runframe_list_incidentsLABSCO SUMMARY
The whole incident loop without the browser tab.
It covers an incident end to end — acknowledge, page a responder, log findings to the timeline, escalate, resolve, write the postmortem — from wherever the work is already happening. Because each tool is bound to a scope, you can give an agent a key that reads incidents and updates the timeline but cannot page anyone at 3am.
What it is
Runframe is an incident lifecycle platform covering incident response, on-call, and status pages. This MCP server translates tool calls into Runframe API requests scoped by your API key, so an incident can be handled from an IDE or an agent instead of a browser tab. The server is stateless and stores nothing locally.
What you get
- Incident handling:
runframe_list_incidentsandrunframe_get_incidentread them,runframe_create_incidentopens one, andrunframe_update_incidentedits title, description, severity, or assignment. - Moving an incident along:
runframe_change_incident_statussets new, investigating, fixing, monitoring, resolved, or closed, andrunframe_acknowledge_incidentauto-assigns and starts SLA tracking. - Getting a human involved:
runframe_page_someonepages a responder over Slack or email, andrunframe_escalate_incidentmoves to the next level of the policy. runframe_add_incident_eventadds a timeline entry while the investigation is still running.- On-call lookups:
runframe_get_current_oncallanswers who is on call right now, andrunframe_get_escalation_policyreturns the policy for a severity level. - Postmortems:
runframe_create_postmortemandrunframe_get_postmortem. - Service and people lookups:
runframe_list_services,runframe_get_service,runframe_list_teams, andrunframe_find_user.
Requirements
A recent Node.js and a Runframe API key from your account settings, passed as RUNFRAME_API_KEY. The default stdio transport runs via npx -y @runframe/mcp-server with no network exposure; the streamable HTTP transport for containers and remote hosts additionally takes a bearer token. Every tool declares the API-key scope it needs, so a key can be narrowed to reads.
Setup effort
One command plus a key — claude mcp add runframe -e RUNFRAME_API_KEY=<YOUR_RUNFRAME_API_KEY> -- npx -y @runframe/mcp-server
USE CASES
First response
Acknowledge the page and pull up the incident detail without leaving the editor.
Getting the right person
Find who is on call and page them about the spike you are already looking at.
Keeping the timeline honest
Log what you checked and what you found while you are still checking it.
Escalating a stalled incident
Move to the next level of the policy when the first responder is not making headway.
Writing the postmortem
Draft the postmortem off the incident record while the detail is still fresh.
Agent triage
Let an agent open an incident for an alert and attach it to the service that owns it.
17 tools
Listed in project docs. Your client may show a different list.
runframe_get_incidentrunframe_create_incidentrunframe_update_incidentrunframe_change_incident_statusrunframe_acknowledge_incidentrunframe_add_incident_eventrunframe_escalate_incidentrunframe_page_someonerunframe_get_current_oncallrunframe_list_servicesrunframe_get_servicerunframe_create_postmortemrunframe_get_postmortemrunframe_list_teamsrunframe_get_escalation_policyrunframe_find_userBEFORE YOU INSTALL
What to know first
Tools you get
17 tools named in the project's documentation.
Requires
- npx on PATH
- RUNFRAME_API_KEY in your environment
INSTALLATION
Connect your client
Server setup
Claude Code
claude mcp add runframe -e RUNFRAME_API_KEY=<YOUR_RUNFRAME_API_KEY> -- npx -y @runframe/mcp-serverMCP Clients
Cursor, Claude Desktop
{
"mcpServers": {
"runframe": {
"command": "npx",
"args": [
"-y",
"@runframe/mcp-server"
],
"env": {
"RUNFRAME_API_KEY": "<YOUR_RUNFRAME_API_KEY>"
}
}
}
}VS Code
{
"servers": {
"runframe": {
"command": "npx",
"args": [
"-y",
"@runframe/mcp-server"
],
"env": {
"RUNFRAME_API_KEY": "<YOUR_RUNFRAME_API_KEY>"
}
}
}
}Any MCP client — setup wizard
npx @runframe/mcp-server --setupRun as HTTP server
RUNFRAME_API_KEY=<YOUR_RUNFRAME_API_KEY> MCP_ACCESS_TOKEN=<YOUR_MCP_ACCESS_TOKEN> npx @runframe/mcp-server --transport http --port 3100 --host 127.0.0.1Run HTTP server in Docker
git clone https://github.com/runframe/runframe-mcp-server
cd runframe-mcp-server
docker build -t runframe-mcp-server .
docker run -e RUNFRAME_API_KEY=<YOUR_RUNFRAME_API_KEY> -e MCP_ACCESS_TOKEN=<YOUR_MCP_ACCESS_TOKEN> -p 3100:3100 runframe-mcp-server