# Agent Control — Agent Meter (remote · agent-control.net)

Can I pay this address? ok·new·warn·sink. First 5 free. Then $0.10 USDC/look. Agents pay. No inbox.

- Trust score: 76/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `agent-control.net`: 76/100 (this document), [markdown](https://verifymcp.io/servers/net-agent-control-agent-control/api-v1-mcp.md), [page](https://verifymcp.io/servers/net-agent-control-agent-control/api-v1-mcp)

## Channel facts

- Endpoint: `https://agent-control.net/api/v1/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

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

Scored 2026-09-20.

- **Endpoint Security**: 80/100
  - 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 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**: 64/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2514 tokens (~157/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 85/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 54% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 17 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 Control — Agent Meter MCP server?

Agent Control — Agent Meter is a hosted endpoint at https://agent-control.net/api/v1/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 net-agent-control-agent-control 'https://agent-control.net/api/v1/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "net-agent-control-agent-control": {
      "url": "https://agent-control.net/api/v1/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "net-agent-control-agent-control": {
      "type": "http",
      "url": "https://agent-control.net/api/v1/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.net-agent-control-agent-control]
url = "https://agent-control.net/api/v1/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "net-agent-control-agent-control": {
      "type": "remote",
      "url": "https://agent-control.net/api/v1/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add net-agent-control-agent-control --url 'https://agent-control.net/api/v1/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  net-agent-control-agent-control:
    url: "https://agent-control.net/api/v1/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "net-agent-control-agent-control": {
      "Transport": "http",
      "Url": "https://agent-control.net/api/v1/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add net-agent-control-agent-control -t streamable-http -u 'https://agent-control.net/api/v1/mcp'
```

### Other

```json
{
  "mcpServers": {
    "net-agent-control-agent-control": {
      "type": "http",
      "url": "https://agent-control.net/api/v1/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.

### 2026-09-20 (score 76, 0)

- [security] Tool “meter_watch” rewrote its description, which is the text the model reads
- [cosmetic] “meter_watch” reworded the description of “payment”

### 2026-09-19 (score 76, −1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “meter_buy_pass” rewrote its description, which is the text the model reads
- [security] Tool “meter_preflight” rewrote its description, which is the text the model reads
- [security] Tool “meter_pricing” rewrote its description, which is the text the model reads
- [security] Tool “meter_scan” rewrote its description, which is the text the model reads
- [security] Tool “meter_scan_batch” rewrote its description, which is the text the model reads
- [security] Tool “meter_stamp” rewrote its description, which is the text the model reads
- [security] Tool “meter_verify_stamp” rewrote its description, which is the text the model reads
- [security] Tool “meter_watch” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 121 → 153
- [cosmetic] “meter_buy_pass” reworded the description of “sku”

### 2026-09-18 (score 77, +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.

### 2026-09-17 (score 76, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “meter_buy_pass” rewrote its description, which is the text the model reads
- [security] Tool “meter_preflight” rewrote its description, which is the text the model reads
- [security] Tool “meter_pricing” rewrote its description, which is the text the model reads
- [security] Tool “meter_scan” rewrote its description, which is the text the model reads
- [security] Tool “meter_watch” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 49% → 54%
- [cosmetic] “meter_buy_pass” added an optional parameter “payment”
- [cosmetic] “meter_watch” added an optional parameter “payment”
- [cosmetic] “meter_buy_pass” reworded the description of “pass_token”
- [cosmetic] “meter_buy_pass” reworded the description of “sku”

### 2026-09-16 (score 76, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “meter_buy_pass” rewrote its description, which is the text the model reads
- [security] Tool “meter_preflight” rewrote its description, which is the text the model reads
- [security] Tool “meter_pricing” rewrote its description, which is the text the model reads
- [security] Tool “meter_scan” rewrote its description, which is the text the model reads
- [security] Tool “meter_scan_batch” rewrote its description, which is the text the model reads
- [security] Tool “meter_stamp” rewrote its description, which is the text the model reads
- [security] Tool “meter_verify_stamp” rewrote its description, which is the text the model reads
- [security] Tool “meter_watch” rewrote its description, which is the text the model reads

### 2026-09-15 (score 76, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “meter_buy_pass” rewrote its description, which is the text the model reads
- [security] Tool “meter_pricing” rewrote its description, which is the text the model reads
- [security] Tool “meter_watch” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 88 → 103
- [functional improvement] Tool coverage: 43% → 49%
- [cosmetic] “meter_buy_pass” added an optional parameter “signature”
- [cosmetic] “meter_watch” added an optional parameter “signature”
- [cosmetic] “meter_buy_pass” reworded the description of “proof”
- [cosmetic] “meter_buy_pass” reworded the description of “sku”
- [cosmetic] “meter_watch” reworded the description of “invoice_id”

### 2026-09-14 (score 75, +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.

### 2026-09-12 (score 74, +2)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “meter_buy_pass” rewrote its description, which is the text the model reads
- [security] Tool “meter_preflight” rewrote its description, which is the text the model reads
- [security] Tool “meter_pricing” rewrote its description, which is the text the model reads
- [security] Tool “meter_scan” rewrote its description, which is the text the model reads
- [security] Tool “meter_scan_batch” rewrote its description, which is the text the model reads
- [security] Tool “meter_stamp” rewrote its description, which is the text the model reads
- [security] Tool “meter_verify_stamp” rewrote its description, which is the text the model reads
- [security] Tool “meter_watch” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 70 → 88
- [cosmetic] “meter_buy_pass” reworded the description of “sku”

## MCP tools (16)

### `meter_pricing` (~118 tokens)

Agent Meter pricing

Can I pay this address? First 5 free. After free-5, buy looks_20 pack ($0.20) → X-Agent-Pass; look $0.10 is optional one-shot. No inbox. Public catalog from this tool: look, looks_20, addresses_100, stamp_tx. default_sku is look. paid_sku looks_20. Base USDC (EIP-3009 exact) and Solana USDC. No email. No API key. Human App $29 plans are separate.

### `meter_buy_pass` (~447 tokens)

Buy an Agent Meter pass

Can I pay this address? First 5 free. After free-5, buy looks_20 pack ($0.20) → X-Agent-Pass; look $0.10 is optional one-shot. No inbox. After free-5, call with sku looks_20 (or omit) to buy a pack that mints/extends X-Agent-Pass. look $0.10 is optional one-shot. Returns a payable invoice as tool content (ok:true / status payment_required) with pay_to, base_pay_to, accepts (Base USDC EIP-3009 exact and Solana USDC), amount_usd, amount_base_units, reference, pay_url, invoice_id, watch_url, adapter_url, base_adapter_url, preferred_rail, pay_page, next_tool, tool_fields, sign_exact, adapter_snippet, next_steps. Prefer Base EIP-3009 exact to base_pay_to (CDP/AgentKit; no Solana key) then meter_watch with payment. Use sign_exact + adapter_snippet to finish in-process (payMeterPassBase / signTypedData). Fetch base_adapter_url only if you need the full file. Optional Solana: fetch adapter_url. 402 invoice includes pay_page for Phantom laptop as a last resort. We never take keys. Packs: looks_20 / addresses_100 / stamp_tx. No human account.

Input parameters:

- `pass_token` (string): Existing X-Agent-Pass to extend with a pack.
- `payment` (object): Optional Base EIP-3009 exact payload. Same JSON as PAYMENT-SIGNATURE. Never send a secret key.
- `proof` (object): Payment proof. { type: dev } only when METER_DEV_GRANT=1. Never send a secret key.
- `signature` (string): Optional on-chain tx signature after you sign locally. Not a private key.
- `sku` (string): Catalog id from meter_pricing. Omit or looks_20 is the pack after free-5. look $0.10 is optional one-shot. Packs: looks_20, addresses_100, stamp_tx. pass_1h stays in catalog only.

### `meter_watch` (~254 tokens)

Watch a Meter invoice

Can I pay this address? First 5 free. After free-5, buy looks_20 pack ($0.20) → X-Agent-Pass; look $0.10 is optional one-shot. No inbox. After Base EIP-3009 exact (CDP/AgentKit; no Solana key) or optional Solana USDC, call with invoice_id until token. Pass the Base payment object from payMeterPassBase / sign_exact.payment_template after you fill signature ({ x402Version, payload:{ authorization, signature }, accepted }) — not a raw signature string. Repeat until the result includes token — that is X-Agent-Pass. Then meter_scan with pass_token. Optional signature (tx sig only). We never take keys. No human account.

Input parameters:

- `invoice_id` (string): From meter_buy_pass / 402 invoice.
- `payment` (object): Base x402 v2 payment object from payMeterPassBase / sign_exact.payment_template (x402Version + payload.authorization + payload.signature + accepted). Not a raw signature string. Never send a secret k…
- `signature` (string): Optional Solana tx signature after local sign. Not a private key.
- `sku` (string)

### `meter_scan` (~192 tokens)

Scan a destination

Can I pay this address? First 5 free. After free-5, buy looks_20 pack ($0.20) → X-Agent-Pass; look $0.10 is optional one-shot. No inbox. One look = one address. Send X-Agent-Pass with any string; first 5 looks on that id are free; then 402 looks_20 pack $0.20 (look $0.10 is optional one-shot). Prefer Base USDC (EIP-3009 exact) to base_pay_to (CDP/AgentKit; no Solana key). Optional Solana USDC. 402 invoice includes next_steps and pay_page for Phantom laptop as a last resort. Risk ok|new|warn|sink. Never hold.

Input parameters:

- `address` (string, required)
- `chain` (string, required): solana, ethereum, or base
- `pass_token` (string)

### `meter_preflight` (~175 tokens)

Preflight against a self cap

Can I pay this address? First 5 free. After free-5, buy looks_20 pack ($0.20) → X-Agent-Pass; look $0.10 is optional one-shot. No inbox. One look = one address. Send X-Agent-Pass with any string; first 5 looks on that id are free; then 402 looks_20 pack $0.20. look $0.10 is optional one-shot. Body: chain, wallet, to, value_usd, cap_usd. allow or stop vs cap_usd. Never hold.

Input parameters:

- `cap_usd` (number, required)
- `chain` (string, required)
- `pass_token` (string)
- `to` (string, required)
- `value_usd` (number, required)
- `wallet` (string, required)

### `meter_scan_batch` (~129 tokens)

Scan a batch of destinations

Can I pay this address? First 5 free. After free-5, buy looks_20 pack ($0.20) → X-Agent-Pass; look $0.10 is optional one-shot. No inbox. Risk scores for up to 100 addresses. Sku addresses_100 ($0.15) covers scan_batch. Never hold. ok|new|warn|sink.

Input parameters:

- `addresses` (array, required): Up to 100 addresses
- `chain` (string, required): solana, ethereum, or base
- `pass_token` (string)
- `sku` (string)

### `meter_stamp` (~184 tokens)

Stamp an allow or stop receipt

Can I pay this address? First 5 free. After free-5, buy looks_20 pack ($0.20) → X-Agent-Pass; look $0.10 is optional one-shot. No inbox. stamp_tx $0.05. Merchants can require the stamp_tx $0.05 ticket before accepting agent USDC. Take this ticket or we do not take your USDC. Signed allow|stop receipt. HMAC-SHA256. Merchants verify with meter_verify_stamp before accepting agent USDC.

Input parameters:

- `cap_usd` (number)
- `chain` (string)
- `decision` (string): allow or stop. Optional if value_usd and cap_usd are set.
- `pass_token` (string)
- `to` (string)
- `value_usd` (number)
- `wallet` (string)

### `meter_verify_stamp` (~147 tokens)

Verify a Meter stamp

Can I pay this address? First 5 free. After free-5, buy looks_20 pack ($0.20) → X-Agent-Pass; look $0.10 is optional one-shot. No inbox. Public. Merchants can require the stamp_tx $0.05 ticket before accepting agent USDC. Take this ticket or we do not take your USDC. GET a signed allow|stop receipt by stamp_id before you accept agent USDC. If verified is true and decision is allow, take the USDC. If not, do not take it. No email. No API key.

Input parameters:

- `id` (string)
- `stamp_id` (string)

### `check_transfer` (~77 tokens)

Check a transfer

MUST be called before the agent signs or sends a transfer. Returns allow, alert, hold, or block. If must_abort is true, do not sign. If decision is hold, poll get_approval until allow or block.

Input parameters:

- `to` (string, required): Destination wallet address
- `value_usd` (number, required): Transfer size in USD

### `get_agent_status` (~21 tokens)

Get agent status

Returns whether this agent is paused, expired, or healthy.

### `get_approval` (~47 tokens)

Get approval decision

Poll a held pre-sign check. Pass approval_id from check_transfer. Repeat until decision is allow or block.

Input parameters:

- `approval_id` (string, required): ID returned when check_transfer decision is hold

### `get_pricing` (~59 tokens)

Get pricing

List Agent Control plans and trial truth. Starter $29 / Pro $49 / Team $149. 1-day trial, no card, no KYC. Pay on-chain USDC on Solana. A human principal owns billing and Approval Inbox.

### `start_trial` (~76 tokens)

Start a trial

Invite a human to start the 1-day trial. Provide human_email or an existing principal_id. Agents cannot open a root account. The human owns billing and Approval Inbox.

Input parameters:

- `human_email` (string): Email of the human customer of record
- `principal_id` (string): Existing human user id, if you already have one

### `attach_human` (~66 tokens)

Attach a human

Attach this agent to a human principal (email or existing principal_id). Does not move the agent to a different human. Agents cannot decide Approval Inbox.

Input parameters:

- `human_email` (string): Email of the human customer of record
- `principal_id` (string): Existing human user id

### `create_checkout` (~99 tokens)

Create checkout

Open a pay request on the human principal that owns this agent. Wraps POST /api/v1/billing/checkout. The human pays on-chain USDC (Solana). Not automatic payment. Agents cannot decide Approval Inbox.

Input parameters:

- `asset` (string): usdc (default), sol, or eth
- `chain` (string): solana (default), ethereum, or base
- `plan` (string, required): starter, pro, or team

### `get_status` (~32 tokens)

Get subscription status

Subscription or trial status for the human principal that owns this agent. Does not return Approval Inbox items and cannot approve holds.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/net-agent-control-agent-control/api-v1-mcp#diagnostics

## Score history

- 2026-09-20: 76
- 2026-09-19: 76
- 2026-09-18: 77
- 2026-09-17: 76
- 2026-09-16: 76
- 2026-09-15: 76
- 2026-09-14: 75
- 2026-09-13: 74
- 2026-09-12: 74
- 2026-09-11: 72
- 2026-09-10: 72
- 2026-09-09: 75
- 2026-09-08: 75
- 2026-09-07: 74

## Common questions

### What is the Agent Control — Agent Meter MCP server?

Agent Control — Agent Meter is an MCP server listed in the public MCP registry as net.agent-control/agent-control. Can I pay this address? ok·new·warn·sink. First 5 free. Then $0.10 USDC/look. Agents pay. No inbox. This page covers its hosted endpoint (https://agent-control.net/api/v1/mcp).

### Is the Agent Control — Agent Meter MCP server safe to use?

Agent Control — Agent Meter 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 Control — Agent Meter MCP server expose?

Agent Control — Agent Meter exposes 16 tools: meter_pricing, meter_buy_pass, meter_watch, meter_scan, meter_preflight, and 11 more. Their descriptions and schemas cost roughly 2,123 tokens of context every time the server is loaded.

### Does the Agent Control — Agent Meter MCP server require authentication?

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

### Is the Agent Control — Agent Meter MCP server still maintained?

Agent Control — Agent Meter is still listed as active in the MCP registry. We last reached this channel on 20 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-control.net/api/v1/mcp
- Repository: https://github.com/Cobra-bit-prog/agent-guard
- Website: https://agent-control.net/
- Changelog RSS feed: https://verifymcp.io/servers/net-agent-control-agent-control/api-v1-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/net-agent-control-agent-control/api-v1-mcp.json
- HTML version of this page: https://verifymcp.io/servers/net-agent-control-agent-control/api-v1-mcp