Is the Agent Control MCP server down?

mcp-registry/net.agent-control/agent-control · v1.0.0

healthy
Last checked 2026-10-18 01:55 UTC · handshake 159ms

As of 2026-10-18 01:55 UTC, the Agent Control MCP server is up with a Glimind reliability score of 85/100 (grade B). Over the last 30 days it answered 99.8% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 26.4 hours.

uptime (30d checks)
99.8%
checks observed
3,539
outages (90d)
1
tools
27

Can I pay this address? ok·new·warn·sink. Buy looks_20 $0.20 or look $0.10. No inbox.

Install Agent Control MCP server

Add to Cursor Add to VS Code

Claude Code

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

Claude Desktop · Windsurf · Cline (mcpServers JSON)

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

Third-party server, listed as discovered. Review its source before installing.

Agent-readiness: B (84/100)

B (84/100): 0 error(s), 3 warning(s) across 27 tool(s); ~4,903 tokens of tool definitions.
Scores higher than 46% of 15,345 MCP servers Glimind has audited.
Its tool list costs an agent ~4,903 tokens per session — more than 60% of servers.
84 → 84 since 2026-10-17
no tool-poisoning patterns
Schemas100
Descriptions69
Safety hints100
Token cost100
Client compatibility54
Protocol100
Reliability85
Stability80

What to fix (5)

25 parameter(s) across 8 tool(s) have no description.

Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call.

Tools: ask_human, list_your_agent, meter_preflight, meter_scan, meter_scan_batch and 3 more

3 tool name(s) contain "." or exceed 64 characters, which OpenAI-compatible function calling rejects (^[a-zA-Z0-9_-]{1,64}$).

Use "_" or "-" instead of "." and keep names to 64 characters, so clients built on OpenAI-style tool calling don't have to rename (or drop) them.

Tools: crm.write, email.send, slack.post

Handshake + tools/list takes ~1,616 ms.

Serve tools/list from memory, keep the process warm, and host close to your users. Every new agent session pays this before its first call.

No tool declares an outputSchema.

Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably.

In the last 30 days: 0 tool(s) removed and 5 schema change(s).

Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts.

Auto-fix: 3 corrected tool definitions

Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 8 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fnet.agent-control%2Fagent-control/fixes

crm.write 1 change
{
  "name": "crm_write",
  "description": "Write Gate. Validates the preview, runs Action Gate check_action for crm.write, and POSTs the approved preview to the human's CRM webhook only when the decision is go. Unpaid, missing DATABASE_URL, stop, and timeout do not post. If decision is wait, poll get_approval, then call crm.write again with approval_id. If the CRM webhook is missing, returns stop and does not post. Same $49 Action Gate seat (plan=action).",
  "inputSchema": {
    "type": "object",
    "properties": {
      "risk": {
        "type": "string",
        "description": "Optional tag such as low, medium, or high"
      },
      "target": {
        "type": "string",
        "description": "Optional record id"
      },
      "payload": {
        "type": "object",
        "description": "Optional JSON object included in the approved preview"
      },
      "preview": {
        "type": "string",
        "description": "Approved text posted to the CRM webhook"
      },
      "summary": {
        "type": "string",
        "description": "One line a human can decide from"
      },
      "approval_id": {
        "type": "string",
        "description": "From a previous wait. Call again after get_approval returns go."
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false
  },
  "title": "Write to CRM after a human allows it"
}
email.send 1 change
{
  "name": "email_send",
  "description": "Write Gate. Validates the message, runs Action Gate check_action for email.send, and sends only when the decision is go. Unpaid, missing DATABASE_URL, stop, and timeout do not send. If decision is wait, poll get_approval, then call email.send again with approval_id. Uses the human's connected Agentmail inbox. If email is not connected, returns stop and does not send. Same $49 Action Gate seat (plan=action).",
  "inputSchema": {
    "type": "object",
    "properties": {
      "to": {
        "type": "string",
        "description": "One recipient email address"
      },
      "risk": {
        "type": "string",
        "description": "Optional tag such as low, medium, or high"
      },
      "text": {
        "type": "string",
        "description": "Plain-text body the human approves"
      },
      "subject": {
        "type": "string",
        "description": "Subject the human approves"
      },
      "approval_id": {
        "type": "string",
        "description": "From a previous wait. Call again after get_approval returns go."
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false
  },
  "title": "Send email after a human allows it"
}
slack.post 1 change
{
  "name": "slack_post",
  "description": "Write Gate. Validates the message, runs Action Gate check_action for slack.post, and posts only when the decision is go. Unpaid, missing DATABASE_URL, stop, and timeout do not post. If decision is wait, poll get_approval, then call slack.post again with approval_id. Uses the Slack incoming webhook saved in Settings. If that webhook is missing, returns stop and does not post. Same $49 Action Gate seat (plan=action).",
  "inputSchema": {
    "type": "object",
    "properties": {
      "risk": {
        "type": "string",
        "description": "Optional tag such as low, medium, or high"
      },
      "text": {
        "type": "string",
        "description": "Message the human approves"
      },
      "channel": {
        "type": "string",
        "description": "Optional channel label, such as #support"
      },
      "summary": {
        "type": "string",
        "description": "Optional one-line summary. Defaults to the message."
      },
      "approval_id": {
        "type": "string",
        "description": "From a previous wait. Call again after get_approval returns go."
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false
  },
  "title": "Post to Slack after a human allows it"
}

Get alerted

Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:

curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/net.agent-control/agent-control"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/net.agent-control/agent-control"}) over MCP.

Passed

Largest tool definitions

Static checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).

Operator? Fix these, then re-check live. Embed the readiness badge:

Markdown
[![MCP agent-readiness](https://glimind.com/v1/readiness/badge/mcp-registry%2Fnet.agent-control%2Fagent-control.svg)](https://glimind.com/server/mcp-registry%2Fnet.agent-control%2Fagent-control?ref=badge)
HTML
<a href="https://glimind.com/server/mcp-registry%2Fnet.agent-control%2Fagent-control?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fnet.agent-control%2Fagent-control.svg" alt="MCP agent-readiness"></a>
reStructuredText
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fnet.agent-control%2Fagent-control.svg
   :target: https://glimind.com/server/mcp-registry%2Fnet.agent-control%2Fagent-control?ref=badge
   :alt: MCP agent-readiness

Tool-definition log

Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:efe3ef736f05acaa…, first seen 2026-10-17, included at leaf 6006 of 19,647. Version history · verify what your client received.

Tools (27)

Compare: most reliable web servers · most reliable communication servers · most reliable billing servers · most reliable other servers · most reliable security servers

Know before your agent calls it

Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.

Add Glimind — free, no signup:

Add to Cursor Add to VS Code

Claude Code

claude mcp add --transport http glimind https://glimind.com/mcp

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "glimind": {
      "type": "http",
      "url": "https://glimind.com/mcp"
    }
  }
}

FAQ

Is the Agent Control MCP server down right now?

As of 2026-10-18 01:55 UTC, the Agent Control MCP server is up with a Glimind reliability score of 85/100 (grade B). Over the last 30 days it answered 99.8% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 26.4 hours.

How many tools does Agent Control MCP server provide?

Agent Control MCP server advertises 27 tools, including agent_readiness_check, ask_human, attach_human, browse_agents, check_action.

How do I install Agent Control MCP server?

Point your MCP client at this streamable-http endpoint: https://agent-control.net/api/v1/mcp

Is the Agent Control MCP server safe to connect to an AI agent?

Glimind scanned all 27 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.

Operator of Agent Control MCP server?

Status page: 90-day uptime, every outage and how long it lasted.

Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.

Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.