sumo-logic-mcp
Provides 37 tools for interacting with Sumo Logic, enabling search and analytics, monitor management, alert management, dashboard management, collector and source management, and metrics queries.
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., "@sumo-logic-mcp list all monitors with critical status"
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.
sumo-logic-mcp
MCP server for Sumo Logic — 48 tools for searching logs, managing monitors, alerts, dashboards, collectors, metrics, content library, users, roles, fields, partitions, lookup tables, and ingest budgets.
Generic and org-agnostic. Any team can plug in their own Sumo Logic credentials and start querying.
Note: This is an experimental, community-driven project — not an official Sumo Logic product. Feel free to test it and use it.
Installation
pip install sumo-logic-mcpOr run without installing (via uv):
uvx sumo-logic-mcpRelated MCP server: Unofficial FortiMonitor MCP Server
Setup
1. Get Access Credentials
Log in to your Sumo Logic account (e.g.,
https://<your-org>.sumologic.com)Click on your profile icon (top right) and go to Preferences
Scroll to My Access Keys and click Add Access Key
Give it a name, leave scopes to default or set as needed
Copy both the Access ID and Access Key
2. Configure Your MCP Client
Add to your MCP client configuration (e.g., ~/.cursor/mcp.json or Claude Desktop config):
{
"mcpServers": {
"sumologic": {
"command": "uvx",
"args": ["sumo-logic-mcp"],
"env": {
"SUMOLOGIC_ACCESS_ID": "<your-access-id>",
"SUMOLOGIC_ACCESS_KEY": "<your-access-key>",
"SUMOLOGIC_ENDPOINT": "https://api.sumologic.com"
}
}
}
}Or run directly:
export SUMOLOGIC_ACCESS_ID="your-access-id"
export SUMOLOGIC_ACCESS_KEY="your-access-key"
export SUMOLOGIC_ENDPOINT="https://api.sumologic.com"
sumo-logic-mcpTool Reference
Search & Analytics (4 tools)
Tool | Description | Required Params |
| Execute a log search (full lifecycle: create job, poll, fetch, cleanup) |
|
| Check status of a running search job |
|
| Fetch messages or records from a search job |
|
| Cancel a running search job |
|
search_logs optional params: from_time (default -15m), to_time (default now), timezone (default UTC), limit (default 100), by_receipt_time, timeout (default 300s).
Time formats: ISO 8601 (2024-01-15T09:00:00), relative (-15m, -1h, -2d, -1w), epoch ms (1718745600000), or now.
Monitor Management (10 tools)
Tool | Description | Required Params |
| List all monitors | — |
| Search by name or status filter |
|
| Get full monitor configuration |
|
| Create a new monitor |
|
| Update monitor config (read-modify-write) |
|
| Delete a monitor (irreversible) |
|
| Enable a disabled monitor |
|
| Disable a monitor |
|
| Get current health/triggering state |
|
| Get alert history for a monitor |
|
Alert Management (3 tools)
Tool | Description | Required Params |
| Get all currently firing alerts | — |
| Get detailed alert info for a monitor |
|
| Resolve an alert by disabling its monitor |
|
Dashboard Management (5 tools)
Tool | Description | Required Params |
| List dashboards with pagination | — |
| Get full dashboard config |
|
| Create a dashboard with panels and layout |
|
| Update dashboard config (read-modify-write) |
|
| Delete a dashboard (irreversible) |
|
Collector & Source Management (8 tools)
Tool | Description | Required Params |
| List all collectors | — |
| Get collector configuration |
|
| Create a new Hosted collector |
|
| Update collector config (with ETag locking) |
|
| Delete a collector and its sources |
|
| List sources on a collector |
|
| Get source configuration |
|
| Create an HTTP source (returns endpoint URL) |
|
Metrics (4 tools)
Tool | Description | Required Params |
| Execute a metrics query |
|
| Discover available metric names | — |
| Get dimensions for a metric |
|
| List metric content types | — |
Content Library (3 tools)
Tool | Description | Required Params |
| Get your personal content folder and children | — |
| Get a folder and its child items |
|
| Look up content by library path |
|
Administration (8 tools)
Tool | Description | Required Params |
| List all users with emails, roles, status | — |
| List roles with capabilities and filters (v2) | — |
| List all fields (built-in + custom) | — |
| List FERs with scopes and parse expressions | — |
| List partitions with routing and retention | — |
| List lookup tables with schemas | — |
| Get a lookup table's config and fields |
|
| List ingest budgets with scopes and capacity | — |
Utility (3 tools)
Tool | Description | Required Params |
| Verify API connectivity and auth | — |
| Get account status and ingestion info | — |
| Check if a query is syntactically valid |
|
Usage Examples
Once configured, just ask your AI assistant naturally:
"Search for 500 errors in the last hour"
"Show me all critical alerts"
"Create a monitor for high error rates on our API"
"List all hosted collectors"
"What CPU metrics are available?"
"Show me the field extraction rules"
"List all partitions and their retention periods"Development
git clone https://github.com/rajfirke/sumo-logic-mcp.git
cd sumo-logic-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
# Lint
ruff check src/ tests/
# Test
pytest -v
# Run locally
export SUMOLOGIC_ACCESS_ID="..."
export SUMOLOGIC_ACCESS_KEY="..."
export SUMOLOGIC_ENDPOINT="https://api.sumologic.com"
sumo-logic-mcpArchitecture
src/sumo_logic_mcp/
├── __init__.py # Exports mcp, triggers tool registration
├── __main__.py # Entry point: python -m sumo_logic_mcp
├── server.py # FastMCP instance + lifespan (shared HTTP client)
├── client.py # Async HTTP client (httpx, Basic Auth, retry, cookies)
├── validation.py # Time parsing and validation
└── tools/
├── __init__.py # Imports all tool modules
├── search.py # 4 search tools
├── monitors.py # 10 monitor tools
├── alerts.py # 3 alert tools
├── dashboards.py # 5 dashboard tools
├── collectors.py # 8 collector/source tools
├── metrics.py # 4 metrics tools
├── content.py # 3 content library tools
├── admin.py # 8 admin tools (users, roles, fields, partitions, etc.)
└── utils.py # 3 utility toolsAvailable Tools
48 toolscancel_searchA
Cancel a running search job and free server-side resources.
Inputs: job_id (required). Returns: result
check_connectionA
Verify that the Sumo Logic API connection is working.
Tests authentication and endpoint reachability. Use this to confirm credentials are configured correctly.
Inputs: no named parameters. Returns: result
create_dashboardA
Create a new dashboard with panels, layout, and variables.
Panels use a 24-column grid layout. Each panel needs a unique 'key' that maps to a layoutStructures entry defining its grid position (x, y, width, height).
Panel types: TextPanel (markdown text), SumoSearchPanel (log/ metric queries with charts), ServiceMapPanel, TracesListPanel.
Inputs: title (required), layout_json (required), panels_json (required), theme, +5 more. Returns: result
create_hosted_collectorA
Create a new Hosted collector.
Hosted collectors are cloud-managed and used for HTTP sources, cloud-to-cloud integrations, and AWS polling sources. Installed collectors cannot be created via API.
Inputs: name (required), category, description, fields_json. Returns: result
create_http_sourceA
Create an HTTP source on a Hosted collector.
Returns the source config including the unique HTTP endpoint URL where data can be sent via POST.
Inputs: name (required), collector_id (required), category, description, +2 more. Returns: result
create_monitorA
Create a new Sumo Logic monitor.
For simple threshold monitors, use threshold/trigger_type params. For complex monitors (anomaly, outlier, multiple triggers, webhook notifications), pass triggers_json and/or notifications_json with the full JSON arrays.
Inputs: name (required), query (required), threshold (required), playbook, +11 more. Returns: result
delete_collectorA
Delete a collector and all its sources.
WARNING: This action is irreversible. All sources on this collector will also be deleted.
Inputs: collector_id (required). Returns: result
delete_dashboardB
Delete a dashboard.
WARNING: This action is irreversible.
Inputs: dashboard_id (required). Returns: result
delete_monitorA
Delete a monitor and all its associated alerts.
WARNING: This action is irreversible.
Inputs: monitor_id (required). Returns: result
disable_monitorA
Disable a monitor to stop evaluation and alerting.
Inputs: monitor_id (required). Returns: result
enable_monitorA
Enable a disabled monitor so it resumes evaluating.
Inputs: monitor_id (required). Returns: result
get_account_usageA
Get account status and data ingestion information.
Inputs: no named parameters. Returns: result
get_active_alertsA
Get all currently active/firing alerts.
Returns monitors in a triggered state. Filter by severity using the status parameter: Critical, Warning, MissingData, or AllTriggered for all.
Inputs: limit, status. Returns: result
get_alert_detailsA
Get detailed information about an active alert.
Returns the monitor's status, trigger conditions, queries, notification config, and playbook.
Inputs: monitor_id (required). Returns: result
get_collectorA
Get a collector's full configuration and status.
Inputs: collector_id (required). Returns: result
get_content_by_pathA
Look up a content item by its library path.
Returns the item's ID, name, type, and parent info. Paths start with /Library/.
Inputs: path (required). Returns: result
get_dashboardA
Get a dashboard's full configuration.
Returns the complete definition including panels, layout, variables, time range, and visual settings.
Inputs: dashboard_id (required). Returns: result
get_folderA
Get a content folder and its children.
Returns the folder metadata and a list of child items (searches, dashboards, sub-folders) with their IDs and types.
Inputs: folder_id (required). Returns: result
get_lookup_tableA
Get a lookup table's configuration and schema.
Returns the table's field definitions, primary keys, TTL, size limit action, and parent folder ID.
Inputs: table_id (required). Returns: result
get_metric_metadataA
Get metadata (dimensions and their values) for a metric.
Runs a short query for the named metric and extracts all dimension keys and sample values from the results.
Inputs: metric_name (required), from_time. Returns: result
get_monitorA
Get a monitor's full configuration and current status.
Inputs: monitor_id (required). Returns: result
get_monitor_historyA
Get alert/trigger history for a monitor.
Returns events within the time range. Falls back to current status if the history endpoint is unavailable.
Inputs: monitor_id (required), to_time, from_time. Returns: result
get_monitor_statusA
Get the current health and triggering state of a monitor.
Returns whether the monitor is Normal, Critical, Warning, MissingData, or Disabled.
Inputs: monitor_id (required). Returns: result
get_personal_folderA
Get the current user's personal content folder.
Returns the root of your personal library including child items (saved searches, dashboards, folders). Use the returned ID as a starting point to navigate the content library.
Inputs: no named parameters. Returns: result
get_search_resultsA
Fetch results from a search job.
Use 'messages' for raw log lines. Use 'records' for aggregated results (queries with count, sum, avg, group by, etc.). Supports pagination via offset and limit.
Inputs: job_id (required), limit, offset, result_type. Returns: result
get_search_statusA
Check the status of a running or completed search job.
Returns the current state, message count, record count, and any pending warnings or errors since the last status check.
Inputs: job_id (required). Returns: result
get_sourceB
Get a source's full configuration.
Inputs: source_id (required), collector_id (required). Returns: result
list_collectorsB
List all collectors with their IDs, names, types, and status.
Inputs: limit, offset, filter_type. Returns: result
list_dashboardsA
List dashboards with pagination.
Returns dashboard titles, IDs, and descriptions. Use the 'next' token from the response to fetch subsequent pages.
Inputs: limit, token. Returns: result
list_field_extraction_rulesA
List field extraction rules (FERs).
Returns rule names, scopes, parse expressions, enabled status, and extracted field names. FERs automatically parse fields from log messages at ingest time.
Inputs: limit, token. Returns: result
list_fieldsA
List all fields (built-in and custom).
Returns field names, data types, and states. Useful for understanding what fields are available for searching and building field extraction rules.
Inputs: no named parameters. Returns: result
list_ingest_budgetsA
List all ingest budgets (v2).
Returns budget names, scopes, capacity in bytes, timezone, reset time, and actions taken when capacity is exceeded. Ingest budgets control data volume limits per scope.
Inputs: limit, token. Returns: result
list_lookup_tablesA
List all lookup tables.
Returns table names, descriptions, field schemas, primary keys, TTL settings, and size limit actions. Lookup tables are used for enrichment in search queries via the 'lookup' operator.
Inputs: limit, token. Returns: result
list_metric_definitionsA
List available metric names.
Discovers metrics by running a short-range query and extracting unique metric names from the results. Use filter_query to narrow by source category, content type, or other dimensions.
Inputs: from_time, filter_query. Returns: result
list_metric_namespacesA
List metric namespaces (content types).
Discovers available metric sources by querying for unique _contentType values (e.g. HostMetrics, AwsCloudWatch, MetricFromLog). These serve as logical namespaces.
Inputs: from_time. Returns: result
list_monitorsB
List all monitors with their names, IDs, types, and statuses.
Inputs: limit, offset. Returns: result
list_partitionsA
List all index partitions.
Returns partition names, routing expressions, analytics tiers, retention periods, and whether they're included in default searches. Partitions control how data is indexed and retained.
Inputs: limit, token. Returns: result
list_rolesA
List all roles in the account (v2 API).
Returns role names, capabilities, assigned users, and data access filters (log analytics, audit, security).
Inputs: limit, token. Returns: result
list_sourcesA
List all sources configured on a collector.
Inputs: collector_id (required). Returns: result
list_usersA
List all users in the account.
Returns user names, emails, role IDs, active status, and last login timestamps. Supports pagination via token.
Inputs: limit, token. Returns: result
query_metricsA
Execute a metrics query and return time-series data.
Uses the same query syntax as the Sumo Logic UI. Supports operators like avg, sum, min, max, rate, delta, topk, outlier, predict, and grouping with 'by'.
Inputs: query (required), rollup, to_time, from_time, +1 more. Returns: result
resolve_alertA
Resolve an active alert by disabling its monitor.
Sumo Logic auto-resolves alerts when trigger conditions are no longer met. For manual resolution, this disables the monitor to stop the alert. Use enable_monitor to reactivate afterward.
Inputs: monitor_id (required). Returns: result
search_logsA
Execute a Sumo Logic log search and return results.
Handles the full search lifecycle: creates a job, polls until done, fetches results, and cleans up. For aggregation queries (containing count, sum, avg, group by, etc.) returns aggregated records. For raw queries returns log messages.
Inputs: query (required), limit, timeout, to_time, +3 more. Returns: result
search_monitorsA
Search monitors by name, description, or status filter.
Filter examples: monitorStatus:Critical, monitorStatus:Warning, monitorStatus:AllTriggered, type:MonitorsLibraryMonitor.
Inputs: query (required), limit, offset. Returns: result
update_collectorA
Update a collector's configuration (read-modify-write).
Fetches current config with ETag, merges your changes, and saves with optimistic locking.
Inputs: fields_json (required), collector_id (required). Returns: result
update_dashboardA
Update a dashboard's configuration (read-modify-write).
Fetches the current config, merges your changes, and saves. Pass a JSON object with only the fields you want to change. For panels/layout, pass the complete arrays.
Inputs: fields_json (required), dashboard_id (required). Returns: result
update_monitorA
Update a monitor's configuration (read-modify-write).
Fetches the current config, merges your changes, and saves. Pass a JSON object with only the fields you want to change.
Inputs: monitor_id (required), fields_json (required). Returns: result
validate_queryA
Check if a Sumo Logic query is syntactically valid.
Creates a minimal search job (1-second range) and immediately cancels it. Returns valid=true if the query was accepted, or the specific error message if it was rejected.
Inputs: query (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 48 tools
Most tools have distinct purposes, but some potential overlap exists: get_active_alerts vs list_monitors with status filters, and resolve_alert vs disable_monitor could confuse agents. Overall, the descriptions clarify the boundaries well.
The naming follows a mostly consistent verb_noun pattern with list_ for collections and get_ for single items, but there are exceptions like get_active_alerts (a list) and get_search_results (retrieval). The mixed use of list_ and get_ for similar operations is a minor inconsistency.
At 48 tools, the set is far beyond the typical range and exceeds the 25+ threshold. While the platform is broad, this many tools creates significant selection overhead for agents.
The tool set covers core workflows like search, monitors, dashboards, and collectors, but has notable gaps: no update_source or delete_source, no create/update/delete for lookup tables, field extraction rules, or many listed resources. Many resources are read-only, which limits administrative use cases.
Maintenance
Related MCP Connectors
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
Marketo MCP server for AI. 130 tools to operate Marketo from Claude, Cursor, or ChatGPT.
One OAuth connector for your team's remote MCP servers, with Tool Packs, guardrails and logs.
A paid remote MCP for CLI tool MCP, built to return verdicts, receipts, usage logs, and audit-ready
Related MCP Servers
- -licenseBqualityNot gradedmaintenanceMCP server for Akamai APIs. 198 tools covering Property Manager, Edge DNS, CPS, WAF, and reporting. Built with TypeScript, featuring modular architecture, comprehensive testing, and multi-account support. Make Akamai accessible to AI assistants.19 npm10-
- AlicenseNot gradedqualityDmaintenanceMCP server for the FortiMonitor v2 monitoring API. 241 tools across 33 modules covering server management, outage monitoring, maintenance windows, metrics, notifications, cloud monitoring, SNMP, dashboards, reporting, and more. Unofficial community project, not affiliated with Fortinet. Python, MIT license, Docker and local deployment supported.3MIT
- FlicenseBqualityBmaintenanceMCP server that integrates with Sumo Logic's API to perform log searches, data discovery, metrics queries, and monitoring.1522 npm-
- AlicenseNot gradedqualityDmaintenanceEnables interaction with Sumo Logic's REST APIs through MCP, allowing log search, dashboard management, metrics querying, collector and monitor operations.5MIT