B2B outbound sales MCP server connecting AI agents to LinkedIn outreach, cold email sequencing, and prospect intelligence. Enables ChatGPT, Claude, Cursor, and custom agents to research leads, trigger personalized campaigns, manage unified inbox replies, and track pipeline metrics through 30 native tools.
Scored across 30 tools
Each tool targets a distinct resource and lifecycle step, and the consistent prepare-then-confirm_action pattern helps an agent sequence them correctly. The main soft spots are research_prospects vs enrich_prospects (both 'prepare' personalized content at credit cost) and the four overlapping intent read tools (get_intent_lead/results/summary, list_intent_leads), which require reading descriptions to separate.
Names are uniformly snake_case with a verb-first pattern (create_, get_, list_, launch_, pause_, resume_, send_, save_, unlock_, search_, enrich_, research_, approve_, confirm_, draft_). The convention is applied without exception across all 30 tools, so intent is predictable from the name alone.
30 tools is on the heavy side of the rubric, though the surface spans several genuine sub-domains (campaigns, prospects/research, intent, inbox, review, workspace config), so roughly 5 tools per area is defensible. Consolidating the four intent read tools would bring it comfortably into scope.
Core workflows are well covered: campaign create/get/list/launch/pause/resume/preview/enroll, prospect search/research/enrich, intent list/get/unlock/save, inbox list/thread/draft/send, and review list/approve. The notable gap is campaign lifecycle maintenance—no update or archive/delete tool despite list_campaigns exposing an 'archived' status—but agents can work around it.
Prepare approving people waiting in the review queue (run ids from list_review_queue). Approval researches them for credits; you still see the message before it is sent. Runs only after confirm_action.
Inputs: run_ids (required).
Run a launch, enroll, resume, inbox send, unlock, research, enrichment or review approval after the user explicitly confirmed in this chat. Pass confirmation_token from the previous tool. Never call this unless they said yes.
Inputs: confirmation_token (required).
Create a draft campaign. Does not launch or enroll anyone. Use mode blank, preset (preset_id), ai (ai_brief), or intent: an Intent-led campaign whose audience fills itself with people who show intent_signals and fit the ideal customer (each waits for review first). Tell the user it is a draft until they confirm a later launch.
Inputs: name (required), mode, min_fit, ai_brief, +4 more.
Draft an inbox reply. Returns text only — does not send. Use send_inbox_reply after the user wants to send it.
Inputs: thread_id (required).
Prepare enriching prospects (mode enrich_only) or writing a personalised first line (mode personalized_line). Costs credits per person; runs only after confirm_action.
Inputs: prospect_ids (required), mode.
Prepare adding a list or specific people to a campaign. Does not enroll until confirm_action after the user agrees in chat.
Inputs: campaign_id (required), list_id, prospect_ids.
Campaign detail: status, enrolled count, sequence step types, and connected seats.
Inputs: campaign_id (required).
Current plan name, trial/paid status, LinkedIn and email seat counts, active campaign limit, and credit balance.
Inputs: no named parameters.
The workspace's ideal customer rules (roles, industries, company size, locations, exclusions) and the High-intent and automatic delivery settings.
Inputs: no named parameters.
One Intent person or company: every signal with its source and date, fit reasons, research status and personalised lines.
Inputs: lead_id (required).
What Intent found and produced: signals by source, people delivered, researched, contacted, replied, meetings, customers, credits per reply and the best signals and playbooks.
Inputs: days.
Intent overview: whether tracking is on, this month's included people used and left, today's deliveries, how many High-intent and Warm people there are, and how many wait for review.
Inputs: no named parameters.
Dashboard snapshot: running campaigns, replies, unread inbox, credits, and account health for this Prosyo workspace.
Inputs: no named parameters.
A prospect's latest research (facts with sources) and personalised lines: icebreaker, connection note, LinkedIn message, email subject and body.
Inputs: prospect_id (required).
One inbox conversation with recent messages.
Inputs: thread_id (required).
Prepare launching a draft campaign. Sending does not start until confirm_action after the user agrees in chat.
Inputs: campaign_id (required).
List campaigns in this workspace. Optional status filter: draft, running, paused, completed, archived.
Inputs: search, status.
Recent LinkedIn and email conversations. Optional search and unread filter.
Inputs: query, filter, channel.
People (or companies) showing buying signals, strongest first, each with intent score, ideal-customer fit and why now. Locked people show only their signals until unlocked.
Inputs: page, tier, view, query, +3 more.
Prospect lists with people counts.
Inputs: no named parameters.
Playbooks and Intent-led campaign audiences: which signals they watch, Review first or Autopilot, matches, people added and credits used this month.
Inputs: no named parameters.
People a playbook matched who are waiting for approval, or whose researched message is ready to review.
Inputs: no named parameters.
Pause a running campaign immediately so it stops queueing new sends.
Inputs: campaign_id (required).
Merge a real prospect into the campaign sequence so the user can read the messages before launch.
Inputs: campaign_id (required), prospect_id.
Prepare researching prospects: sourced facts plus a personalised icebreaker, connection note, LinkedIn message and email. Costs credits per person; fresh research is reused free. Runs only after confirm_action.
Inputs: prospect_ids (required).
Prepare resuming a paused campaign. Sending does not restart until confirm_action after the user agrees in chat.
Inputs: campaign_id (required).
Save unlocked Intent people to a prospect list (existing list_id or a new list_name). Their personalised lines go with them. Free; locked people are skipped.
Inputs: lead_ids (required), list_id, list_name.
Search people in this workspace by name, company, or email.
Inputs: query, stage, list_id.
Prepare sending a LinkedIn or email reply from Inbox. The message is not sent until confirm_action after the user agrees in chat.
Inputs: body (required), thread_id (required).
Prepare unlocking locked Intent people. Uses the plan's included people first, then credits per person. Nothing is unlocked until confirm_action after the user agrees in chat.
Inputs: lead_ids (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.
