# Permits Engine — Agent Market (remote · agents.ustechautomations.com)

Free MCP tools: permit quotes, jurisdiction index, track record, attestation.

- Trust score: 0/100 (low)
- Change this week: −61
- Registry status: active
- Liveness: dead
- Owner verified: no
- Last scored: 2026-09-14

> **Dead**: every channel of this server has been unreachable for long enough to be marked dead. Its trust score is pinned to 0 and does not recover automatically.

## Components

- remote · `agents.ustechautomations.com`: 0/100 (this document), [markdown](https://verifymcp.io/servers/ustechautomations-usta-agent-market-mcp/agents.md), [page](https://verifymcp.io/servers/ustechautomations-usta-agent-market-mcp/agents)

## Channel facts

- Endpoint: `https://agents.ustechautomations.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 2026-09-14.

- **Endpoint Security**: 11/100
  - TLS not yet verified: we couldn't open a connection to check the certificate.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS not yet verified: we couldn't read the response headers to check for it.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but we couldn't connect to verify it.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the Permits Engine — Agent Market MCP server?

Permits Engine — Agent Market is a hosted endpoint at https://agents.ustechautomations.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 ustechautomations-usta-agent-market-mcp 'https://agents.ustechautomations.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ustechautomations-usta-agent-market-mcp": {
      "url": "https://agents.ustechautomations.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ustechautomations-usta-agent-market-mcp": {
      "type": "http",
      "url": "https://agents.ustechautomations.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ustechautomations-usta-agent-market-mcp]
url = "https://agents.ustechautomations.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ustechautomations-usta-agent-market-mcp": {
      "type": "remote",
      "url": "https://agents.ustechautomations.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ustechautomations-usta-agent-market-mcp --url 'https://agents.ustechautomations.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ustechautomations-usta-agent-market-mcp:
    url: "https://agents.ustechautomations.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ustechautomations-usta-agent-market-mcp": {
      "Transport": "http",
      "Url": "https://agents.ustechautomations.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ustechautomations-usta-agent-market-mcp -t streamable-http -u 'https://agents.ustechautomations.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ustechautomations-usta-agent-market-mcp": {
      "type": "http",
      "url": "https://agents.ustechautomations.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.

### 2026-09-14 (score 0, −12)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-09-13 (score 12, −12)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-09-12 (score 24, −13)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-09-11 (score 37, −12)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-09-10 (score 49, −12)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-09-08 (score 61, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] HSTS header: fail → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] TLS certificate: pass → unverified
- [security regression] Stability: 0.03 → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-09-07 (score 61, 0)

- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “claim_source_receipt”

### 2026-09-06 (score 61)

First indexed and scored.

## MCP tools (16)

### `jurisdiction_index` (~17 tokens)

List all AZ jurisdictions with permit data available.

### `verified_track_record` (~143 tokens)

This house's verified prediction track record — per-loop calibration scores (Brier, ECE, MCE, ROC-AUC, coverage, base rate) computed monthly from sealed prediction snapshots against observed public outcomes, with a reproducible content-sha256 seal. Bad numbers are published alongside good ones. Free: verify the record before buying any paid feed.

Input parameters:

- `include_reliability` (boolean): Include each loop's per-bin reliability curve (mean predicted vs mean observed per probability bin).
- `loop` (string): Optional loop-name filter (e.g. 'permits:psir_prob'). Case-insensitive exact match; an unknown loop returns count=0.

### `seal_lookup` (~152 tokens)

Verify whether a SHA-256 (or artifact filename) was sealed into this house's OTS/Bitcoin-anchored priority manifest, and when. Proof-of-priority lookup at the cheapest possible price so an agent can exercise the paid rail end-to-end. Returns an Ed25519-signed receipt.

Input parameters:

- `artifact` (string): Artifact filename (case-insensitive exact match, e.g. 'dcbi_2026-06-22.json'). Provide this or sha256, never both.
- `sha256` (string): 64-hex-char SHA-256 to look up. Matches either the sealed artifact's content_sha256 or its sha256_file. A hash not in the manifest returns found=false.

### `agent_attestation` (~206 tokens)

What this house can attest about another agent: ERC-8004 registry events + liveness probes (sealed on-chain census), collected public incident candidates, sealed first-report sea protests, and aggregate first-party x402 payment observations for a payer wallet. Text/identifier matching — not verified identity, not a reputation score. Sources degrade individually and honestly.

Input parameters:

- `agent_id` (string): Optional exact ERC-8004 agent id (registry token id). Overrides text matching for the registry source; combine with chain to disambiguate.
- `chain` (string): Optional chain filter for the ERC-8004 registry source (e.g. 'base', 'optimism'). Case-insensitive exact match.
- `limit` (integer): Max matches per source (1-100, default 20).
- `query` (string, required): Agent identifier to look up: a name, an agent-URI substring, or a 0x wallet address (an address also unlocks first-party payment observations).

### `claim_source_receipt` (~124 tokens)

Fetch a public URL ourselves, hash it, and return a signed record of whether the claim's numbers or quoted words appear in it. Free. Not a truth judgment.

Input parameters:

- `claim` (string, required): A sentence that must contain at least one number or one quoted phrase. The tool records whether those tokens appear in the fetched source; it is not a judgment that the claim is true.
- `source_url` (string, required): Public http or https URL to GET. The tool fetches this URL itself, hashes the bytes, and signs the record. Free. GET-only.

### `request_quote` (~244 tokens)

Store one consent-bound, agent-attributed quote request for a canonical US Tech Automations offer priced at $200 or more. A human reviews it; no message, charge, checkout, contract, or work start occurs automatically.

Input parameters:

- `agent_name` (string, required): Agent product or runtime name for source attribution.
- `agent_version` (string)
- `company` (string)
- `email` (string, required): Reply address for the consenting human. Stored privately; never returned.
- `human_authorized` (boolean, required): True only when the named human authorized this agent to file this scope.
- `idempotency_key` (string, required): Opaque non-PII retry key, such as a UUID. The server stores only its SHA-256.
- `name` (string)
- `scope` (string, required): Coarse business scope only. No URLs, credentials, code, files, or private, customer, personal, medical, or regulated data.
- `sku` (string, required): Canonical US Tech Automations offer SKU priced at $200 or more.
- `transactional_email_consent` (boolean, required): True only when that human consents to a human reply about this quote request.

### `permit_lookup` (~45 tokens)

Look up permit fees, turnaround, required docs for a jurisdiction.

Input parameters:

- `jurisdiction` (string, required): Slug like 'phoenix' or 'gilbert'. Use jurisdiction_index to enumerate.

### `rebate_eligibility_check` (~65 tokens)

Find rebate programs and eligible measures for an AZ service area.

Input parameters:

- `jurisdiction` (string, required): AZ jurisdiction slug. Used to filter to programs serving that area.
- `measure` (string): Optional measure filter: 'HVAC', 'Heat Pump', 'Solar', etc.

### `search_permits` (~65 tokens)

FTS5 search across the permit corpus (jurisdictions, rebates, templates).

Input parameters:

- `limit` (integer)
- `query` (string, required): FTS5 query across jurisdictions, rebates, templates.
- `record_type` (string): Optional filter to a single record type.

### `verify_contractor_license` (~108 tokens)

Verify a contractor license and (optionally) cross-reference jurisdiction permit context. Returns an Ed25519-signed receipt the agent can store as proof of verification.

Input parameters:

- `jurisdiction` (string): Optional jurisdiction slug — if given, the response includes the jurisdiction's permit context so an agent doesn't need a second paid call to find fees / required documents.
- `license_number` (string, required): Contractor license number (e.g. 'ROC123456'). Spaces stripped; matched case-insensitively.

### `datacenter_site_changes` (~149 tokens)

Per-site Datacenter Buildout Activity Index — observed ground-activity state (Sentinel-2 bare-soil/earthworks change) for each publicly-announced datacenter site, with a content-sha256 attestation. The per-site granularity the free public page omits. Returns an Ed25519-signed receipt.

Input parameters:

- `min_confidence` (string): Optional floor on per-site confidence.
- `operator` (string): Optional operator substring filter (case-insensitive).
- `state` (string): Optional activity-state filter (the per-site `state` field, e.g. 'active_earthworks', 'stable_no_change', 'insufficient_data'). Lowercase exact value.

### `datacenter_operator_breakdown` (~60 tokens)

Operator-level Datacenter Buildout Activity Index — index headline, state counts, and per-operator assessable/active tallies from the latest sealed issue, with a content-sha256 attestation. Returns an Ed25519-signed receipt.

### `web_policy_history` (~197 tokens)

Per-domain agent-access policy history — exact-date sealed declarations for robots.txt / ai.txt / llms.txt / TDM-Rep, with row, retained-body and collection-membership verification. A pre-coverage date returns NOT-HELD without inference. The existing timeline view remains available when no date is given. Returns an Ed25519-signed receipt.

Input parameters:

- `date` (string): Optional exact capture date. The response is HELD only for rows sealed on this date; pre-coverage and missing dates return NOT-HELD without carrying another value.
- `domain` (string, required): Registrable domain to look up (e.g. 'openai.com'). Lowercased; must be in the sealed Tranco top-100k universe to have history (a miss returns count=0).
- `limit` (integer): Max snapshot rows returned (newest first).
- `resource` (string): Optional filter to one policy surface.

### `enclosure_evidence_pack` (~205 tokens)

Per-incident enclosure evidence pack — one domain's observed policy-surface change (robots.txt / ai.txt / llms.txt / TDM-Rep) as a self-contained bundle: before/after observations, the stored response bodies re-hashed at read time, and the per-day custody record (rows in store vs rows batch-committed, gaps disclosed). Sealed-run attestation. Returns an Ed25519-signed receipt.

Input parameters:

- `domain` (string, required): Domain whose policy-surface change to document (lowercased, e.g. 'flickr.com').
- `event_date` (string): Optional change-event date (YYYY-MM-DD) to select a specific incident; default = the most recent change. A date with no change event returns incident_found=false.
- `include_bodies` (boolean): Include the stored before/after response bodies, re-hashed at read time (default true).
- `resource` (string): Policy surface (default 'robots').

### `agentic_commerce_adoption` (~112 tokens)

Agentic-commerce adoption snapshot — per-merchant presence of the agent-checkout discovery surfaces (ucp, llms.txt, agent cards, MCP documents) across a fixed ~276-merchant panel on the latest sealed day, with the run's batch-sha256 attestation. Returns an Ed25519-signed receipt.

Input parameters:

- `domain` (string): Optional merchant domain — returns that merchant's per-surface rows instead of the panel-wide tally. A domain outside the panel returns count=0.

### `agent_census_stats` (~104 tokens)

ERC-8004 agent-census stats — per-chain registration counts, distinct agents, and URI-scheme mix from the latest sealed on-chain sample, with the run's batch-sha256 attestation and honest per-run chain coverage. Returns an Ed25519-signed receipt.

Input parameters:

- `chain` (string): Optional chain filter (e.g. 'polygon', 'base'). Case-insensitive exact match; a chain absent from the latest sealed day returns count=0.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ustechautomations-usta-agent-market-mcp/agents#diagnostics

## Score history

- 2026-09-14: 0
- 2026-09-13: 12
- 2026-09-12: 24
- 2026-09-11: 37
- 2026-09-10: 49
- 2026-09-09: 61
- 2026-09-08: 61
- 2026-09-07: 61
- 2026-09-06: 61

## Common questions

### What is the Permits Engine — Agent Market MCP server?

Permits Engine — Agent Market is an MCP server listed in the public MCP registry as io.github.USTechAutomations/usta-agent-market-mcp. Free MCP tools: permit quotes, jurisdiction index, track record, attestation. This page covers its hosted endpoint (https://agents.ustechautomations.com/mcp).

### Is the Permits Engine — Agent Market MCP server safe to use?

Permits Engine — Agent Market scores 0 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 Permits Engine — Agent Market MCP server expose?

Permits Engine — Agent Market exposes 16 tools: jurisdiction_index, verified_track_record, seal_lookup, agent_attestation, claim_source_receipt, and 11 more. Their descriptions and schemas cost roughly 1,996 tokens of context every time the server is loaded.

### Does the Permits Engine — Agent Market MCP server require authentication?

Its publisher declares no required credentials for Permits Engine — Agent Market. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

### Is the Permits Engine — Agent Market MCP server still maintained?

Permits Engine — Agent Market has been unreachable for long enough that we treat it as dead, and its score is pinned to zero. We last reached this channel on 7 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://agents.ustechautomations.com/mcp
- Website: https://agents.ustechautomations.com/
- Changelog RSS feed: https://verifymcp.io/servers/ustechautomations-usta-agent-market-mcp/agents.xml
- Changelog JSON feed: https://verifymcp.io/servers/ustechautomations-usta-agent-market-mcp/agents.json
- HTML version of this page: https://verifymcp.io/servers/ustechautomations-usta-agent-market-mcp/agents