
Ironscales
io.github.WYRE-AIPublished by GitHub account WYRE-AIv2.0.1Updated Nov 21, 2026
MCP server for Ironscales phishing incident management — incidents, mailboxes, and reporting.
Overview
Connects an AI assistant to Ironscales email security to investigate phishing incidents, classify email, run remediations and view security stats.
- What you can do
- Check connection status and list available tools
- List and open phishing incidents, with an interactive incident card in MCP Apps hosts
- Investigate and classify email
- Manage email allowlists and blocklists
- Execute email remediations and quarantine
- View company security statistics and reporting
- When to use it
- Useful for security or MSP teams that run Ironscales and want an assistant to triage phishing incidents, look up incident details, and carry out remediation or allowlist changes from a chat session.
- Requirements
- Runs as a local process (npm package or container image) over stdio, or as an HTTP service when hosted. Requires an Ironscales API key in IRONSCALES_API_KEY and a company/tenant ID in IRONSCALES_COMPANY_ID; AUTH_MODE can switch to gateway header injection. Network access to Ironscales is needed.
Installation
In SourceWeft
- Open Ironscales in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Ironscales MCP Server
A Model Context Protocol (MCP) server for Ironscales email security. Enables AI assistants to investigate phishing incidents, manage email classification, execute remediations, and view security statistics.
This is a Model Context Protocol (MCP) server that connects Claude (or any MCP-compatible AI) to your Ironscales environment.
Part of the MSP Claude Plugins ecosystem — a growing suite of AI integrations for the MSP stack. Built by MSPs, for MSPs.
Interactive Incident Card (MCP Apps)
ironscales_incidents_get renders as an interactive card in MCP Apps hosts
(Claude Desktop/web) showing the phishing incident's subject, status, severity,
sender, affected recipients, and threat indicators; plain-JSON behavior is
unchanged in other hosts. The card is read-only — remediation stays with the
model-driven remediation tools. It is neutral by default and brandable via
window.__BRAND__ injection or MCP_BRAND_* env vars (MCP_BRAND_NAME,
MCP_BRAND_LOGO_URL, MCP_BRAND_PRIMARY_COLOR, MCP_BRAND_ACCENT_COLOR,
MCP_BRAND_BG, MCP_BRAND_TEXT) — no rebuild needed.
Installation
Configuration
Set the following environment variables:
Usage
Running with Claude Desktop
Add to your Claude Desktop claude_desktop_config.json:
Running with Claude Code (CLI)
Docker
Available Tools
Every tool is listed and callable immediately; there is no domain to enter first. The groupings below are documentation only.
Upgrading?
ironscales_navigateandironscales_backare removed. Call the domain tools directly.ironscales_statusstill works and now lists the available tools.
Status
ironscales_status- Connection status and the available tools
Allowlist
ironscales_allowlist_manage- Manage email allowlists and blocklists
ironscales_email_classify- Email investigation and classification
Incidents
ironscales_incidents_list- List phishing incidentsironscales_incidents_get- Get a phishing incident
Remediation
ironscales_remediation_act- Execute email remediations and quarantine
Stats
ironscales_stats_company- Security statistics and reporting
Development
Contributing
Contributions are welcome! Please see CONTRIBUTING.md if present, or open an issue to discuss changes.
License
Licensed under the Apache License, Version 2.0. See LICENSE for details.
Source: README.md at commit 2b66db5
Tools
0Version history
4- v2.0.1LatestNov 21, 2026
- v2.0.0Nov 20, 2026
- v1.2.3Oct 13, 2026
- v1.2.2Sep 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 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- 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