Is the Civai Nova Support Agent Admin MCP server down?

mcp-registry/co.civai.nova/support-agent-admin · v1.0.0

healthy
Last checked 2026-10-22 17:53 UTC · handshake 106ms

As of 2026-10-22 17:53 UTC, the Civai Nova Support Agent Admin MCP server is up with a Glimind reliability score of 77/100 (grade B). Over the last 30 days it answered 99% of Glimind's liveness checks. It had 37 outages in 90 days, with a median recovery of 8 minutes.

uptime (30d checks)
99%
checks observed
4,456
outages (90d)
37
tools
93

I manage your Support Agent CRM, pipeline analytics, follow-ups, Leads Discovery, and workspace out…

Install Civai Nova Support Agent Admin MCP server

Add to Cursor Add to VS Code

Claude Code

claude mcp add --transport http civai-nova-support-agent-admin-mcp-serve https://nova.civai.co/mcp/agents/support-agent-admin

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "civai-nova-support-agent-admin-mcp-serve": {
      "type": "http",
      "url": "https://nova.civai.co/mcp/agents/support-agent-admin"
    }
  }
}

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

Agent-readiness: D (56/100)

D (56/100): 0 error(s), 6 warning(s) across 93 tool(s); ~9,682 tokens of tool definitions.
Scores higher than 0% of 15,558 MCP servers Glimind has audited.
Its tool list costs an agent ~9,682 tokens per session — more than 80% of servers.
56 → 56 since 2026-10-17
no tool-poisoning patterns
Schemas100
Descriptions30
Safety hints0
Token cost75
Client compatibility70
Protocol100
Reliability75
Stability20

What to fix (8)

93 of 93 tool(s) carry no readOnlyHint/destructiveHint annotations.

Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →

Tools: admin__abort_scans, admin__assign_instagram_account, admin__assign_jiji_account, admin__assign_smtp_account, admin__assign_telegram_account and 88 more

93 tools on one server. Tool-selection accuracy drops as the menu grows, and some clients (e.g. Cursor) cap the number of active tools.

Group tools by task into smaller servers or toolsets, and merge near-duplicates behind one tool with a mode parameter. How to fix →

255 parameter(s) across 71 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. How to fix →

Tools: admin__abort_scans, admin__assign_instagram_account, admin__assign_jiji_account, admin__assign_smtp_account, admin__assign_telegram_account and 66 more

31 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.

Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →

Tools: admin__bulk_delete_sessions, admin__bulk_set_session_labels, admin__create_agent, admin__create_scan_schedule, admin__delete_agent and 26 more

Reachable 99.0% of the time over the last 30 days; median recovery 8 min.

Agents fail over to an alternative the first time a call fails. Add health checks and restart-on-failure, and avoid cold starts on serverless hosts.

In the last 30 days: 292 tool(s) removed and 14 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. How to fix →

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. How to fix →

3 tools share an identical description with another tool on this server.

Make each description say how the tool differs from its siblings, or the model will pick between them at random. How to fix →

Tools: calendar__converse, docs__converse, sheets__converse

Auto-fix: 76 corrected tool definitions

Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 71 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fco.civai.nova%2Fsupport-agent-admin/fixes

admin__assign_instagram_account 1 change 
{
  "name": "admin__assign_instagram_account",
  "description": "Assign or remove Instagram account on agent.",
  "inputSchema": {
    "type": "object",
    "required": [
      "agent_id"
    ],
    "properties": {
      "agent_id": {
        "type": "string"
      },
      "instagram_account_id": {
        "type": "string"
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false
  }
}
admin__assign_jiji_account 1 change 
{
  "name": "admin__assign_jiji_account",
  "description": "Assign or remove Jiji account on agent.",
  "inputSchema": {
    "type": "object",
    "required": [
      "agent_id"
    ],
    "properties": {
      "agent_id": {
        "type": "string"
      },
      "jiji_account_id": {
        "type": "string"
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false
  }
}
admin__assign_smtp_account 1 change 
{
  "name": "admin__assign_smtp_account",
  "description": "Assign or remove SMTP account on agent.",
  "inputSchema": {
    "type": "object",
    "required": [
      "agent_id"
    ],
    "properties": {
      "agent_id": {
        "type": "string"
      },
      "smtp_account_id": {
        "type": "string"
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false
  }
}

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/co.civai.nova/support-agent-admin"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/co.civai.nova/support-agent-admin"}) 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%2Fco.civai.nova%2Fsupport-agent-admin.svg)](https://glimind.com/server/mcp-registry%2Fco.civai.nova%2Fsupport-agent-admin?ref=badge)
HTML 
<a href="https://glimind.com/server/mcp-registry%2Fco.civai.nova%2Fsupport-agent-admin?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fco.civai.nova%2Fsupport-agent-admin.svg" alt="MCP agent-readiness"></a>
reStructuredText 
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fco.civai.nova%2Fsupport-agent-admin.svg
   :target: https://glimind.com/server/mcp-registry%2Fco.civai.nova%2Fsupport-agent-admin?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 sha256:51e0780b9a3187f7…, first seen 2026-10-21, included at leaf 40601 of 47,343. Version history · verify what your client received.

Tools (93)

Compare: most reliable devops servers · most reliable communication servers · most reliable data servers · most reliable search servers · most reliable admin 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 Civai Nova Support Agent Admin MCP server down right now?

As of 2026-10-22 17:53 UTC, the Civai Nova Support Agent Admin MCP server is up with a Glimind reliability score of 77/100 (grade B). Over the last 30 days it answered 99% of Glimind's liveness checks. It had 37 outages in 90 days, with a median recovery of 8 minutes.

How many tools does Civai Nova Support Agent Admin MCP server provide?

Civai Nova Support Agent Admin MCP server advertises 93 tools, including admin__abort_scans, admin__assign_instagram_account, admin__assign_jiji_account, admin__assign_smtp_account, admin__assign_telegram_account.

How do I install Civai Nova Support Agent Admin MCP server?

Point your MCP client at this streamable-http endpoint: https://nova.civai.co/mcp/agents/support-agent-admin

Is the Civai Nova Support Agent Admin MCP server safe to connect to an AI agent?

Glimind scanned all 93 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 Civai Nova Support Agent Admin 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.

Feedback
Help us improve