MuntuAI

io.github.design-smithPublished by GitHub account design-smithv1.0.0Updated Oct 24, 2026

Hosted MCP server for MuntuAI outreach campaigns, leads, senders, domains, and analytics.

VerifiedStreamable HTTPWeb executableCommunication & CollaborationBusiness & Commerce

Overview

AI-generated overview

Hosted MCP server for MuntuAI email outreach, letting an assistant manage campaigns, leads, senders, domains and webhooks in a workspace.

What you can do
Read workspace, domain, sender, campaign, draft-plan and event resources through muntu:// URIs with pagination and filters. Create, launch, pause, resume, monitor and send email campaigns, and review drafts. Import leads from an array or CSV URL, enrich and sample them. Add, verify and check domains; create, delete, health-check and assign senders. Preview, refine and generate campaign email content, and subscribe to workspace events via webhooks.
When to use it
Use it when an assistant should operate a MuntuAI email outreach workspace: launching or monitoring campaigns, importing and enriching leads, setting up sending domains, or wiring webhook notifications into an agent workflow.
Requirements
A remote MCP endpoint over streamable HTTP; no local package. A MuntuAI account and an agent key created in Settings, sent as an Authorization bearer token in the form Bearer mnt_ . . The key is bound to one workspace and carries an autonomy level (observer, copilot or autonomous). Network access to the MuntuAI API.
Before you install
The agent key is a secret shown only once; store it in an environment variable or secret manager, not in source control or shared files. The autonomy level decides what the agent may do: copilot can create and modify, autonomous can also pause, resume and delete. Sending campaigns and publishing DNS records for domain verification affect real email delivery and external systems. Rejected calls are logged.

Installation

In SourceWeft

  1. Open MuntuAI in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.design-smith%2Fmuntuai-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "muntuai": {
      "type": "http",
      "url": "https://api.muntuai.com/api/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

MuntuAI MCP

This repository contains the public documentation, manifest, and reference clients for the live MuntuAI MCP server. The runnable server implementation lives in the main Muntu backend.

The official Model Context Protocol (MCP) server for MuntuAI — giving AI agents programmatic access to email outreach campaigns, lead management, domain infrastructure, and real-time workspace events.

What This Is

MuntuAI is an AI-native email outreach platform. This MCP server lets external agents (Claude, Cursor, custom scripts) connect to a MuntuAI workspace and perform actions: create campaigns, import leads, verify domains, send emails, and subscribe to webhook events — all through a standard MCP interface over HTTP.

Protocol: Model Context Protocol over HTTP (JSON-RPC 2.0)
Transport: Streamable HTTP (text/event-stream or application/json)
Server protocol revision: 2025-03-26
Server URL: https://api.muntuai.com/api/mcp

Quick Start

1. Get an agent key

Log in to app.muntuai.com, go to Settings → Agent Keys, and create a key. Choose the autonomy level that matches what your agent needs:

LevelWhat it can do
observerRead anything — campaigns, leads, domains, senders, events
copilotRead + create and modify — campaigns, domains, senders, leads, webhooks
autonomousEverything above + pause, resume, delete

You will see the raw key once: mnt_<keyId>.<secret>. Copy it immediately.

2. Configure your client

Security note: store the raw agent key in an environment variable or secret manager. Do not commit it to source control or paste it into shared files.

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

json
{  "mcpServers": {    "muntu": {      "url": "https://api.muntuai.com/api/mcp",      "headers": {        "Authorization": "Bearer ${env:MUNTU_AGENT_KEY}"      }    }  }}

Cursor (.cursor/mcp.json or Settings → MCP):

json
{  "mcpServers": {    "muntu": {      "url": "https://api.muntuai.com/api/mcp",      "headers": {        "Authorization": "Bearer ${env:MUNTU_AGENT_KEY}"      }    }  }}

Python:

bash
pip install requestsexport MUNTU_AGENT_KEY="mnt_YOUR_KEY_HERE"python clients/python/muntu_mcp_client.py list-campaigns

Recommended:

bash
export MUNTU_SESSION_ID="$(uuidgen)"

Muntu uses the optional MUNTU_SESSION_ID to group requests into one logical MCP session for session-scoped safety controls and budgeting.

3. Make your first call

Once connected, ask your agent:

"List all campaigns in my MuntuAI workspace"

The agent will call resources/read on muntu://campaigns/{workspaceId} and return the campaign list.

Or via Python CLI:

bash
python clients/python/muntu_mcp_client.py list-campaignspython clients/python/muntu_mcp_client.py list-domainspython clients/python/muntu_mcp_client.py list-emails

What Agents Can Do

Resources (read-only views)

ResourceURIDescription
workspacemuntu://workspace/{id}Profile, policy, infrastructure counts
domainsmuntu://domains/{id}?cursor=0&limit=50All domains with DNS and verification state
sendersmuntu://senders/{id}?cursor=0&limit=50All email accounts with status
campaignsmuntu://campaigns/{id}?cursor=0&limit=20Unified campaign list
campaign-plansmuntu://campaign-plans/{id}?cursor=0&limit=20Draft review queue
eventsmuntu://events/{id}?cursor=0Recent system events (filterable)

Tools (30 total)

Grouped by domain — see tools/README.md for the full index.

  • Campaigns — create, launch, pause, resume, monitor, review drafts, send
  • Leads — import from array or CSV URL, enrich, sample
  • Senders — create, delete, health check, assign to campaign
  • Domains — add, verify, check status
  • Email generation — preview, refine, generate campaign guide
  • Webhooks — subscribe to workspace events
  • Meta — get agent key info

Repository Structure

muntuai-mcp/├── README.md                    # This file├── QUICKSTART.md                # 5-minute setup guide├── docs/│   ├── authentication.md        # Token format, headers, rate limits│   ├── autonomy-levels.md       # Permission model│   ├── resources.md             # All 6 resources with schemas│   ├── events.md                # All event types and payloads│   ├── webhooks.md              # Register, sign, verify│   └── errors.md                # Error codes and handling├── tools/│   ├── README.md                # Full tool index│   ├── campaigns.md│   ├── leads.md│   ├── senders.md│   ├── domains.md│   ├── email-generation.md│   └── meta.md├── workflows/│   ├── README.md                # What workflows are│   ├── launch-first-campaign.md│   ├── review-and-send-drafts.md│   ├── domain-setup.md│   └── monitor-campaign.md├── reference/│   ├── event-types.md│   ├── resource-schemas.md│   └── tool-schemas.md├── clients/│   └── python/│       ├── muntu_mcp_client.py  # Reference Python client│       ├── README.md│       └── examples/├── agent-guides/│   ├── for-claude.md│   ├── for-cursor.md│   └── decision-guide.md└── .well-known/    └── mcp-manifest.json        # Machine-readable capabilities manifest

Key Concepts

Workspace — All data in MuntuAI is scoped to a workspace. Your agent key is bound to one workspace and can only access data within it.

Autonomy levels — Every tool has a minimum required level. If your key's level is below the requirement, the call is rejected and the attempt is logged. See docs/autonomy-levels.md.

Campaign lifecycle — uploaded → enriching → drafting → sending → completed. Agents can observe this lifecycle through get_campaign_performance and the events resource. See workflows/monitor-campaign.md.

Domain verification — Before sending, a domain must be verified with the email provider. This involves publishing DNS records and triggering verification. See workflows/domain-setup.md.

Support

Source: README.md at commit b959b64

Tools

0
This server asks for a credential such as an API key, so SourceWeft could not read its tools without one and has not indexed them.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.