
MCP server for Mach GTM — AI-powered B2B outbound sales platform for software teams
MCP server for Mach GTM — AI-powered B2B outbound sales platform for software teams
·
A small, free Model Context Protocol (MCP) server with five outbound sales helpers. It runs inside Claude Desktop, Claude Code, Cursor and other MCP clients.
It is a starter kit from the team behind Mach. The tools shape what you give them into an ICP, a message, a research checklist, a lead score or a sequence. The handlers return templates and rules from supplied inputs. Inspect their fixed assumptions and remove unsupported fallback proof before using an output.
| Tool | What it does |
|---|---|
build_icp | Returns a largely fixed profile with best-customers and deal-size inputs copied into it. The handler accepts but does not use company_description. |
draft_outreach | Drafts a cold email or LinkedIn message from a buying signal and a proof point you provide |
research_prospect | Gives a research checklist and the questions to answer before you reach out |
score_lead | Scores a lead 0-100 against your ICP with a simple, readable formula, plus reasons for and against |
build_sequence | Slices a fixed schedule of up to eight touches. Check the returned length and timing. |
Run it straight from GitHub (needs Node.js 18 or later):
npx -y github:verma6uc/mach-gtm-mcpOr clone and run locally:
git clone https://github.com/verma6uc/mach-gtm-mcp
cd mach-gtm-mcp
npm install
node index.jsAdd to claude_desktop_config.json:
{
"mcpServers": {
"mach-gtm": {
"command": "npx",
"args": ["-y", "github:verma6uc/mach-gtm-mcp"]
}
}
}claude mcp add mach-gtm -- npx -y github:verma6uc/mach-gtm-mcpThe companies and results below are made up.
Build an ICP:
Use the build_icp tool.
company_description: "We sell AI-powered code review tools to engineering teams"
best_customers: "Series B SaaS companies with 20-100 engineers, CTOs worried about code quality at scale"
deal_size: "$30k-$80k ACV"Draft outreach:
Use draft_outreach.
prospect_name: "Sarah"
prospect_title: "VP Engineering"
company_name: "Acme Corp"
buying_signal: "posted about struggling to maintain code quality while scaling the team"
your_offering: "AI code review that catches issues before they hit production"
proof_point: "helped DataCo reduce production bugs by 60% in 90 days"Read every draft before you send it, and check that each fact in it is true.
To use your signed-in Mach workspace from an assistant, follow the hosted connector guide. The remote endpoint is https://machgtm.com/mcp.
The hosted connector checks the connected member's workspace permissions. Research actions return a plan and maximum cost for confirmation.
Read the implementation and capability guide. Use the known-account connection checklist to record the connection and outputs you observe.
The local score starts at 50 and applies the rules in index.js, clamped to 0 through 100. Its confidence label follows the supplied inputs. The score has no measured calibration against meetings or purchases.
The outreach handler inserts generic proof when proof_point is omitted. Supply verified proof or remove that fallback before using a message.
Before changing a handler, write down the intended behaviour and check its failure paths. The AI code-review checklist gives a sequence for reviewing requirements, edge cases, security and test quality. The checklist is part of CodeIntelligently, another project by this maintainer.
Mach is an outbound sales workspace for teams selling software and software services. It reads your website and case studies to learn what you sell, supports sourced account and person research, and drafts outreach under configurable playbook review modes. Confirm the active review mode and permissions before starting. Email, LinkedIn and WhatsApp replies land in one inbox by company.
Mach works with design partners and early adopters. Current terms are available from the team.
MIT
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add mach-gtm -- npx -y github:verma6uc/mach-gtm-mcp{
"mcpServers": {
"mach-gtm": {
"args": [
"-y",
"github:verma6uc/mach-gtm-mcp"
],
"command": "npx"
}
}
}code --add-mcp '{"name":"mach-gtm","args":["-y","github:verma6uc/mach-gtm-mcp"],"command":"npx"}'[mcp_servers.mach-gtm]
command = "npx"
args = ["-y", "github:verma6uc/mach-gtm-mcp"]Runs locally on your device. Your client starts the server itself, so nothing has to be hosted.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/mach-gtm-mcp-server to learn what the "Mach GTM MCP Server" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
npx -y github:verma6uc/mach-gtm-mcpclaude mcp add mach-gtm -- npx -y github:verma6uc/mach-gtm-mcpThis server runs locally, so we can't read its tool list over the web yet.
We could not run this server: it ships no npx package for our sandbox and no public endpoint. The four checks that need a live server are left out, and the grade tops out at B until one exists.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/mach-gtm-mcp-server)Nothing comparable is listed yet.
No tagged releases on record.
Connect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "mach-gtm-mcp-server" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.