F
licenseNot graded
qualityC
maintenanceEnables AI agents to draft evidence-grounded cold-email openers, A/B variants, personalized LinkedIn DMs, and SEO content-gap plans for sales and marketing outreach.
-
Outbound Engine MCP
by closermethod
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Outbound Engine MCP Audit my cold DM for a brand deal"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Outbound Engine MCP
The cold-outreach method layer for AI agents. One engine, any target: brand deals, UGC, newsletter sponsorships, jobs, podcasts.
Built from the method behind The Outbound Engine.
Disclaimer. Outputs are structured outreach-method frameworks based on documented practice. Results vary by niche, proof quality, and consistency. Not legal advice. Follow platform rules and outreach law for your channel and region.
Why This Exists
Every AI agent that drafts cold outreach today has the same failure mode: it writes long, polite, generic pitches that ask a stranger for the biggest possible thing on the first touch. Those messages don't get replies, and outreach that doesn't get replies doesn't get deals.
This MCP encodes one rule and enforces it with tools:
A cold pitch is not trying to close a deal. It is trying to get a reply. The deal closes in the follow-up.
It does NOT send messages and does NOT scrape prospects. It is the method layer: give it a draft, a target type, or a reply — get back structure, violations, and the next move.
Related MCP server: openoutbound
7 Tools
Tool | What it returns |
| HOOK / BRIDGE / SOFT ASK structure + the 4 swap variables (who to pitch, signal to research, proof to lead with, soft-ask object) per target type |
| PASS/FAIL audit of a draft: money in a cold message, identity-first opener, generic hook, hard ask, length over ~90 words, multiple asks — with a rewrite recipe |
| The 5-step ladder (Day 3 / 7 / 12 / 18 / 25) — where 80% of deals actually close. The Day 25 break-up alone pulls ~30% of replies |
| The next move for any reply type: price question, interested, not now, no budget, exposure offer, spec request, pay-on-performance, ghosted |
| The 3-option menu (Starter / Most Popular / Full) + the two scoping questions to ask first. Drop scope, never price |
| Scans a reply or brief for walk-away signals: exposure-pay, spec work, pay-on-performance, budget mismatch, scope creep |
| The complete engine as one payload — drop it into a Claude Project system prompt |
Sample Use
// Agent drafted a cold DM for a brand deal. Before sending:
mcp.call("audit_cold_message", {
message: "Hi, I'm a UGC creator with 50k followers! I love your brand. My rate is $500/video...",
target_type: "brand_deal"
});
// Returns: FAIL — no_money_in_cold_message, no_identity_first_opener,
// specific_hook_required + a 3-move rewrite recipe.
// Prospect replied asking "what do you charge?"
mcp.call("handle_reply", { reply_type: "price_question" });
// Returns: don't send one number — two scoping questions first, then the 3-option menu.Target Types
brand_deal · ugc · newsletter_sponsorship · job · podcast · client_work
Same engine, four swapped variables per target. That's the whole trick.
The Full System
This MCP is the free method layer. The full Outbound Engine product adds per-target research packs, an onboarding intake that builds your proof inventory, and the daily operating system — at elisabethhitz.com.
Built By
Elisabeth Hitz — 10+ years of B2B enterprise sales experience across ad-tech, SaaS, media, and global hiring. Now building MCP servers for the AI agent ecosystem.
License: MIT
Available Tools
7 toolsaudit_cold_messageA
Audit a drafted cold message against the engine rules: no money/rates, no identity-first opener, specific hook required, soft ask only, under ~90 words, one ask. Returns PASS/FAIL with named violations and a rewrite recipe.
Inputs: message (required), target_type.
build_followup_ladderA
Returns the 5-step follow-up ladder (Day 3 bump, Day 7 value-give, Day 12 new proof, Day 18 soft close, Day 25 break-up) with the move and rule for each rung. 80% of deals close in follow-up; the break-up alone pulls ~30% of replies.
Inputs: target_type.
detect_red_flagsA
Scan a prospect's reply or brief for walk-away signals: exposure-pay, spec-work requests, pay-on-performance, budget mismatch, scope-creep probes. Returns flags found and a CLEAN/CAUTION/WALK verdict.
Inputs: text (required).
get_full_packA
Returns the complete engine: core rules, all target packs, follow-up ladder, reply playbook, pricing menu, red flags. Useful for full agent context (e.g. a Claude Project system prompt).
Inputs: no named parameters.
handle_replyA
Given the type of reply received, returns what it means, the next move, the reply shape, and the trap to avoid. Reply types: price_question, interested, not_now, no_budget, exposure_offer, spec_request, pay_on_performance, ghosted_after_interest.
Inputs: reply_type (required).
structure_cold_pitchA
Get the HOOK / BRIDGE / SOFT ASK structure plus the 4 swap variables (who to pitch, signal to research, proof to lead with, soft-ask object) for a target type. Target types: brand_deal, ugc, newsletter_sponsorship, job, podcast, client_work.
Inputs: target_type (required), signal_found.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A4.4/5.0
Scored across 7 tools
Disambiguation5/5
Each tool targets a distinct stage or aspect of the outbound workflow: pitch creation, pitch audit, reply interpretation, red-flag detection, pricing, follow-up, and full context. No two tools share the same purpose, even though some operate on similar inputs (replies or pitches).
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern in lowercase snake_case (handle_reply, build_pricing_menu, detect_red_flags, get_full_pack, structure_cold_pitch, audit_cold_message, build_followup_ladder). Verbs are clear and parallel.
Tool Count5/5
Seven tools is well-scoped for an outbound engagement engine, covering the core stages without redundancy. The count is within the ideal range and each tool earns its place.
Completeness5/5
The tools cover the full lifecycle: structuring a pitch, auditing it, handling replies, detecting red flags, providing pricing guidance, building follow-up ladders, and retrieving the entire engine context. There are no obvious dead ends or missing operations for the server's stated purpose.
Maintenance
ActivityInactive
ResponsivenessNo recent community issues
Related MCP Connectors
Run B2B outreach from your AI agent: 250+ tools for campaigns, leads, LinkedIn and email workflows.
Run cold email outbound from an AI agent: campaigns, leads, replies, sender accounts, autopilot.
Find LinkedIn prospects, draft outreach, and run human-paced campaigns from your AI agent.
Cold email API for AI agents: connect mailboxes, warm up, run campaigns and handle replies.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables agents to find leads, read buying signals, write and send email and LinkedIn outreach, handle replies, and report results, with built-in safety gates, approvals, limits, and compliance controls.10Apache 2.0
PumpGTM MCP serverofficial
AlicenseNot gradedqualityBmaintenanceEnables AI agents to find intent-signaling buyers and run LinkedIn, email, and X outreach from connected accounts while respecting platform limits. Every reply is handed back to a human for approval or decision.3MIT- AlicenseNot gradedqualityBmaintenanceEnables AI agents to connect to a hosted multichannel B2B outbound engine for LinkedIn messaging, cold email sequencing, and pipeline management, including campaign reads and prospect research. Write actions that send, launch, enroll, or spend credits require chat confirmation before completing.MIT