IRONSCALES MCP Server
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., "@IRONSCALES MCP Serverlist my open phishing incidents from the last 7 days"
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.
IRONSCALES MCP Server
An MCP server for the IRONSCALES Management API (AppAPI v1), the email security platform that turns reported phishing into incidents and removes malicious emails from every affected mailbox. It lets an AI agent read incidents and their details, look up what IRONSCALES knows about a sender, read mitigation statistics and the allow list and, on explicit request, classify incidents (phishing, spam, false positive) and add or remove allow-list entries.
Transport: MCP Streamable HTTP at
POST /mcp, health probe atGET /healthStateless and multi-tenant: credentials arrive on every request as HTTP headers and are never stored; every tool is listed from the first
tools/listPython 3.12, uv, FastMCP, httpx
License: Apache-2.0, Copyright 2026 MSPbots.ai
Authentication headers
Header | Required | Type | Default | Allowed values | Description | Example |
| Yes | string | none | - | The company's AppAPI token |
|
| Yes | integer | none | positive number | IRONSCALES company id the key belongs to |
|
| No | string |
| comma-separated scopes | Token scopes to request when the key does not hold |
|
Where to get them: in the IRONSCALES dashboard the key is under Settings > General > Company
Token. Scopes available to keys: company.all, company.view, company.classify,
company.edit and, for partner keys, partner.all, partner.company.view,
partner.company.classify, partner.company.edit, partner.mitigation.view.
How they are used: the key is exchanged at POST https://appapi.ironscales.com/appapi/get-token/
({"key": ..., "scopes": [...]}) for a JWT, which is sent as Authorization: JWT <token>.
Without X-Ironscales-Scopes the server asks for company.all and, if the key is not allowed
that scope, partner.all. Tokens are cached in memory, keyed by a SHA-256 of the key and the
scopes, until shortly before they expire, and refreshed once when the API rejects one.
A request to /mcp without both required headers gets HTTP 401 naming the missing one; a
non-numeric company id or a malformed scope list gets HTTP 400.
Related MCP server: proofpoint-essentials-mcp
Tools
All tools return a JSON string. write marks tools that change data; confirm marks the
tool that changes mailboxes and also needs confirm: true.
Area | Tools |
Overview |
|
Incidents |
|
Sender lookup |
|
Remediation | confirm: |
Stats |
|
Allow list | write: |
Errors come back as a JSON envelope instead of an exception:
{"error": {"code": "unauthorized", "message": "IRONSCALES returned HTTP 403 for get-token: No company found for API key [<redacted>]", "retryable": false}}code is one of not_configured, unauthorized, not_found, invalid_argument,
rate_limited, upstream_error. Reads are retried with backoff on 429, 5xx and network
errors; writes only on 429. IRONSCALES allows 120 API calls per minute per company.
Run locally
uv sync
uv run python -m ironscales_mcp # listens on 0.0.0.0:8080or with Docker:
docker build --platform linux/amd64 -t ironscales-mcp:dev .
docker run --rm -p 8080:8080 ironscales-mcp:devConfiguration (environment variables, all optional): MCP_HTTP_HOST (default 0.0.0.0),
MCP_HTTP_PORT (default 8080), LOG_LEVEL (default INFO). Credentials are never read
from the environment.
Testing example
# list tools
curl -s http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-H "X-Ironscales-API-Key: your-api-key" \
-H "X-Ironscales-Company-ID: 123456" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
# open incidents
curl -s http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-H "X-Ironscales-API-Key: your-api-key" \
-H "X-Ironscales-Company-ID: 123456" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"ironscales_incidents_list","arguments":{"status":"open","limit":10}}}'Unit tests (no network access needed):
uv run pytestDelivery notes
Tool count (9). Kept as is because the tool names are an existing contract.
Rebuilt on the documented API. The official specification is published at
https://appapi.ironscales.com/appapi/docs/(IRONSCALES Management API v1). Older versions called/api/v1/...routes withX-IronScales-API-Keyheaders, which do not exist (the API answers 404); every tool now uses the AppAPI routes with the JWT exchange.Status words.
open/in_progresslist unclassified incidents,closedclassified ones andpendingchallenged ones (release requests and end-user reports).offsetis rounded down to a whole page because the API pages by page number.Remediation is classification. IRONSCALES acts on an incident by classifying it:
quarantine/deleteclassify it as phishing (the emails are removed from all affected mailboxes),mark_spamas spam,mark_false_positiveas a false positive. The API requires the analyst's email (classifying_user_email) and the current classification, which the tool reads first.block_senderandreport_to_microsofthave no API and return aninvalid_argumenterror. The tool needsconfirm: true.Sender lookup instead of a scan. IRONSCALES has no API that scans an arbitrary email, so
ironscales_email_classifyreturns past incidents from the sender, their classifications and matching allow-list entries, withverdict: null; body, headers, URLs and attachments are not sent anywhere.Stats periods map to the API's presets; 30 days (the default) uses the date-range email and remediation statistics because no preset covers it.
Allow-list removal deletes only entries whose value matches exactly.
Parameters the API cannot honour were removed:
severityon the incident list,reasonandnotify_userson remediation.Not included: the incident "card" UI resource of older versions (an MCP Apps HTML view); the tools return the same data as JSON.
License
This server cannot be deployed
Maintenance
Related MCP Connectors
Governed email for agents: Gmail, M365 and IMAP; per-mailbox permissions, send allowlist, audit log
Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.
Live threat intel for agents: incidents, actors, CVEs with KEV/EPSS, ransomware leak-site victims.
AI agents read & send email, manage mailboxes, domains and webhooks via the QMailing API.
Related MCP Servers
- AlicenseCqualityDmaintenanceEnables AI agents to manage FortiMail email security through the FortiMail Engine API, providing tools for domains, users, queues, reports, logs, and SMTP configuration.561MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to manage MSP-multi-tenant email security: organizations, domains, users, licensing, features, subscription packages, and email flow reporting.Apache 2.0
- AlicenseBqualityBmaintenanceEnables AI agents to query and act on Microsoft Defender XDR incidents, alerts, advanced hunting data, Entra ID logs, threat indicators, device response actions, and vulnerability management via Microsoft Graph and Defender for Endpoint APIs.66Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to review email threats detected by Abnormal Security, inspect the underlying messages, evaluate or trigger remediation, and examine employee-reported campaigns and account-takeover cases through the Abnormal REST API.Apache 2.0