Skip to main content
Glama
sumo-logic-mcp

sumo-logic-mcp

by rajfirke

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-mcp

Or run without installing (via uv):

uvx sumo-logic-mcp

Related MCP server: Unofficial FortiMonitor MCP Server

Setup

1. Get Access Credentials

  1. Log in to your Sumo Logic account (e.g., https://<your-org>.sumologic.com)

  2. Click on your profile icon (top right) and go to Preferences

  3. Scroll to My Access Keys and click Add Access Key

  4. Give it a name, leave scopes to default or set as needed

  5. 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-mcp

Tool Reference

Search & Analytics (4 tools)

Tool

Description

Required Params

search_logs

Execute a log search (full lifecycle: create job, poll, fetch, cleanup)

query

get_search_status

Check status of a running search job

job_id

get_search_results

Fetch messages or records from a search job

job_id

cancel_search

Cancel a running search job

job_id

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_monitors

List all monitors

—

search_monitors

Search by name or status filter

query

get_monitor

Get full monitor configuration

monitor_id

create_monitor

Create a new monitor

name, query, threshold

update_monitor

Update monitor config (read-modify-write)

monitor_id, fields_json

delete_monitor

Delete a monitor (irreversible)

monitor_id

enable_monitor

Enable a disabled monitor

monitor_id

disable_monitor

Disable a monitor

monitor_id

get_monitor_status

Get current health/triggering state

monitor_id

get_monitor_history

Get alert history for a monitor

monitor_id

Alert Management (3 tools)

Tool

Description

Required Params

get_active_alerts

Get all currently firing alerts

—

get_alert_details

Get detailed alert info for a monitor

monitor_id

resolve_alert

Resolve an alert by disabling its monitor

monitor_id

Dashboard Management (5 tools)

Tool

Description

Required Params

list_dashboards

List dashboards with pagination

—

get_dashboard

Get full dashboard config

dashboard_id

create_dashboard

Create a dashboard with panels and layout

title, panels_json, layout_json

update_dashboard

Update dashboard config (read-modify-write)

dashboard_id, fields_json

delete_dashboard

Delete a dashboard (irreversible)

dashboard_id

Collector & Source Management (8 tools)

Tool

Description

Required Params

list_collectors

List all collectors

—

get_collector

Get collector configuration

collector_id

create_hosted_collector

Create a new Hosted collector

name

update_collector

Update collector config (with ETag locking)

collector_id, fields_json

delete_collector

Delete a collector and its sources

collector_id

list_sources

List sources on a collector

collector_id

get_source

Get source configuration

collector_id, source_id

create_http_source

Create an HTTP source (returns endpoint URL)

collector_id, name

Metrics (4 tools)

Tool

Description

Required Params

query_metrics

Execute a metrics query

query

list_metric_definitions

Discover available metric names

—

get_metric_metadata

Get dimensions for a metric

metric_name

list_metric_namespaces

List metric content types

—

Content Library (3 tools)

Tool

Description

Required Params

get_personal_folder

Get your personal content folder and children

—

get_folder

Get a folder and its child items

folder_id

get_content_by_path

Look up content by library path

path

Administration (8 tools)

Tool

Description

Required Params

list_users

List all users with emails, roles, status

—

list_roles

List roles with capabilities and filters (v2)

—

list_fields

List all fields (built-in + custom)

—

list_field_extraction_rules

List FERs with scopes and parse expressions

—

list_partitions

List partitions with routing and retention

—

list_lookup_tables

List lookup tables with schemas

—

get_lookup_table

Get a lookup table's config and fields

table_id

list_ingest_budgets

List ingest budgets with scopes and capacity

—

Utility (3 tools)

Tool

Description

Required Params

check_connection

Verify API connectivity and auth

—

get_account_usage

Get account status and ingestion info

—

validate_query

Check if a query is syntactically valid

query

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-mcp

Architecture

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 tools

Available Tools

48 tools
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

    A3.5/5.0

    Scored across 48 tools

    Disambiguation4/5

    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.

    Naming Consistency4/5

    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.

    Tool Count2/5

    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.

    Completeness3/5

    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

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • -
      license
      B
      quality
      Not graded
      maintenance
      MCP 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.
      1
      9 npm
      10
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP 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.
      3
      MIT
    • F
      license
      B
      quality
      B
      maintenance
      MCP server that integrates with Sumo Logic's API to perform log searches, data discovery, metrics queries, and monitoring.
      15
      22 npm
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables interaction with Sumo Logic's REST APIs through MCP, allowing log search, dashboard management, metrics querying, collector and monitor operations.
      5
      MIT