normalize` (~77 tokens)

Normalize an entity name

Normalize an organization or entity name into a deterministic canonical form and tokens for matching and dedupe. Paid: $0.005 USDC per call via x402 on Base. Calling without payment returns the payment requirement; invalid input is not charged.

Input parameters:

- `name` (string, required): Organization or entity name, e.g. Acme, Inc.

### `text_extract_signals` (~87 tokens)

Extract signals from text

Extract URLs, emails, money amounts, and ISO dates from free text as structured lists. Paid: $0.008 USDC per call via x402 on Base. Calling without payment returns the payment requirement; invalid input is not charged.

Input parameters:

- `text` (string, required): Text to scan, e.g. Email ops@example.com on 2026-08-30 about $25.

### `web_read_batch` (~144 tokens)

Read up to 5 web pages as Markdown

Read up to 5 public URLs in one call. Each URL returns its own status, final URL, title, main content as Markdown, truncated flag, byte and char counts and error code; one failing URL never fails the rest. Not charged if no URL can be read. Paid: $0.015 USDC per call via x402 on Base. Calling without payment returns the payment requirement; invalid input is not charged.

Input parameters:

- `maxCharsPerUrl` (integer): Optional Markdown cap per URL, default 8,000.
- `urls` (array, required): 1 to 5 public http(s) URLs, e.g. ["https://example.com/"].

### `vendor_intelligence` (~164 tokens)

Research a company (vendor due diligence)

Company research and vendor due diligence: send a company name and official website, get a sourced profile (summary, official-site facts, public contact emails, recent mentions, evidence score, sources, limitations) for company lookup, supplier checks and KYB pre-screens from public web evidence. Not legal identity, credit or registry data. Paid: $0.04 USDC per call via x402 on Base. Calling without payment returns the payment requirement; invalid input is not charged.

Input parameters:

- `name` (string, required): Company name, e.g. Example, Inc.
- `objective` (string): Optional research question, e.g. Is this a legitimate supplier of industrial pumps?
- `websiteUrl` (string, required): Official http(s) website, e.g. https://example.com/

### `domain_rdap_lookup` (~106 tokens)

Look up domain age and registration (RDAP)

Domain age and registration from public RDAP: registration, expiry and last-changed dates, age in days, registrar, status flags and nameservers. Uncharged if a data source is down. Paid: $0.003 USDC per call via x402 on Base. Calling without payment returns the payment requirement; invalid input is not charged.

Input parameters:

- `domain` (string, required): Domain to check, e.g. example.com. An email address or URL is reduced to its domain.

### `email_auth_check` (~120 tokens)

Check email authentication (SPF, DMARC, DKIM, MX)

Check a sending domain's MX, SPF, DMARC and DKIM (common selectors) over public DNS and get pass/weak/missing per check, findings and a 0-100 score. No mail is sent. Uncharged if a data source is down. Paid: $0.003 USDC per call via x402 on Base. Calling without payment returns the payment requirement; invalid input is not charged.

Input parameters:

- `domain` (string, required): Domain to check, e.g. example.com. An email address or URL is reduced to its domain.

### `domain_trust_score` (~126 tokens)

Score whether to trust a domain

One-call domain vetting: RDAP age and status, DNS, MX, SPF, DMARC, DKIM and an HTTPS probe combined into a 0-100 score, a low_risk/review/high_risk verdict and reason codes. Uncharged if a data source is down. Paid: $0.01 USDC per call via x402 on Base. Calling without payment returns the payment requirement; invalid input is not charged.

Input parameters:

- `domain` (string, required): Domain to check, e.g. example.com. An email address or URL is reduced to its domain.

### `vendor_watch_recheck` (~127 tokens)

Re-check a supplier for changes

Fresh public snapshot of a supplier domain (site up/down and redirect host, registrar, registry status, DNS, MX/SPF/DMARC, trust verdict) plus whether anything changed since the last stored check. Use vendor_what_changed for the full diff. Uncharged if a data source is down. Paid: $0.005 USDC per call via x402 on Base. Calling without payment returns the payment requirement; invalid input is not charged.

Input parameters:

- `domain` (string, required): Supplier domain, e.g. example.com. An email address or URL is reduced to its domain.

### `vendor_what_changed` (~119 tokens)

Report what changed at a supplier

Every field that changed at a supplier domain since the previous stored check, with before/after values and high/medium/low severity, a one-line summary, recent change history and a fresh snapshot. Public signals only. Uncharged if a data source is down. Paid: $0.01 USDC per call via x402 on Base. Calling without payment returns the payment requirement; invalid input is not charged.

Input parameters:

- `domain` (string, required): Supplier domain, e.g. example.com. An email address or URL is reduced to its domain.

### `search_utilities` (~122 tokens)

Search AUN utilities (free)

Free and read-only; never charges. Start here to pick one of the public paid utilities for a job. Returns ranked matches with id, method, URL, price and a one-line summary. Leave task empty to list every utility.

Input parameters:

- `limit` (integer): Maximum results, default 10.
- `maxPriceUsd` (number): Only return utilities at or below this price per call, e.g. 0.005.
- `task` (string): Plain-language job, e.g. check a supplier company or fix broken JSON. Empty lists all.

### `get_utility_details` (~89 tokens)

Get a utility's full contract (free)

Free and read-only; never charges. Use after search_utilities to see everything needed before paying: method, URL, price, payment terms, input fields, a valid example body and an example output.

Input parameters:

- `utility` (string, required): Utility id, route key, path or full URL, e.g. vendor.intelligence, json-repair, /v1/paid/dns-lookup.

### `get_call_snippet` (~84 tokens)

Get a ready-to-run paid request (free)

Free and read-only; never charges or sends a request. Returns the x402 payment steps plus curl and JavaScript that call the chosen utility with a working example body over HTTP.

Input parameters:

- `utility` (string, required): Utility id, route key, path or full URL, e.g. vendor.intelligence, json-repair, /v1/paid/dns-lookup.

### `network_capabilities` (~180 tokens)

Find the right AUN utility (free)

Free. Find the right paid AUN utility for a task and get its x402 HTTP path and price. Covers all public utilities, including vendor.intelligence (company research, company lookup, vendor checks, supplier and KYB pre-screening from public web evidence, $0.04; also a paid MCP tool, vendor_intelligence) and $0.001 primitives (json.validate, url.parse, text.slugify, email.normalize, uuid.validate, base64, querystring). Example: {"task":"research a vendor company website"}. Omit task for the full catalog.

Input parameters:

- `budgetUsd` (number): Optional maximum price per call in USD, e.g. 0.01.
- `task` (string): Plain-language job to do, e.g. repair this JSON or research a supplier company. Omit to list all utilities.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-avedaris-agent-utility-network/api#diagnostics

## Score history

- 2026-11-21: 76
- 2026-11-20: 75
- 2026-11-19: 75
- 2026-11-18: 74
- 2026-11-17: 74
- 2026-11-16: 30
- 2026-11-15: 73
- 2026-11-14: 72
- 2026-11-13: 72
- 2026-11-12: 71
- 2026-11-11: 71
- 2026-11-10: 71
- 2026-11-09: 70
- 2026-11-08: 70
- 2026-11-07: 69
- 2026-11-06: 69
- 2026-11-05: 68

## Common questions

### What is the Agent Utility Network (AveDaris) MCP server?

Agent Utility Network (AveDaris) is an MCP server listed in the public MCP registry as com.avedaris/agent-utility-network. Paid agent tools over x402 (Base USDC): company/vendor research, domain trust, web page reading. This page covers its hosted endpoint (https://api.avedaris.com/mcp).

### Is the Agent Utility Network (AveDaris) MCP server safe to use?

Agent Utility Network (AveDaris) scores 76 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 Utility Network (AveDaris) MCP server expose?

Agent Utility Network (AveDaris) exposes 14 tools: json_repair, entity_normalize, text_extract_signals, web_read_batch, vendor_intelligence, and 9 more. Their descriptions and schemas cost roughly 1,627 tokens of context every time the server is loaded.

### Does the Agent Utility Network (AveDaris) MCP server require authentication?

No. We connected to Agent Utility Network (AveDaris) without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Agent Utility Network (AveDaris) MCP server still maintained?

Agent Utility Network (AveDaris) 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 Agent Utility Network (AveDaris) MCP server?

VerifyMCP ran 12 checks on Agent Utility Network (AveDaris), covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Agent Utility Network (AveDaris): HTTPS. 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://api.avedaris.com/mcp
- Repository: https://github.com/SchedNestCEO/agent-utility-network
- Website: https://api.avedaris.com/docs
- Changelog RSS feed: https://verifymcp.io/servers/com-avedaris-agent-utility-network/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-avedaris-agent-utility-network/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-avedaris-agent-utility-network/api.json
- HTML version of this page: https://verifymcp.io/servers/com-avedaris-agent-utility-network/api
