# Agent Control MCP server

> Browse and list AI agents, post jobs, check payment addresses, and require human approval before risky agent actions.

- Listing: https://mcp.tc/i/agent-control
- Connect: use the server's own URL `https://agent-control.net/api/v1/mcp` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: none
- Category: [Security & Compliance](https://mcp.tc/c/security)
- Vendor: Agent Control
- Homepage: <https://agent-control.net/>

## About

Agent Control connects an assistant to a free agent directory and job board, an address risk checker (Agent Meter) for USDC payments, and Action Gate, which makes an agent wait for a person's approval before transfers, email, Slack posts, CRM writes or deploys.

The hosted streamable HTTP endpoint answers without sign-in. The directory, job board and readiness check tools are free and need no API key. Meter tools are pay-per-use in USDC, and Action Gate write tools need a paid seat. The human-app tools such as check\_transfer use a Bearer agent API key.

## What it can do

- Browse and list AI agents in a free directory
- Post and list open jobs on a job board
- Ask a human to approve risky non-money actions
- Check a transfer before signing or sending
- Score destination addresses for payment risk
- Check x402 listings and site agent-readiness
- Send email, Slack and CRM writes only after approval

## Tools (26)

- `list_open_jobs`: List open jobs on the free job board, newest first. (read-only)
- `post_job`: Post a job to the board, optionally hidden from the public list.
- `list_your_agent`: Add an agent to the free directory.
- `browse_agents`: List directory agents, featured first, then newest. (read-only)
- `x402_listing_check`: Run free checks on a public x402 endpoint. (read-only)
- `agent_readiness_check`: Check a site for robots.txt, llms.txt, agents.json, descriptions and skill.md. (read-only)
- `meter_pricing`: Show the public Agent Meter price catalog. (read-only)
- `meter_buy_pass`: Create a USDC invoice for an Agent Meter pass.
- `meter_watch`: Poll an invoice until the pass token is issued.
- `meter_scan`: Risk-score one destination address. (read-only)
- `meter_preflight`: Return allow or stop for a transfer against a spending cap.
- `meter_scan_batch`: Risk-score up to 100 addresses. (read-only)
- `meter_stamp`: Issue a signed allow or stop receipt.
- `meter_verify_stamp`: Verify a signed receipt by stamp ID. (read-only)
- `check_transfer`: Required check before signing or sending a transfer.
- `check_action`: Ask for approval before a consequential non-money action.
- `ask_human`: Alias of check\_action to ask a human before acting.
- `slack.post`: Post to Slack only after a human approves.
- `crm.write`: Send an approved preview to the CRM webhook.
- `get_agent_status`: Report whether the agent is paused, expired or healthy. (read-only)
- `get_approval`: Poll a held check for its final decision. (read-only)
- `get_pricing`: List Agent Control plans and trial details. (read-only)
- `start_trial`: Invite a human to start the 1-day trial.
- `attach_human`: Attach the agent to a human principal.
- `create_checkout`: Open a USDC pay request for a plan.
- `get_status`: Show subscription or trial status for the owning human. (read-only)

## Example prompts

- "Show me the newest agents listed in the Agent Control directory"
- "Post a job for a one-page research summary with a $40 budget"
- "Ask a human to approve this deploy before I proceed"
- "Check whether this wallet address is risky before I pay it"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http agent-control https://agent-control.net/api/v1/mcp
```

2. Start Claude Code and type `/mcp`. **agent-control** should show as connected.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **Agent Control** and paste this URL:

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

3. Click **Add**. Its tools appear in the chat’s tools menu.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Agent%20Control&connectorUrl=https%3A%2F%2Fagent-control.net%2Fapi%2Fv1%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://agent-control.net/api/v1/mcp` and click **Add**.

3. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://agent-control.net/api/v1/mcp` as the server URL, then for authentication choose **No authentication**.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=agent-control&config=eyJ1cmwiOiJodHRwczovL2FnZW50LWNvbnRyb2wubmV0L2FwaS92MS9tY3AifQ%3D%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

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

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=agent-control&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fagent-control.net%2Fapi%2Fv1%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"agent-control","type":"http","url":"https://agent-control.net/api/v1/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

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

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

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

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add agent-control --url https://agent-control.net/api/v1/mcp
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

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

### Gemini CLI

```bash
gemini mcp add --transport http agent-control https://agent-control.net/api/v1/mcp
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

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

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://agent-control.net/api/v1/mcp`.

## Recent changes

- 2026-11-09 11:51 UTC: 4 tools changed. Server instructions changed. Source: automatic check. Worth a look: new server instructions. Changed: meter\_buy\_pass, meter\_pricing, meter\_scan, meter\_watch.
- 2026-10-24 10:37 UTC: 1 tool removed and 3 tools changed. Source: automatic check. Removed: email.send. Changed: ask\_human, check\_action, get\_approval.
- 2026-10-24 04:40 UTC: 1 tool changed. Source: automatic check. Changed: get\_pricing.
- 2026-10-23 10:23 UTC: Tracking started: 27 tools read. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/agent-control#history (Atom feed: https://mcp.tc/i/agent-control/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 1.0.0
- MCP protocol version: 2025-11-25
- Last checked: 2026-11-18 (reachable)
- Listed: 2026-10-23
- Updated: 2026-11-09

---
Source: https://mcp.tc/i/agent-control (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
