Incident Triage MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AUDIT_MODE | No | Audit log destination: 'stdout' or 'file' | |
| EVIDENCE_DIR | No | Local directory for evidence when EVIDENCE_BACKEND='fs' | |
| MCP_TRANSPORT | No | Transport mode: 'stdio' or 'streamable-http' | |
| AIRFLOW_BASE_URL | No | Base URL for Airflow (required when WORKFLOW_BACKEND='airflow' or EVIDENCE_BACKEND='airflow') | |
| EVIDENCE_BACKEND | No | Evidence backend: 'none', 'fs', 's3', or 'airflow' | |
| MCP_HTTP_API_KEY | No | API key for HTTP auth when MCP_HTTP_AUTH_MODE='api_key' | |
| WORKFLOW_BACKEND | No | Workflow backend: 'none' or 'airflow' | |
| DEPLOYMENT_PROFILE | No | Deployment profile: 'local', 'staging', or 'prod' | |
| MCP_HTTP_AUTH_MODE | No | HTTP auth mode: 'none', 'api_key', or 'jwt_hs256' |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| incident_triage_runC | One-call triage orchestration. Airflow trigger is optional and backend-dependent. |
| alerts_fetch_activeD | – |
| service_health_snapshotD | – |
| logs_fetch_recentD | – |
| traces_fetch_recentD | – |
| runbooks_searchD | – |
| pingD | – |
| mcp_healthD | – |
| mcp_metricsD | – |
| mcp_traces_recentD | – |
| notify_post_updateC | Provider-agnostic notification entrypoint. Routes to Slack or Teams based on provider/env defaults. |
| slack_post_updateB | Post an incident update to Slack via Incoming Webhook. Safe-by-default: dry_run=True returns payload without sending. |
| teams_post_updateC | Post an incident update to Microsoft Teams via Incoming Webhook. Safe-by-default: dry_run=True returns payload without sending. |
| evidence_get_bundleD | – |
| evidence_wait_for_bundleD | – |
| evidence_seed_sampleC | Offline helper: writes a deterministic Evidence Bundle v1 JSON to EVIDENCE_DIR. |
| incident_triage_summaryB | Deterministic (non-LLM) summary of an incident from the Evidence Bundle. |
| jira_draft_ticketD | – |
| jira_create_ticketB | Safe action:
|
| jira_list_projectsD | – |
| jira_list_issue_typesD | – |
| jira_validate_credentialsD | – |
| jira_add_commentA | Add a comment to an existing Jira/ServiceNow ticket. Safe-by-default: dry_run=True returns the comment body without posting. |
| jira_transition_issueA | Transition an existing Jira/ServiceNow ticket to a new workflow state. Safe-by-default: dry_run=True returns the intended transition without applying it. Common transition_name values: 'In Progress', 'Resolved', 'Done', 'Closed'. |
| pd_acknowledge_alertA | Acknowledge a PagerDuty incident via the PagerDuty REST API. Safe-by-default: dry_run=True returns the intended action without sending. Requires PAGERDUTY_API_TOKEN and PAGERDUTY_FROM_EMAIL env vars. |
| pd_resolve_alertB | Resolve a PagerDuty incident via the PagerDuty REST API. Safe-by-default: dry_run=True returns the intended action without sending. Requires PAGERDUTY_API_TOKEN and PAGERDUTY_FROM_EMAIL env vars. |
| opsgenie_acknowledge_alertA | Acknowledge an OpsGenie alert via the OpsGenie REST API. Safe-by-default: dry_run=True returns the intended action without sending. Requires OPSGENIE_API_KEY env var. |
| opsgenie_close_alertA | Close an OpsGenie alert via the OpsGenie REST API. Safe-by-default: dry_run=True returns the intended action without sending. Requires OPSGENIE_API_KEY env var. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/felixkwasisarpong/incident-triage-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server