Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

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

+4 this week 88 Trust /100

Last scanned (12 hours ago)

Scores higher than 93% of remote servers

Reachable. Last reached 22 Nov 2026.

Category CRM and Sales

Trust breakdown (7 categories)

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
Transport & Reachability100
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
What we tested

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 →

Changelog

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
Diagnostics

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
MCP tools · 115 exposed · ~9,245 tokens

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 →

Tool Tokens
admin__list_connectors ~45

List Leads Discovery source status for a support agent (for scans). To check or connect one messaging channel, use connect_channel instead.

NameTypeReqDescription
agent_idstringyes–

No output schema declared.

No examples provided.

admin__list_followup_runs ~36

List bulk follow-up runs for an agent.

NameTypeReqDescription
agent_idstringyes–
limitinteger––

No output schema declared.

No examples provided.

admin__list_growth_experiments ~34

List this agent's growth experiments (status, package, progress).

NameTypeReqDescription
agent_idstringyes–

No output schema declared.

No examples provided.

admin__list_leads ~304

This agent's Leads Discovery scan results (discovered leads, imported or not) as a compact table, 20 per page, newest scans first. These are scan rows, not CRM chats: for conversations in the CRM use list_chats. Each row: name, channel, where they were found (group, post, who posted), what they said, any country the platform reports (TikTok region, X account location), fit, whether imported, and the link. Use it for any question about several leads at once (which ones are from a country, who commented on a group, which were imported) instead of opening chats one by one. Filter by channel, scan_id, since (YYYY-MM-DD), imported (yes/no/any), query (words in the name, group, post or comment), and include_filtered for leads the qualifier set aside. Fetch the next page with page=next_page while has_more is true.

NameTypeReqDescription
agent_idstringyes–
channelstring–facebook, instagram, tiktok, x, youtube, whatsapp, telegram, web, ...
importedstring––
include_filteredboolean––
pageinteger–1-based
per_pageinteger–Default 20, at most 50
querystring––
scan_idstring––
sincestring–Only scans from this date, YYYY-MM-DD

No output schema declared.

No examples provided.

admin__list_scan_results ~55

Alias of get_scan — read leads from an active or completed scan.

NameTypeReqDescription
agent_idstringyes–
limitinteger––
offsetinteger––
scan_idstringyes–

No output schema declared.

No examples provided.

admin__list_scan_schedules ~29

List auto-scan schedules for an agent.

NameTypeReqDescription
agent_idstringyes–

No output schema declared.

No examples provided.

admin__list_scans ~30

List past and active leads discovery scans for an agent.

NameTypeReqDescription
agent_idstringyes–

No output schema declared.

No examples provided.

admin__list_session_labels ~28

List visitor session label catalog for an agent.

NameTypeReqDescription
agent_idstringyes–

No output schema declared.

No examples provided.

admin__list_sessions ~76

Filtered drill-down on visitor sessions (requires filter_by).

NameTypeReqDescription
agent_idstringyes–
contact_typestring––
created_fromstring––
created_tostring––
filter_bystringyes–
limitinteger––
pageinteger––

No output schema declared.

No examples provided.

admin__list_top_agents ~37

List busiest CRM agents (limit 5–10).

NameTypeReqDescription
limitinteger––
order_bystring––

No output schema declared.

No examples provided.

admin__pause_growth_experiment ~40

Pause a running growth experiment (no new runs until resumed).

NameTypeReqDescription
agent_idstringyes–
experiment_idstringyes–

No output schema declared.

No examples provided.

admin__pending_reply_count ~33

Count pending replies on an agent.

NameTypeReqDescription
agent_idstringyes–
channelsstring––

No output schema declared.

No examples provided.

admin__preview_followup_email ~67

Preview rendered follow-up email HTML.

NameTypeReqDescription
agent_idstringyes–
cta_labelstring––
cta_urlstring––
formatstring––
image_urlstring––
messagestringyes–

No output schema declared.

No examples provided.

admin__quote_growth_experiment ~137

Price a growth experiment for one agent before creating it: the package priced against today's capacity, the run plan per channel (runs a day x leads per run for each of the three keyword sets), whether Nova can message leads on each channel, and the owner's credit balance. Reads only.

NameTypeReqDescription
agent_idstringyes–
customobject–Custom package: days 1-30, reach_per_day (people a day) 10-500, channels (keyword channels: x, instagram, tiktok, facebook).
package_idstring–Preset package, or custom with the custom object.

No output schema declared.

No examples provided.

admin__regenerate_attachment ~41

Re-process one attachment (re-convert or re-extract schema).

NameTypeReqDescription
agent_idstringyes–
attachment_idstringyes–

No output schema declared.

No examples provided.

admin__remove_agent_collaborator ~38

Remove a collaborator from an agent (owner only).

NameTypeReqDescription
agent_idstringyes–
emailstringyes–

No output schema declared.

No examples provided.

admin__remove_chats ~105

Permanently delete CRM chats (the conversations) by visitor_id from list_chats. Leads Discovery scan rows are not touched; to drop scan results use remove_leads. Call it ONCE with every visitor_id; the owner approves once. Report the deleted_count it returns, never more.

NameTypeReqDescription
agent_idstringyes–
reasonstring–Short reason shown in the approval
visitor_idsarrayyesvisitor_id values from list_chats

No output schema declared.

No examples provided.

admin__remove_leads ~136

Remove chosen discovered leads (by lead_id from list_leads) from this agent's Leads Discovery scan results, for example leads from the wrong country or the wrong groups. It never deletes a CRM chat: to delete conversations use remove_chats. Call it ONCE with every lead_id to remove; the owner approves once. Later scans do not find these people again. Leads already imported keep their CRM chat; the result lists their visitor_ids.

NameTypeReqDescription
agent_idstringyes–
lead_idsarrayyeslead_id values from list_leads
reasonstring–Short reason shown in the approval

No output schema declared.

No examples provided.

admin__resume_conversation ~33

Resume a paused visitor conversation.

NameTypeReqDescription
agent_idstringyes–
visitor_idstringyes–

No output schema declared.

No examples provided.

admin__resume_followup_run ~35

Resume an interrupted follow-up run.

NameTypeReqDescription
agent_idstringyes–
run_idstringyes–

No output schema declared.

No examples provided.

admin__resume_growth_experiment ~41

Resume a paused growth experiment. Needs credits for the remaining days.

NameTypeReqDescription
agent_idstringyes–
experiment_idstringyes–

No output schema declared.

No examples provided.

admin__run_scan ~116

Start a leads discovery scan (whatsapp, instagram, x, telegram, or jiji). Discovery params for x/instagram/facebook/tiktok accept max_post_age_days (1-365; omit = no age limit) and post_age_relax_steps (0-4, default 3) to cap how old a source post may be before its engagers are collected; the window widens within a run only.

NameTypeReqDescription
agent_idstringyes–
channelstringyes–
paramsobject––

No output schema declared.

No examples provided.

admin__send_followup ~142

Send follow-up via admin_followup channels. Optionally attach public KB files.

NameTypeReqDescription
agent_idstringyes–
contactstring–Generic contact from analytics/list_sessions (email, phone, or @instagram).
file_idsarray–Optional attachment_id values from list_attachments to attach to this send. Only attachments marked public (is_public true) can be sent; private ones are rejected. Attach only what the lead asked for.
instagram_usernamestring––
messagestringyes–
visitor_emailstring––
visitor_idstring––
whatsapp_nostring––

No output schema declared.

No examples provided.

admin__send_message ~144

Send follow-up via WhatsApp, email, or Instagram. Optionally attach public KB files.

NameTypeReqDescription
agent_idstringyes–
contactstring–Generic contact from analytics/list_sessions (email, phone, or @instagram).
file_idsarray–Optional attachment_id values from list_attachments to attach to this send. Only attachments marked public (is_public true) can be sent; private ones are rejected. Attach only what the lead asked for.
instagram_usernamestring––
messagestringyes–
visitor_emailstring––
visitor_idstring––
whatsapp_nostring––

No output schema declared.

No examples provided.

admin__set_attachment_visibility ~117

Mark a KB attachment public or private. Every attachment defaults to private on upload. Only a public attachment can ever be offered or sent by the agent's converse tool (email attachment, or a shared file in chat) — a private one is never visible to the model at all, regardless of what a visitor asks for.

NameTypeReqDescription
agent_idstringyes–
attachment_idstringyes–
is_publicbooleanyesTrue to let the agent attach/send this file; false (default) to keep it private.

No output schema declared.

No examples provided.

admin__set_growth_auto_tune ~51

Switch the daily keyword review (arm replacement) on or off.

NameTypeReqDescription
agent_idstringyes–
auto_tunebooleanyes–
experiment_idstringyes–

No output schema declared.

No examples provided.

admin__set_pool_mode ~88

Enable/disable pool mode for a channel. x/instagram/telegram: fallback when the agent's own account halts. jiji/whatsapp: the pool is the sender when the agent has no account of its own (WhatsApp conversations stay on one pool number).

NameTypeReqDescription
agent_idstringyes–
channelstringyes–
enabledbooleanyes–

No output schema declared.

No examples provided.

admin__set_session_labels ~41

Replace labels on one visitor session.

NameTypeReqDescription
agent_idstringyes–
labelsarray––
visitor_idstringyes–

No output schema declared.

No examples provided.

admin__set_whatsapp_account_role ~76

Mark one of your WhatsApp Web numbers as a pool number (role=pool) that agents with whatsapp_pool_mode send from, or back to a normal number (role=agent). Only numbers you own; donated accounts are refused.

NameTypeReqDescription
rolestringyes–
whatsapp_account_idstringyes–

No output schema declared.

No examples provided.

admin__set_x_account_attention ~298

Set X Leads Discovery public-attention settings on an account (main or pool): poster, surface, post goal, quote target, like/public-after-DM toggles, pool fallback, per-run limit, and the account's daily post/like caps (superset of set_x_account_daily_limits). Only fields you pass change; everything else keeps its current account/workspace/env value.

NameTypeReqDescription
x_account_idstringyes–
x_followup_max_per_threadinteger–Max automated reply rounds in one public thread before going quiet. Not a daily cap — per-thread, and not account-only.
x_ld_like_before_dmboolean––
x_ld_like_daily_limitinteger–Max engagement likes this account may send per day (0-2000).
x_ld_pool_public_quote_after_dm_failboolean––
x_ld_public_after_dmboolean––
x_ld_public_daily_limitinteger–Max public quotes/replies this account may post per day (0-500).
x_ld_public_onlyboolean–Cold LD import: public quote/reply only, no DMs.
x_ld_public_per_run_limitinteger––
x_ld_public_post_goalstring––
x_ld_public_posterstring––
x_ld_public_surfacestring––
x_ld_quote_targetstring––

No output schema declared.

No examples provided.

admin__set_x_account_daily_limits ~129

Set the daily public-post and/or engagement-like cap for an X account (main or pool). This is the only place these volumes can be set — they are a per-account safety ceiling shared by every agent/campaign that uses the account, never per-agent or per-workspace.

NameTypeReqDescription
x_account_idstringyes–
x_ld_like_daily_limitinteger–Max engagement likes this account may send per day (0-2000).
x_ld_public_daily_limitinteger–Max public quotes/replies this account may post per day (0-500).

No output schema declared.

No examples provided.

admin__start_growth_experiment ~135

Start a draft growth experiment: writes the keyword sets, creates the Leads Discovery schedules (day 1 runs now) and messages real people. Needs the package's credits on hand. Optional package_id/custom re-picks the package first.

NameTypeReqDescription
agent_idstringyes–
customobject–Custom package: days 1-30, reach_per_day (people a day) 10-500, channels (keyword channels: x, instagram, tiktok, facebook).
experiment_idstringyes–
package_idstring–Preset package, or custom with the custom object.

No output schema declared.

No examples provided.

admin__stop_ad_plan ~53

Switch one launched ad off. The campaign is paused first, so spend stops on the very first call.

NameTypeReqDescription
agent_idstringyes–
plan_idstringyesFrom list_ad_plans.

No output schema declared.

No examples provided.

admin__suggest_targets ~81

AI-propose Instagram or X @targets for a discovery scan (depth/breadth optional).

NameTypeReqDescription
agent_idstringyes–
channelstringyes–
disable_hard_filterboolean––
discovery_breadthinteger––
discovery_depthinteger––
min_followersinteger––

No output schema declared.

No examples provided.

admin__transfer_agent_owner ~37

Transfer agent ownership to another subscribed Nova user.

NameTypeReqDescription
agent_idstringyes–
new_owner_emailstringyes–

No output schema declared.

No examples provided.

admin__trigger_scan_schedule ~38

Run an auto-scan schedule immediately (Run now).

NameTypeReqDescription
agent_idstringyes–
schedule_idstringyes–

No output schema declared.

No examples provided.

admin__update_agent ~869

Update Support Agent settings (partial patch — only send fields to change).

NameTypeReqDescription
agent_idstringyes–
allow_listarray–Visitor allow list (emails, @handles, Jiji seller ids, X ids). Empty list = allow all visitors.
auto_reply_allowed_channelsarray–Channels where the agent may send AI auto-replies. Empty = all channels (still filtered by allow_list).
bulk_followup_enabledboolean––
contact_optionstring––
contextstring––
descriptionstring––
disable_ai_replyboolean––
file_supportboolean––
followup_email_messagestring–Email opening template (UI: Outreach opening messages → Email). Used for Leads Discovery Message now, bulk follow-up, and first inbound CRM email auto-reply.
followup_email_subjectstring–Subject line for this agent's outbound follow-up emails (UI: Outreach opening messages → Email). Max 200 characters, no line breaks. Empty = default subject that includes the agent title. Later messa…
followup_instagram_messagestring–Instagram DM opening template for outreach compose.
followup_telegram_messagestring–Telegram opening template for outreach compose.
followup_whatsapp_messagestring–WhatsApp opening template for outreach compose.
followup_x_messagestring–X DM opening template for outreach compose.
inappboolean––
instructionsstring––
intake_as_leadboolean–When true, an intake form submission is imported as a lead (saved as Leads Discovery-style context) and the agent sends its own first outreach, instead of the form being treated as the contact's firs…
intake_enabledboolean–Whether POST /api/public-agents/{agent_id}/intake accepts website form submissions for this agent. No API key is needed to call it, so it is off by default and the endpoint answers 404 while off.
intake_originsarray–Origins allowed to post to the intake endpoint, e.g. https://civai.co. Empty list = any origin. Up to 10.
is_publicboolean––
nudge_handoff_modeboolean–For agents whose nudge is the hand-off itself (an order desk reporting each decision in one long-lived chat): only an exact repeat of a nudge reason is skipped, and there is no per-session nudge cap.…
nudge_on_first_replyboolean–Offer nudge_operator from the agent's very first reply, instead of only after a few exchanges. For agents whose first reply can already be the event the team needs (an order desk whose vendor answers…
nudge_operator_enabledboolean–Whether the nudge_operator tool (email the owner/collaborators when the agent needs human follow-up) is available to this agent. Defaults to false.
public_category_idinteger––
public_descriptionstring––
public_slugstring––
themestring––
titlestring––
x_followup_max_per_threadinteger–Max automated reply rounds in one public thread (main-account thread replies, or a pool peer answering its own quote) before going quiet. Not account-only — layered agent/account/workspace/env like t…
x_ld_attention_use_customboolean–When true, use agent-specific X Leads Discovery public attention (Lane A/B).
x_ld_like_before_dmboolean––
x_ld_pool_public_quote_after_dm_failboolean––
x_ld_public_after_dmboolean––
x_ld_public_onlyboolean–Cold LD import: public quote/reply only, no DMs.
x_ld_public_per_run_limitinteger––
x_ld_public_post_goalstring––
x_ld_public_posterstring––
x_ld_public_surfacestring––
x_ld_quote_targetstring––

No output schema declared.

No examples provided.

admin__update_agent_collaborator ~61

Update collaborator role or permissions on an agent (owner only).

NameTypeReqDescription
agent_idstringyes–
emailstringyes–
permissionsarray––
rolestring––
statusstring––

No output schema declared.

No examples provided.

admin__update_crm_unreplied_alert_config ~58

Update CRM unreplied digest email settings.

NameTypeReqDescription
agent_idstringyes–
enabledboolean––
min_unrepliedinteger––
recipient_emailsarray––

No output schema declared.

No examples provided.

admin__update_scan_schedule ~195

Update or pause/resume an auto-scan schedule. Discovery params for x/instagram/facebook/tiktok accept max_post_age_days (1-365; omit = no age limit) and post_age_relax_steps (0-4, default 3) to cap how old a source post may be before its engagers are collected; the window widens within a run only.

NameTypeReqDescription
agent_idstringyes–
auto_importboolean––
auto_outreachstring––
channelstring––
enabledboolean––
frequencystring––
labelstring––
max_leads_per_runinteger––
max_runsinteger––
paramsobject––
relax_target_filter_after_runsinteger––
run_hour_utcinteger––
schedule_idstringyes–

No output schema declared.

No examples provided.

admin__update_session_label ~47

Update catalog label (e.g. disable_auto_reply).

NameTypeReqDescription
agent_idstringyes–
disable_auto_replyboolean––
label_idstringyes–

No output schema declared.

No examples provided.

admin__upload_agent_icon ~54

Upload agent icon (JPEG/PNG/WebP, max 2MB, base64).

NameTypeReqDescription
agent_idstringyes–
content_base64stringyes–
content_typestring––

No output schema declared.

No examples provided.

admin__upload_attachments ~110

Upload files to agent KB (PDF/DOCX/DOC/TXT → prose, max 10MB; CSV/SQLite/DB → database, max 50MB; XLSX → database, max 20MB). Each file gives content_base64 (small files only) or file_url (public https link the server downloads). For a large local file with no public link, use create_attachment_upload_url instead.

NameTypeReqDescription
agent_idstringyes–
filesarrayyes–

No output schema declared.

No examples provided.

calendar__add_event ~31

Run Google calendar action: add event

NameTypeReqDescription
detailstring–Task-specific details from the objective.

No output schema declared.

No examples provided.

calendar__check_events_today ~33

Run Google calendar action: check events today

NameTypeReqDescription
detailstring–Task-specific details from the objective.

No output schema declared.

No examples provided.

calendar__check_events_week ~33

Run Google calendar action: check events week

NameTypeReqDescription
detailstring–Task-specific details from the objective.

No output schema declared.

No examples provided.

calendar__converse ~36

Reply conversationally when the request is ambiguous or needs clarification.

NameTypeReqDescription
reply_hintstring–Optional hint for the conversational reply.

No output schema declared.

No examples provided.

calendar__convert_timezone ~31

Run Google calendar action: convert timezone

NameTypeReqDescription
detailstring–Task-specific details from the objective.

No output schema declared.

No examples provided.

calendar__delete_event ~31

Run Google calendar action: delete event

NameTypeReqDescription
detailstring–Task-specific details from the objective.

No output schema declared.

No examples provided.

calendar__update_event ~31

Run Google calendar action: update event

NameTypeReqDescription
detailstring–Task-specific details from the objective.

No output schema declared.

No examples provided.

Install

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

# add to Claude Code
claude mcp add --transport http co-civai-nova-support-agent-admin 'https://nova.civai.co/mcp/agents/support-agent-admin'
Common questions

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.