ListmonkSAFE
MCP (Model Context Protocol) server for Listmonk newsletter management
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An MCP (Model Context Protocol) server implementation for Listmonk, providing programmatic access to newsletter and mailing list management functionality.
Project Status
✅ Implementation Complete - The core MCP server is fully implemented and functional.
Goal
Create an MCP server that enables LLMs and AI assistants to interact with Listmonk instances through the Model Context Protocol. This will allow for:
- Subscriber management (add, remove, update subscribers)
- Mailing list operations (create, manage lists)
- Campaign management (create, send newsletters)
- Analytics and reporting access
- Template and content management
Architecture
This server will bridge the MCP protocol with Listmonk's REST API, providing a standardized interface for AI models to interact with Listmonk installations.
Features
- Complete Listmonk API Coverage: All major Listmonk operations supported
- 18 MCP Tools: Comprehensive subscriber, list, campaign, and template management
- MCP Resources: Easy access to subscriber, list, campaign, and template data
- Async Operations: Built with modern async/await patterns
- Type Safety: Full Pydantic model validation
- Environment Configuration: Easy setup with environment variables
Installation
Using uvx (Recommended)
Install and run directly from PyPI without managing dependencies:
# Run directly (installs if needed) uvx listmonk-mcp --help # Or install globally uvx install listmonk-mcp listmonk-mcp --help
Using pip
pip install listmonk-mcp
Development Installation
git clone https://github.com/rhnvrm/listmonk-mcp.git cd listmonk-mcp uv sync --extra dev
Development
Code Quality Checks
Run the same checks that are executed in the CI/CD pipeline:
# Install development dependencies uv sync --extra dev # Run linting (same as CI) uv run ruff
e686ac7d4c88OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add listmonk-mcp -- uvx listmonk-mcp
{
"mcpServers": {
"listmonk-mcp": {
"command": "uvx",
"args": [
"listmonk-mcp"
]
}
}
}Exposed tools (29)
12 read · 13 write · 4 destructive. Blast radius: 4 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
add_subscriber | write | |
batch_replace_in_campaign_body | read | |
change_subscriber_status | read | |
check_listmonk_health | read | Check if Listmonk server is healthy and accessible. |
create_campaign | write | |
create_mailing_list | write | |
create_template | write | |
delete_mailing_list | destructive | |
delete_media_file | destructive | |
delete_template | destructive | |
get_campaign | read | |
get_campaigns | read | |
get_list_subscribers_tool | read | |
get_mailing_lists | read | |
get_media_list | read | |
get_template | read | |
get_templates | read | |
regex_replace_in_campaign_body | read | |
remove_subscriber | destructive | |
rename_media | write | |
replace_in_campaign_body | read | |
schedule_campaign | write | |
send_campaign | write | |
send_transactional_email | write | |
update_campaign | write | |
update_mailing_list | write | |
update_subscriber | write | |
update_template | write | |
upload_media_file | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
delete_mailing_list, delete_media_file, delete_template, remove_subscriber
.envrc
docs/logo.png
Gates applied: no_behavioural_pass.
e686ac7d4c88full audit observations/trust-audit/mcp-server/rhnvrm__listmonk.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | e686ac7d4c88 | SAFE | B | 89 | first audit |
Questions
What is the Listmonk MCP server?
MCP (Model Context Protocol) server for Listmonk newsletter management
What tools does Listmonk expose?
29 in total: 12 read-only, 13 that write, and 4 that can delete or overwrite (delete_mailing_list, delete_media_file, delete_template, remove_subscriber). Every one is listed on this page with its risk.
Is Listmonk safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 4 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Listmonk need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (e686ac7d4c88), read on 2026-10-08. The repository is watched and re-audited when it changes.