Leads Discovery Agent by Nova (CIVAI) is an MCP server with 22 tools an agent can call, among them abort_scans, clear_discovery_cache, continue_scan. It answers at https://nova.civai.co/mcp/agents/leads-discovery-agent over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 23 September 2026; the last check, on 6 November 2026, succeeded.
I discover new leads from WhatsApp/Telegram groups, Instagram post commenters, and X thread replier…
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
abort_scans | Stop stuck running scans (marks interrupted, releases schedule lock). Inputs: agent_id, scan_ids, reason |
clear_discovery_cache | Clear Leads Discovery scan cache for an agent (seen handles / WA progress). Inputs: agent_id |
continue_scan | Continue a scan paused for selection (WhatsApp/Telegram groups or IG/X targets). Inputs: agent_id, scan_id, selected_resources, max_contacts_per_group |
create_scan_schedule | Create an auto-scan schedule (Import Only or Message now outreach). Discovery params for x/instagram 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 Inputs: agent_id, channel, params, frequency, auto_import, auto_outreach |
delete_scan_schedule | Delete an auto-scan schedule. Inputs: agent_id, schedule_id |
delete_scans | Delete one or more completed scan runs (does not delete schedules). Inputs: agent_id, scan_ids |
get_ad_guide | The ad plan rendered as steps to tap, per channel, in the owner's own words with the daily budget already divided. Use this when the owner wants to run the ads themselves. Nova never touches their ad account. Inputs: agent_id, channel, leads_target |
get_ad_plan | The ads this business should run, built from its own scans: three things to film, each citing a count from this agent's own leads, plus the spend and reach for a lead target. Reads only; nothing is launched and no money moves. Returns statu Inputs: agent_id, leads_target, country, account_mode |
get_discovery_analytics | Get sourced-leads analytics for an agent (window e.g. 7d, 30d). Inputs: agent_id, window |
get_scan | Get one scan with paginated leads (status, progress, leads). Inputs: agent_id, scan_id, offset, limit |
import_leads | Import discovered leads into the agent CRM (outreach: none|immediate|bulk_followup). Inputs: agent_id, scan_id, lead_ids, label, outreach |
launch_ad_plan | Run one ad on one channel, under a spend cap the owner has named out loud. The cap is debited before anything is created and nothing is ever created above it. Creative is the owner's: this never writes an ad. Needs a connected ad account. Inputs: agent_id, channel, cap_minor, currency, headline, body |
list_ad_plans | Every ad this agent has already launched, newest first, with its cap, its channel and whether it is running or stopped. Reads only. Inputs: agent_id |
list_connectors | List WhatsApp, Instagram, Email, X connector status for a support agent. Inputs: agent_id |
list_scan_results | Alias of get_scan — read leads from an active or completed scan. Inputs: agent_id, scan_id, offset, limit |
list_scan_schedules | List auto-scan schedules for an agent. Inputs: agent_id |
list_scans | List past and active leads discovery scans for an agent. Inputs: agent_id |
run_scan | Start a leads discovery scan (whatsapp, instagram, x, telegram, or jiji). Discovery params for x/instagram 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 b Inputs: agent_id, channel, params |
stop_ad_plan | Switch one launched ad off. The campaign is paused first, so spend stops on the very first call. Inputs: agent_id, plan_id |
suggest_targets | AI-propose Instagram or X @targets for a discovery scan (depth/breadth optional). Inputs: agent_id, channel, discovery_depth, discovery_breadth, min_followers, disable_hard_filter |
trigger_scan_schedule | Run an auto-scan schedule immediately (Run now). Inputs: agent_id, schedule_id |
update_scan_schedule | Update or pause/resume an auto-scan schedule. Discovery params for x/instagram 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 colle Inputs: agent_id, schedule_id, channel, params, frequency, auto_import |
Every block below points at https://nova.civai.co/mcp/agents/leads-discovery-agent. Pick your client and copy.
claude mcp add --transport http leads-discovery-agent-by-nova-ci https://nova.civai.co/mcp/agents/leads-discovery-agent
{
"mcpServers": {
"leads-discovery-agent-by-nova-ci": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://nova.civai.co/mcp/agents/leads-discovery-agent"]
}
}
}{
"mcpServers": {
"leads-discovery-agent-by-nova-ci": {
"url": "https://nova.civai.co/mcp/agents/leads-discovery-agent"
}
}
}{
"servers": {
"leads-discovery-agent-by-nova-ci": {
"type": "http",
"url": "https://nova.civai.co/mcp/agents/leads-discovery-agent"
}
}
}{
"context_servers": {
"leads-discovery-agent-by-nova-ci": {
"url": "https://nova.civai.co/mcp/agents/leads-discovery-agent"
}
}
}{
"mcpServers": {
"leads-discovery-agent-by-nova-ci": {
"serverUrl": "https://nova.civai.co/mcp/agents/leads-discovery-agent"
}
}
}{
"mcpServers": {
"leads-discovery-agent-by-nova-ci": {
"url": "https://nova.civai.co/mcp/agents/leads-discovery-agent"
}
}
}name: Leads Discovery Agent by Nova (CIVAI)
version: 0.0.1
schema: v1
mcpServers:
- name: Leads Discovery Agent by Nova (CIVAI)
type: streamable-http
url: https://nova.civai.co/mcp/agents/leads-discovery-agent{
"mcpServers": {
"leads-discovery-agent-by-nova-ci": {
"httpUrl": "https://nova.civai.co/mcp/agents/leads-discovery-agent"
}
}
}{
"mcpServers": {
"leads-discovery-agent-by-nova-ci": {
"type": "http",
"url": "https://nova.civai.co/mcp/agents/leads-discovery-agent"
}
}
}{
"mcpServers": {
"leads-discovery-agent-by-nova-ci": {
"url": "https://nova.civai.co/mcp/agents/leads-discovery-agent"
}
}
}goose://extension?url=https%3A%2F%2Fnova.civai.co%2Fmcp%2Fagents%2Fleads-discovery-agent&type=streamable_http&id=leads-discovery-agent-by-nova-ci&name=Leads%20Discovery%20Agent%20by%20Nova%20%28CIVAI%29
It answered our last check on 6 November 2026 in 473 ms. Over 4 checks since 23 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by civai.co and served from nova.civai.co, the vendor's own domain: https://nova.civai.co/mcp/agents/leads-discovery-agent.
22, as returned by the server's own tools/list on 12 November 2026: abort_scans, clear_discovery_cache, continue_scan, create_scan_schedule, delete_scan_schedule, delete_scans, get_ad_guide, get_ad_plan, and 14 more.
It answered our last check on 6 November 2026 in 473 ms. Over 4 checks since 23 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://nova.civai.co/mcp/agents/leads-discovery-agent. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: co.civai.nova. Endpoint host: nova.civai.co. ARD identifier: urn:air:co.civai.nova:mcp:leads-discovery-agent.
First indexed 21 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.