Rootly MCP Server

An MCP server for the Rootly REST API (v1), the incident management and on-call platform. It lets an AI agent read incidents, alerts, on-call schedules, teams, severities and the API user and, on explicit request, declare, update and resolve incidents, acknowledge, resolve, create and update alerts, and manage teams.

• Transport: MCP Streamable HTTP at POST /mcp, health probe at GET /health

• Stateless and multi-tenant: the API token arrives on every request as an HTTP header and is never stored; every tool is listed from the first tools/list

• Python 3.12, uv, FastMCP, httpx

• License: Apache-2.0, Copyright 2026 MSPbots.ai

MSPbots Connector

The MCP Gateway built for MSPs: visible, controlled, and your data stays where it belongs.

Get started at connect.mspbots.ai →

MSPbots Connector gives your AI clients one MCP URL to reach your entire MSP stack (RMM, PSA, documentation, security, finance), and gives you control over who can call which tool and a record of everything that was called.

Hosted service: connect.mspbots.ai · Free to use.

Why Connector

Quick start

1. Sign up at connect.mspbots.ai.

2. Connect your vendors. Pick from 150+ connectors and authorize each one on the vendor's own page, or bring your own API keys. No extra vendor accounts needed.

3. Set access. Create roles and decide which tools each role may call. Nothing is allowed until you allow it.

4. Add your MCP URL to your AI client. Copy the URL from your Connector dashboard into Claude, ChatGPT, Cursor, VS Code, Gemini, Codex, or any MCP-capable client.

5. Ask your AI to do real work, and watch every call appear in the audit log.

Features

Unified gateway

• One MCP URL for all your AI clients

• 150+ connectors across the MSP stack

• Custom MCP servers supported, free

• Authorization happens on each vendor's own page; the AI never sees passwords or tokens

• Bring your own credentials: use the vendor API keys you already have

• Multiple accounts per app; connect once, reuse across AI clients

• Tool search: finds the right action for the task

• One sign-in; vendor credentials are injected behind the scenes and OAuth tokens refresh automatically

Visibility

• Audit log for every tool call (who, which vendor, when)

• Usage dashboard: call volume, top vendors, error rate, per-user activity

• Export audit logs to CSV, or stream to Loki, Graylog, or LogScale (SIEM)

• Optional recording of tool arguments and result summaries (off by default, enabled per organization)

Control

• Per-role, per-tool allowlist, deny by default

• owner / admin / member roles

• SCIM provisioning with Entra ID, Okta, JumpCloud, and Google Workspace

Security

• Credentials encrypted one record at a time (AES-256-GCM, per-record key)

• AI clients authenticate with OAuth 2.1 + PKCE

• Vendor responses are scanned for prompt-injection patterns and returned as structured data. This is one layer of defense, not a guarantee against every attack.

• Static egress IP for customer firewall and API allowlisting

Pricing

Free.

Links: connect.mspbots.ai · mspbots.ai

Related MCP server: PagerDuty MCP Server

Authentication headers

Where to get it: an admin creates an API key in Rootly's organization settings (API keys). A global key works across the organization; a team or personal key is limited to what that team or user can see and change. Use a key whose permissions cover incidents, alerts, schedules and teams.

How the token is sent to Rootly: as Authorization: Bearer <token> to https://api.rootly.com/v1/..., with the JSON:API media type. Values that look like unresolved templates (${...}) are treated as missing.

A request to /mcp without the header gets HTTP 401 naming it.

Tools

All tools return a JSON string. JSON:API resources are flattened to {id, type, ...attributes} with related ids as <relationship>_id / <relationship>_ids. List tools take limit (default 25, at most 100) and page and return {items, count, total, page, total_pages, has_more} under the resource name. The incidents, alerts, schedules and teams lists also take offset (record position, overriding page) and return offset / next_offset: when a page is too large for the response size limit and is cut, next_offset continues right after the last record returned, which page cannot (the rest of a cut page is on no other page).

Errors come back as a JSON envelope instead of an exception:

{"error": {"code": "invalid_argument", "message": "Rootly returned HTTP 422 for incidents: title: can't be blank", "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.

Run locally

uv sync
uv run python -m rootly_mcp          # listens on 0.0.0.0:8080

or with Docker:

docker build --platform linux/amd64 -t rootly-mcp:dev .
docker run --rm -p 8080:8080 rootly-mcp:dev

Configuration (environment variables, all optional): MCP_HTTP_HOST (default 0.0.0.0), MCP_HTTP_PORT (default 8080), LOG_LEVEL (default INFO). The token is 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-Rootly-Api-Token: rootly_xxxxxxxxxxxxxxxx" \
  -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-Rootly-Api-Token: rootly_xxxxxxxxxxxxxxxx" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"rootly_incidents_list","arguments":{"status":"started"}}}'

Unit tests (no network access needed):

uv run pytest

Delivery notes

• All tools always listed. Older versions only listed the navigation tools until one was called. Behind a stateless gateway that hid every other tool, so this version lists all 23 tools up front. rootly_navigate and rootly_back remain for compatibility and only describe the tools.

• Built on the published API reference. Every call follows Rootly's OpenAPI document. Corrections compared with the older version: on-call schedules come from /schedules; incidents are updated with PUT and resolved through PUT /incidents/{id}/resolve; alerts are acknowledged / resolved through POST /alerts/{id}/acknowledge|resolve; incident teams are sent as group_ids; teams use the API's groups resource type with user_ids as an attribute.

• Parameters. rootly_alerts_create no longer takes severity (the API has no such alert field) and gained description; the resolve tools gained an optional resolution_message; rootly_alerts_update status is limited to the transitions the API supports.

• Deletes. rootly_org_teams_delete needs confirm: true.

• Gateway registration. Rootly is not in the gateway registry yet; register it with the single credential field X-Rootly-Api-Token.

License

Apache License 2.0 - see LICENSE and NOTICE.