Support Agent Admin by Nova (CIVAI)
REMOTE · NOVA.CIVAI.CO
I manage your Support Agent CRM, pipeline analytics, follow-ups, Leads Discovery, and workspace out…
Available components
Last scanned (12 hours ago)
Scores higher than 93% of remote servers
Reachable. Last reached 22 Nov 2026.
Category CRM and Sales
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. How we score → Why this is hard to score →
Endpoint Security92
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability72
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 9276 tokens (~79/item across 116 items; 115 tools + 1 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage76
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 27% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 15 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "admin__delete_agent" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 116 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 22 Nov 26 0
- New tool “admin__create_growth_experiment” functional
- New tool “admin__get_growth_experiment” functional
- New tool “admin__get_growth_readout” functional
- New tool “admin__growth_arm_action” functional
- New tool “admin__list_growth_experiments” functional
- New tool “admin__pause_growth_experiment” functional
- New tool “admin__quote_growth_experiment” functional
- New tool “admin__resume_growth_experiment” functional
- New tool “admin__set_growth_auto_tune” functional
- New tool “admin__start_growth_experiment” functional
- “admin__create_agent” added an optional parameter “nudge_on_first_reply” cosmetic
- “admin__update_agent” added an optional parameter “nudge_on_first_reply” cosmetic
- 21 Nov 26 +3
- Authorization: fail → pass ▲ security
- First check of Authorization: pass security
- Tool “admin__create_scan_schedule” rewrote its description, which is the text the model reads security
- Tool “admin__list_leads” rewrote its description, which is the text the model reads security
- Tool “admin__remove_leads” rewrote its description, which is the text the model reads security
- Tool “admin__run_scan” rewrote its description, which is the text the model reads security
- Tool “admin__update_scan_schedule” rewrote its description, which is the text the model reads security
- Tool “admin__upload_attachments” rewrote its description, which is the text the model reads security
- New tool “admin__create_attachment_upload_url” functional
- New tool “admin__list_chats” functional
- New tool “admin__remove_chats” functional
- “admin__remove_leads” reworded the description of “reason” cosmetic
- 20 Nov 26 +1
- New tool “admin__list_leads” functional
- New tool “admin__remove_leads” functional
- “admin__create_agent” added an optional parameter “nudge_handoff_mode” cosmetic
- “admin__update_agent” added an optional parameter “nudge_handoff_mode” cosmetic
- 19 Nov 26 0
- HSTS header: unverified → fail ▼ security
- 18 Nov 26 0
- HSTS header: fail → unverified ▼ security
- Tool “admin__list_channel_accounts” rewrote its description, which is the text the model reads security
- Tool “admin__list_connectors” rewrote its description, which is the text the model reads security
- New tool “admin__connect_channel” functional
- 11 Nov 26 0
- Stability: 0.97 → pass security
- Tool “admin__set_pool_mode” rewrote its description, which is the text the model reads security
- New tool “admin__set_whatsapp_account_role” functional
- “admin__create_agent” added an optional parameter “intake_as_lead” cosmetic
- “admin__update_agent” added an optional parameter “intake_as_lead” cosmetic
- 10 Nov 26 0
- Stability: pass → 0.97 functional
- New tool “research__conduct-deep-research” functional
- New tool “research__generate-research-report” functional
- 9 Nov 26 0
- A breaking change shipped without a version bump: still 1.0.0 ▼ security
- Tool “research__conduct-deep-research” was removed ▼ security
- Tool “research__generate-research-report” was removed ▼ security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 22 Nov 2026 · Probed https://nova.civai.co/mcp/agents/support-agent-admin
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.vearn.co | CN=YR2,O=Let's Encrypt,C=US | 18 Oct 2026 | 16 Jan 2027 | RSA 2048 | SHA256-RSA | 5989a0174450d554cb27dbfdec88b2ff58a |
| SANs: allegedly-api.crypvestai.cloud, allegedly.crypvestai.cloud, api.agi.civai.co, api.browser.civai.co, api.nova.civai.co, api.vearn.co, app.browsergpt.co, app.vearn.co, arcade-assets.civai.co, audience-resolver-api.civai.co, audience-resolver.civai.co, audience.civai.co and 11 more | ||||||
| CN=YR2,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | 4ebd24947e24d394802d84a52fd5b319 |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of nova.civai.co. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| co. | DS published | 7786 | 8 | Verified |
| civai.co. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer resource_metadata="https://nova.civai.co/.well-known/oauth-protected-resource/mcp/agents/support-agent-admin", scope="mcp:access"
Bearer resource_metadata="https://nova.civai.co/.well-known/oauth-protected-resource/mcp/agents/support-agent-admin", scope="mcp:access" Protected resource metadata
| Document | https://nova.civai.co/.well-known/oauth-protected-resource/mcp/agents/support-agent-admin |
|---|---|
| Retrieved | Yes |
| Resource | https://nova.civai.co/mcp/agents/support-agent-admin |
| Authorisation server | https://nova.civai.co |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://nova.civai.co/mcp/agents/support-agent-admin | Verified | 200 | |
| http (plaintext) | http://nova.civai.co/mcp/agents/support-agent-admin | HTTPS enforced | 301 | https://nova.civai.co/mcp/agents/support-agent-admin |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
docs__converse ~36
Reply conversationally when the request is ambiguous or needs clarification.
| Name | Type | Req | Description |
|---|---|---|---|
| reply_hint | string | – | Optional hint for the conversational reply. |
No output schema declared.
No examples provided.
docs__create_doc ~31
Run Google docs action: create doc
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | Task-specific details from the objective. |
No output schema declared.
No examples provided.
docs__delete_doc ~31
Run Google docs action: delete doc
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | Task-specific details from the objective. |
No output schema declared.
No examples provided.
docs__get_doc ~31
Run Google docs action: get doc
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | Task-specific details from the objective. |
No output schema declared.
No examples provided.
docs__list_docs ~31
Run Google docs action: list docs
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | Task-specific details from the objective. |
No output schema declared.
No examples provided.
docs__rewrite_doc ~31
Run Google docs action: rewrite doc
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | Task-specific details from the objective. |
No output schema declared.
No examples provided.
research__conduct-deep-research ~155
Conduct deep, iterative research on a topic by generating multiple search queries, processing the results, and recursively exploring new research directions.
| Name | Type | Req | Description |
|---|---|---|---|
| breadth | integer | – | Number of search queries per research direction (1-5) |
| connection_id | string | – | Optional connection ID for the user |
| depth | integer | – | Depth of recursive exploration (0-2) |
| max_duration_seconds | integer | – | Maximum duration for the research process in seconds (60-300) |
| max_total_queries | integer | – | Maximum number of search queries to process (2-5) |
| objective | string | yes | The specific goal or objective of the research |
| topic | string | yes | The main topic or question to research |
No output schema declared.
No examples provided.
research__generate-research-report ~55
Generate a comprehensive research report from existing research data.
| Name | Type | Req | Description |
|---|---|---|---|
| objective | string | yes | The specific goal or objective of the report |
| research_data | string | yes | The research data and findings to include in the report |
No output schema declared.
No examples provided.
sheets__converse ~36
Reply conversationally when the request is ambiguous or needs clarification.
| Name | Type | Req | Description |
|---|---|---|---|
| reply_hint | string | – | Optional hint for the conversational reply. |
No output schema declared.
No examples provided.
sheets__create_sheet ~31
Run Google sheets action: create sheet
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | Task-specific details from the objective. |
No output schema declared.
No examples provided.
sheets__delete_sheet ~31
Run Google sheets action: delete sheet
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | Task-specific details from the objective. |
No output schema declared.
No examples provided.
sheets__generate_sheet ~31
Run Google sheets action: generate sheet
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | Task-specific details from the objective. |
No output schema declared.
No examples provided.
sheets__get_sheet ~31
Run Google sheets action: get sheet
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | Task-specific details from the objective. |
No output schema declared.
No examples provided.
sheets__list_sheets ~32
Run Google sheets action: list sheets
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | Task-specific details from the objective. |
No output schema declared.
No examples provided.
sheets__update_sheet ~31
Run Google sheets action: update sheet
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | Task-specific details from the objective. |
No output schema declared.
No examples provided.
How do I install the Support Agent Admin by Nova (CIVAI) MCP server?
Support Agent Admin by Nova (CIVAI) is a hosted endpoint at https://nova.civai.co/mcp/agents/support-agent-admin, 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.
remote · nova.civai.co
claude mcp add --transport http co-civai-nova-support-agent-admin 'https://nova.civai.co/mcp/agents/support-agent-admin'
What is the Support Agent Admin by Nova (CIVAI) MCP server?
Support Agent Admin by Nova (CIVAI) is an MCP server listed in the public MCP registry as co.civai.nova/support-agent-admin. I manage your Support Agent CRM, pipeline analytics, follow-ups, Leads Discovery, and workspace out… This page covers its hosted endpoint (https://nova.civai.co/mcp/agents/support-agent-admin).
Is the Support Agent Admin by Nova (CIVAI) MCP server safe to use?
Support Agent Admin by Nova (CIVAI) scores 88 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 Support Agent Admin by Nova (CIVAI) MCP server expose?
Support Agent Admin by Nova (CIVAI) exposes 115 tools: admin__list_agents, admin__list_top_agents, admin__get_agent, admin__get_agent_analytics, admin__list_sessions, and 110 more. Their descriptions and schemas cost roughly 9,245 tokens of context every time the server is loaded.
Does the Support Agent Admin by Nova (CIVAI) MCP server require authentication?
Yes. Support Agent Admin by Nova (CIVAI) asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Support Agent Admin by Nova (CIVAI) MCP server still maintained?
Support Agent Admin by Nova (CIVAI) is still listed as active in the MCP registry. We last reached this channel on 22 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Support Agent Admin by Nova (CIVAI) MCP server?
VerifyMCP ran 13 checks on Support Agent Admin by Nova (CIVAI), covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.