
Runframe Mcp Server
io.github.runframePublished by GitHub account runframev0.1.5Updated Oct 24, 2026
MCP server for Runframe incident management covering incidents, on-call, postmortems, and more.
Overview
Runframe MCP server lets an AI assistant manage incident response, on-call lookups, services, postmortems, teams and people from the editor.
- What you can do
- List, read, create and update incidents, change status, acknowledge, add timeline events and escalate them, and page responders via Slack or email. Look up who is currently on call and read escalation policies for a severity level. List services and fetch service details by public service key. Create postmortems and retrieve the postmortem for an incident. List teams and search users by name or email, including inactive users for historical lookups.
- When to use it
- Useful for engineering teams already on Runframe who want to triage, acknowledge, escalate or document incidents and check on-call coverage without leaving the IDE or agent. Also handy for drafting postmortems and resolving people or team names before filtering incidents.
- Requirements
- Runs locally via npx as a stdio process and needs Node.js 20+. Requires a Runframe account and an API key supplied in RUNFRAME_API_KEY (starts with rf_); RUNFRAME_API_URL optionally overrides the API base URL. HTTP transport mode additionally needs MCP_ACCESS_TOKEN. Network access to the Runframe API is required.
Installation
In SourceWeft
- Open Runframe Mcp Server 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
runframe-mcp-server
[CI] [npm] [License: MIT] [Node 20+]
Runframe is the complete incident lifecycle platform for engineering teams, covering incident response, on-call, and status pages. This MCP server lets you manage those workflows from your IDE or AI agent.
17 tools covering incidents, on-call, services, postmortems, teams, and people lookup. Requires Node.js 20+.
Why Use This
- Stay in your editor — acknowledge incidents, page responders, and write postmortems without switching to a browser
- Let agents handle the routine — AI agents can triage, escalate, and update incidents autonomously using scoped API keys
- Zero infrastructure — runs via
npx, no server to deploy for local use
How It Works
The server is stateless. It translates MCP tool calls into Runframe API requests, scoped by your API key permissions. No data is stored locally.
Examples
Ask your agent:
- "Acknowledge incident INC-2026-001" → calls
runframe_acknowledge_incident - "Who is on call right now?" → calls
runframe_get_current_oncall - "Create a postmortem for the database outage" → calls
runframe_create_postmortem - "Page the backend team lead about the API latency spike" → calls
runframe_page_someone - "List all open SEV1 incidents" → calls
runframe_list_incidentswith severity filter - "Find Alex so I can check their open incidents" → calls
runframe_find_user
Install
Get your API key from settings inside Runframe.io, then add to your agent:
Claude Code:
Cursor (~/.cursor/mcp.json) · VS Code (.vscode/mcp.json) · Claude Desktop (claude_desktop_config.json):
Other MCP clients: Add the JSON config above to your client's MCP config file.
Interactive setup wizard:
Environment Variables
Transports
stdio (default) — used by MCP clients like Claude Code and Cursor. No network exposure. This is what the install commands above configure.
Streamable HTTP — for containerized or remote deployments. Requires MCP_ACCESS_TOKEN for bearer auth:
Security Model
Responsibility is split across three boundaries:
- Runframe API handles authorization and scopes via
RUNFRAME_API_KEY. - This MCP server handles process isolation (stdio) and bearer-token validation (HTTP). It also enforces method filtering, Host/Origin checks on localhost, declared Content-Length validation (1 MB limit), 8 KB header limit, and 15s upstream timeout.
- Your reverse proxy handles TLS, rate limiting, and streamed-body enforcement if you expose HTTP mode to a network.
The server stores nothing. It is a pass-through to the Runframe API.
Tools
Incidents (9)
On-call (1)
Services (2)
Postmortems (2)
Teams (2)
Users (1)
Direct API alignment
This MCP server follows the public Runframe direct API contract.
- Incident create requires
service_idscontaining public service keys likesvc_K7M4Q9TZ2H, not internal UUIDs. runframe_get_servicenow looks up services by publicservice_key, not UUID.- Incident tools now follow the latest V1 contract: use incident numbers like
INC-2026-001in path parameters. - Incident update and list filters now use the latest public identifiers where V1 does: assignee/resolver email and
team_name. runframe_create_incidentaccepts an optionalidempotency_key, which is forwarded as theIdempotency-Keyheader for retry-safe creates.runframe_create_incidentdefaultsseveritytoSEV2when omitted, matching the V1 API.- Incident create now mirrors the V1 API limits:
titlemust be 1-200 chars,descriptionmaxes at 10000 chars, andservice_idsallows at most 50 items. - Incident creation depends on valid SLA configuration for the requested severity. If acknowledge or closure deadlines are missing, the API rejects the create.
- Use
runframe_list_servicesto discover validservice_keyvalues before creating incidents. runframe_page_someonenow uses the latest V1 delivery contract:email,channels, and optionalmessage.- Postmortem tools now follow the latest V1 contract: use
incident_numberand snake_case nested fields likeusers_affected,owner_email, andtime_to_acknowledge. - Use
runframe_find_userto resolve a person name to an email address before filtering incidents byassigned_toorresolved_by. - Set
include_inactive=trueonrunframe_find_userwhen you need to resolve former employees in historical incident queries. - Set
is_active=trueoris_active=falseonrunframe_find_userwhen you need an explicit V1 active-state filter. - Use
runframe_list_teamswithsearchto resolve the exactteam_namebefore filtering incidents.
Docker
The Docker image runs HTTP transport by default on port 3100:
Deploying HTTP Mode
HTTP mode is meant for private networks. If you put it on the internet:
- Run behind TLS (nginx, Caddy, cloud LB). This server does not do TLS.
- Use a reverse proxy for rate limiting and request buffering.
- Prefer private subnets or VPNs over public exposure.
- Rotate
MCP_ACCESS_TOKENregularly. Pass old and new tokens comma-separated for zero-downtime swaps.
Rate limiting
The Runframe API enforces rate limits server-side. If you hit a limit, tools return a 429 error with a retry hint. For HTTP transport deployments, your reverse proxy can add additional request-level throttling.
Token rotation
MCP_ACCESS_TOKEN accepts comma-separated tokens:
- Set
MCP_ACCESS_TOKEN=new_token,old_token - Update clients to
new_token - Drop the old one:
MCP_ACCESS_TOKEN=new_token
Limitations
- Read-only for schedules — you can query on-call and escalation policies but not modify them via MCP
- Requires a Runframe account and API key
Contributing
Issues and PRs welcome at github.com/runframe/runframe-mcp-server.
License
Source: README.md at commit f7d76b6
Tools
0Version history
1- v0.1.5LatestSep 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