LogicMonitor MCP Server

Model Context Protocol (MCP) server for LogicMonitor REST API v3 integration. Enables AI assistants to interact with LogicMonitor monitoring data through 306 structured tools, 15 workflow prompts, and 26 resources. Optional integrations: IBM watsonx.ai for Granite TTM forecasting and NL summaries, Terraform IaC for any provider, and HuggingFace local Granite model fallback.

Works with any MCP-compatible client: Claude Desktop, Claude Code, Cursor, Continue, Cline, and more.

Quick Start

1. Get your LogicMonitor Bearer Token:

• Log into your LogicMonitor portal
• Go to Settings → Users and Roles → API Tokens
• Create a new API-only user or add a token to an existing user
• Copy the Bearer token

2. Configure your MCP client:

For Claude Code (CLI):

claude mcp add logicmonitor \
  -e LM_PORTAL=yourcompany.logicmonitor.com \
  -e LM_BEARER_TOKEN=your-bearer-token \
  -- uvx --from lm-mcp lm-mcp-server

With IBM watsonx.ai integration (optional -- adds Granite TTM forecasting and NL summaries):

claude mcp add logicmonitor \
  -e LM_PORTAL=yourcompany.logicmonitor.com \
  -e LM_BEARER_TOKEN=your-bearer-token \
  -e WATSONX_API_KEY=your-ibm-cloud-api-key \
  -e WATSONX_URL=https://us-south.ml.cloud.ibm.com \
  -e WATSONX_PROJECT_ID=your-watsonx-project-id \
  -- uvx --from "lm-mcp[ibm]" lm-mcp-server

With Terraform IaC (optional -- adds terraform plan/apply/generate tools):

claude mcp add logicmonitor \
  -e LM_PORTAL=yourcompany.logicmonitor.com \
  -e LM_BEARER_TOKEN=your-bearer-token \
  -e TF_WORKSPACE_DIR=/path/to/terraform/workspaces \
  -- uvx --from lm-mcp lm-mcp-server

With HuggingFace local models (optional -- local Granite TTM + NL summaries, no cloud API needed):

claude mcp add logicmonitor \
  -e LM_PORTAL=yourcompany.logicmonitor.com \
  -e LM_BEARER_TOKEN=your-bearer-token \
  -- uvx --from "lm-mcp[huggingface]" lm-mcp-server

For Claude Desktop, add to your config file (see MCP Client Configuration below).

3. Verify it's working:

claude mcp list

You should see: logicmonitor: uvx --from lm-mcp lm-mcp-server - ✓ Connected

4. Test with a prompt:

"Show me all critical alerts in LogicMonitor"

What's New in v4.2.0

Multi-portal mode arrives, hardened. A single server can now serve many customer portals, selecting the active one at runtime with list_portals, use_portal, current_portal, and reload_portals — one entry in your MCP client instead of one server (and one pasted token) per portal. Credentials live in an age-encrypted vault, every portal is read-only unless its vault record says otherwise, and the mode is deliberately stdio-only: the server refuses to start it on the shared HTTP transport. The release also carries a full dependency refresh clearing 53 dependabot alerts across the lockfile.

What's New in v4.0.0

Major. Every tool now wraps an endpoint proven to exist, validated against a live portal. Six tools that called nonexistent API paths since introduction are removed (get_cloud_cost_accounts, get_cost_summary, get_resource_cost, get_remediation_status, get_remediation_history, get_batchjob_history); the cost recommendation tools move onto the working /cost-optimization API; the Service Insight tools query real Service Insight objects (deviceType 6 devices and BizService groups) instead of the legacy v1 websites API. The Automated Diagnostics & Remediation surface arrives in full: get_diagnostic_remediation_assignments and get_diagnostic_remediation_results (structured execution records with script output, replacing audit-log scraping), execute_diagnostic, full CRUD plus import/export for diagnostic and remediation sources, and the new action chain / action rule namespace (11 tools including the set_action_rule_status toggle). update_logicmodule gains the two new source types and its apply mode actually applies now (it previously tripped its own sub-tools' confirm guards). run_report executions are pollable via get_report_execution, get_alert_details can fetch the full message body, and NextGen reports are visible to the report list tools.

Full release history, including v3.9.x and earlier, is in CHANGELOG.md. The v3.8.0 networking intelligence tools have a dedicated reference: documentation/networking-intelligence.md.

Features

306 Tools across comprehensive LogicMonitor API coverage (277 LM + 18 AAP + 10 Terraform + 1 watsonx):

Core Monitoring

• Alert Management: Query, acknowledge, bulk acknowledge, add notes, view rules
• Device Management: Full CRUD - list, create, update, delete devices and groups
• Metrics & Data: Query datasources, instances, metric data, and graphs. Instance CRUD for manual datasource instances.
• Dashboard Management: Full CRUD for dashboards, widgets, and groups
• SDT Management: Create, list, bulk create/delete Scheduled Downtime
• Collector Management: List collectors and collector groups

Extended Features

• Website Monitoring: Full CRUD for synthetic checks and website groups
• Report Management: List, view, run reports, manage schedules
• Escalation Management: Full CRUD for escalation chains and recipient groups
• Alert Rules: Full CRUD for alert routing rules
• User & Role Management: View users, roles, access groups, API tokens
• Ops Management: Audit logs, ops notes, login/change audits
• Automated Diagnostics & Remediation: Assigned-source resolution, structured execution results with script output, diagnostic/remediation source CRUD, manual execution, action chains and rules
• Native OTLP Metrics (preview): Metric and label discovery plus PromQL range queries against the feature-flag-gated OTLP metrics store

AI Analysis Tools

Server-side intelligence that transforms raw monitoring data into actionable insights:

• Alert Correlation: Automatically clusters related alerts by device, datasource, and temporal proximity — replaces dozens of manual API calls with a single aggregated view
• Alert Statistics: Aggregated alert counts by severity, top-10 devices and datasources, time-bucketed distributions for trend analysis
• Metric Anomaly Detection: Multi-method anomaly detection (z-score, IQR, MAD) with auto-selection based on data distribution
• Metric Baselines: Save baseline snapshots of metric behavior, then compare current performance against the baseline to detect drift
• Scheduled Analysis: HTTP API endpoints for triggering analysis workflows (alert correlation, RCA, top talkers, health checks) from external schedulers and webhooks

ML/Statistical Analysis Tools

Pure-Python statistical methods for capacity planning, trend analysis, and operational scoring:

• Metric Forecasting: Linear regression, Holt-Winters triple exponential smoothing, and IBM Granite TTM (via watsonx.ai, optional) with auto-selection, confidence intervals, and threshold breach prediction
• Metric Correlation: Pearson correlation matrix across multiple metric series with strong-correlation highlighting
• Error Budget Tracking: SLO-based error budget calculation with burn rate, projected exhaustion, and status classification
• Change Point Detection: CUSUM algorithm for identifying regime shifts and mean-level changes
• Alert Noise Scoring: Shannon entropy and flap detection to quantify alert noise (0-100) with tuning recommendations
• Seasonality Detection: Autocorrelation-based periodicity detection at standard intervals with peak-hour identification
• Availability Calculation: SLA-style uptime percentage from alert history with MTTR, incident counts, and per-device breakdown
• Blast Radius Analysis: Topology-based downstream impact scoring for device failure scenarios
• Change Correlation: Cross-references alert spikes with audit/change logs to identify change-induced incidents
• Trend Classification: Categorizes metrics as stable, increasing, decreasing, cyclic, or volatile
• Device Health Scoring: Multi-metric composite health score (0-100) using z-score analysis with configurable weights

Composite Workflow Tools

Multi-step analysis tools that combine several sub-tools into a single call. Each supports detail_level ("summary" or "full"), optional summarize=true for plain-English NL summaries via IBM Granite (requires watsonx.ai), and handles sub-tool failures gracefully with partial results.

• Triage: Correlates active alerts, scores noise, analyzes blast radius, and cross-references recent changes
• Health Check: Device health score, monitoring coverage, anomaly detection, active alerts, and 30-day availability
• Capacity Plan: Per-datasource forecasting, trend classification, seasonality detection, and change point analysis
• Portal Overview: Alert statistics, collector health, active SDTs, alert clusters, noise assessment, and down devices
• Diagnose: Alert details, device context, correlation, blast radius, health scoring, and root cause analysis
• Update LogicModule (Safe Partial Updates): update_logicmodule(type, id, changes, mode) exports the current full definition, deep-merges your changes, validates required fields, and returns a dry-run diff (default) or applies the merge. Prevents the full-replace blanking that wiped production Groovy scripts in two prior incidents. Supports configsource, datasource, eventsource, logsource, propertysource, topologysource.
• Search Tools: Keyword search across all tools by name and description with category filtering

APM Trace Tools

Service discovery and RED metrics for LogicMonitor APM (Application Performance Monitoring):

• Service Discovery: List all traced services, inspect individual service details and properties
• Operation Listing: Discover endpoints/routes monitored within each service
• RED Metrics: Duration, error count, and operation count at both service and per-operation level
• Alert Integration: View active alerts for any traced service
• Property Inspection: OTel attributes, namespace info, and auto-discovered metadata

Ansible Automation Platform Integration

18 tools for observability-driven remediation via Ansible Automation Platform (AAP). Connects LogicMonitor alerts to automated remediation playbooks.

• Job Templates: List, inspect, and launch job templates with extra variables and host limits
• Job Execution: Launch jobs, check status, view output, cancel or relaunch runs
• Workflows: Launch workflow templates, monitor multi-step automation sequences
• Inventories & Hosts: List inventories, inspect hosts for targeted remediation
• Projects & Credentials: Browse available projects and credentials (secrets never exposed)
• Write Protection: launch_job, launch_workflow, cancel_job, relaunch_job require LM_ENABLE_WRITE_OPERATIONS=true
• Jinja2 Safety: All extra_vars inputs are validated to prevent template injection

AAP tools are optional — they only appear when AWX_URL and AWX_TOKEN are configured. See Example Playbooks for remediation templates.

IBM watsonx.ai Integration

Optional AI-powered enhancements using IBM Granite foundation models via watsonx.ai. Requires an IBM Cloud account with a watsonx.ai project (Lite/free tier supported).

• Granite TTM Forecasting: ML-powered time series forecasting using IBM Granite Tiny Time Mixer (TTM). Use method="ttm" on forecast_metric for 96-step predictions that detect seasonality and non-linear patterns. Requires 512+ data points. Gracefully falls back to statistical methods when data is insufficient.
• Granite NL Summaries: Plain-English shift-handoff summaries on composite workflow tools (triage, diagnose, health_check, capacity_plan, portal_overview). Pass summarize=true to append an IBM Granite-generated analysis summary to the structured output.
• watsonx_summarize: Standalone tool that takes any JSON data and generates a concise NL summary via Granite 4.0. Useful for summarizing output from any MCP tool.

watsonx tools are optional — they only appear when WATSONX_API_KEY and WATSONX_PROJECT_ID are configured. Install with lm-mcp[ibm] to include the IBM SDK dependencies.

Setup:

1. Create a free IBM Cloud account at cloud.ibm.com
2. Provision watsonx.ai Runtime (Lite plan, free) from the IBM Cloud catalog
3. Create a watsonx.ai project and associate the Runtime instance
4. Generate an IBM Cloud API key at cloud.ibm.com/iam/apikeys
5. Configure the MCP server with WATSONX_API_KEY, WATSONX_URL, and WATSONX_PROJECT_ID

Terraform Integration

11 tools for Infrastructure as Code workflows with any Terraform provider. AI agents can author HCL, use pre-made scripts, or reverse-engineer existing LM resources.

• terraform_init: Initialize workspace and download providers
• terraform_validate: Syntax-check HCL configuration
• terraform_plan: Preview changes with structured JSON output
• terraform_apply: Apply changes (triple-gated: write perms + config flag + confirm param)
• terraform_destroy: Destroy infrastructure (same triple gate)
• terraform_import: Import existing resources into Terraform state
• terraform_state_list / terraform_state_show: Inspect current state
• terraform_output: View Terraform outputs
• terraform_write_config: Write HCL files to workspace directories
• terraform_generate: Export existing LM portal resources as HCL using the logicmonitor/logicmonitor provider

Terraform tools are optional -- they only appear when TF_WORKSPACE_DIR is configured. Requires the terraform CLI installed separately.

Three entry points:

1. Agent-authored: AI generates HCL from natural language, writes to workspace, plans, applies
2. Pre-made scripts: Point TF_WORKSPACE_DIR at existing .tf files, agent operates on them
3. Reverse-engineer: terraform_generate exports LM resources as HCL, then import into state

HuggingFace Local Fallback

When watsonx.ai API credentials are not configured, TTM forecasting and NL summaries automatically fall back to local Granite models via HuggingFace transformers. Install with lm-mcp[huggingface].

Priority chain: watsonx.ai API (remote) > HuggingFace local > statistical/linear

• TTM Model: ibm-granite/granite-timeseries-ttm-r2 (512 context, 96 forecast)
• LLM Model: ibm-granite/granite-3.3-2b-instruct (2B params, runs on CPU)
• Models lazy-load on first inference call (initial download: ~500MB TTM, ~4GB LLM)
• Same interface as WatsonxClient -- all existing watsonx tools work with either backend

LogicModules

• DataSources: Query and export datasource definitions
• ConfigSources: Query definitions, retrieve device config data from the Config Archive, view diffs, trigger on-demand collection, and audit change history
• EventSources: Query and export event detection modules
• PropertySources: Query, create, and export property collection modules
• TopologySources: Query and export topology mapping modules
• LogSources: Query and export log collection modules
• Import Support: Import LogicModules from JSON definitions

Advanced Capabilities

• Cost Optimization: Cost recommendations, recommendation categories, idle resources (LM Envision)
• Network Topology: Device neighbors, interfaces, flows, connections
• Batch Jobs: View and manage batch job execution history
• Log/Metric Ingestion: Push logs and metrics via LMv1 authentication

MCP Protocol Features

• Resources: 26 schema/enum/filter/guide resources for API reference
• Prompts: 15 workflow templates (incident triage, RCA, capacity forecasting, remediation execution, etc.)
• Completions: Auto-complete for tool arguments

Claude Code Skills

Pre-built slash-command workflows for Claude Code that orchestrate multiple tools into guided operational runbooks:

Skills ship with the repo — clone it and invoke /lm-triage in Claude Code to get started.

Operational Features

• Security-First: Read-only by default, write operations require explicit opt-in
• Rate Limit Handling: Automatic retry with exponential backoff and jitter
• Server Error Recovery: Automatic retry on 5xx server errors
• Pagination Support: Handle large result sets with offset-based pagination
• Session Persistence: Optional file-backed session variables that survive restarts

Multi-Portal Mode (optional)

Work across many customer portals from a single server entry instead of one server (and one token) per portal. Set LM_MULTI_PORTAL=true and point the server at a credential vault; the full tool set loads once, and you switch the active portal at runtime. Four tools manage it: list_portals, use_portal, current_portal, and reload_portals. Credentials come from an age-encrypted vault (or a plaintext JSON file for testing) rather than the environment, and each portal is read-only unless explicitly marked writable — so an assistant can browse any portal but cannot change one by accident. Multi-portal mode is stdio-only (the server refuses to start it on the HTTP transport) and Terraform tools are unavailable in it. Unmodified single-portal behavior is unchanged (no LM_MULTI_PORTAL, fixed LM_PORTAL + token). See MULTIPORTAL.md.

Installation

Via PyPI (Recommended)

# Using uvx (no install needed)
uvx --from lm-mcp lm-mcp-server

# Using pip
pip install lm-mcp

From Source

git clone https://github.com/ryanmat/mcp-server-logicmonitor.git
cd mcp-server-logicmonitor
uv sync

Docker Deployment

For remote/shared deployments using HTTP transport:

cd deploy
cp .env.example .env
# Edit .env with your credentials

# Run with docker-compose
docker compose up -d

# With TLS via Caddy
docker compose --profile tls up -d

The server exposes health endpoints for container orchestration:

• GET /health - Detailed health check with all component statuses
• GET /healthz - Liveness probe (200 OK or 503)
• GET /readyz - Readiness probe (includes connectivity check if enabled)

Kubernetes

deploy/k8s/deployment.yaml is a vendor-neutral Deployment and Service running the published ghcr.io image. It works on AKS, EKS, GKE, OpenShift, or vanilla Kubernetes, reads credentials from a Kubernetes secret you create, and wires the liveness and readiness probes to the endpoints above. Apply it with kubectl apply -f deploy/k8s/deployment.yaml after creating the secret documented at the top of the file.

Configuration

Environment Variables

*Either LM_BEARER_TOKEN or both LM_ACCESS_ID and LM_ACCESS_KEY are required.

Authentication Methods

Bearer Token (Recommended):

• Simpler setup, works for most operations
• Set LM_BEARER_TOKEN

LMv1 HMAC (Required for Ingestion):

• Required for ingest_logs and push_metrics tools
• Set both LM_ACCESS_ID and LM_ACCESS_KEY
• Can be used alongside Bearer token

Getting API Credentials

Bearer Token:

1. Log into your LogicMonitor portal
2. Go to Settings → Users and Roles → API Tokens
3. Create a new API-only user or add a token to an existing user
4. Copy the Bearer token

LMv1 Credentials:

1. Go to Settings → Users and Roles → Users
2. Select a user → API Tokens tab
3. Create or view the Access ID and Access Key

MCP Client Configuration

The Quick Start covers Claude Code. Every JSON-based client (Cursor, Claude Desktop, Cline, GitHub Copilot, Gemini CLI, OpenAI Codex) runs the same server with the same block:

{
  "mcpServers": {
    "logicmonitor": {
      "command": "uvx",
      "args": ["--from", "lm-mcp", "lm-mcp-server"],
      "env": {
        "LM_PORTAL": "yourcompany.logicmonitor.com",
        "LM_BEARER_TOKEN": "your-bearer-token"
      }
    }
  }
}

Add LM_ENABLE_WRITE_OPERATIONS, LM_ACCESS_ID/LM_ACCESS_KEY (ingestion), or the watsonx/Terraform variables to env as needed. Per-client config file locations and exact steps (Claude Code, Cursor, Claude Desktop, OpenAI Codex, Cline, GitHub Copilot, Gemini CLI) are in documentation/client-setup.md.

Cursor's 40-tool cap

Cursor only loads the first 40 MCP tools, so the remaining ~240 are invisible to the agent. Use LM_MCP_CATEGORIES to fit a curated subset under the cap. The workflow category alone (triage, diagnose, health_check, portal_overview, capacity_plan, plus the scoring/correlation tools and update_logicmodule) is roughly 23 tools and covers the 80% case:

"env": {
  "LM_PORTAL": "yourcompany.logicmonitor.com",
  "LM_BEARER_TOKEN": "your-bearer-token",
  "LM_MCP_CATEGORIES": "workflow"
}

LM_MCP_CATEGORIES composes with LM_ENABLED_TOOLS by intersection (it only narrows, never expands); unset, the server returns all 306 tools. In multi-portal mode the four portal tools are exempt from category filtering (they are the mode's control plane) and do not count toward your curated set. See documentation/client-setup.md for a surgical LM_ENABLED_TOOLS example.

Available Tools

306 tools cover the full LogicMonitor surface plus the optional Ansible Automation Platform, Terraform, and IBM watsonx.ai integrations. The complete per-tool reference (every tool, its parameters, and its read/write classification) is in documentation/tools.md, generated from the tool registry so it never drifts.

Discover tools at runtime without leaving your client:

• search_tools: keyword search across every tool by name and description
• the lm://guide/tool-categories resource: all 306 tools grouped by domain

Tools are organized into these categories: Alerts, Alert Rules, Devices, Metrics, APM Traces, Dashboards, SDT, Collectors, Websites, Escalations, Device Properties, Reports, DataSources, LogicModules (Config/Event/Property/Topology/Log), Cost Optimization, Actions (Chains & Rules), Ingestion, Network & Topology, Batch Jobs, Ops & Audit, Users & Access, Services, Netscans, OIDs, Session, Correlation & Analysis, Baselines, ML/Statistical Analysis, Ansible Automation Platform, Remediation, Composite Workflows, and Error Budget.

MCP Resources

The server exposes 26 resources for API reference:

Schema Resources

Enum Resources

Filter Resources

Guide Resources

MCP Prompts

Pre-built workflow templates for common tasks:

Example Usage

Once configured, ask your assistant in natural language. A representative sample (the server understands far more across all 306 tools):

• "List the first 5 devices in LogicMonitor" (quick connectivity check)
• "Show me all critical alerts from the last hour"
• "Acknowledge alert LMA12345 with note 'Investigating disk issue'"
• "What datasources are applied to device 123, and get CPU metrics for the last hour"
• "Create a dashboard called 'API Health' and add a graph widget"
• "Create a 2-hour maintenance window (SDT) for device 123"
• "Triage all critical alerts from the last 4 hours"
• "Run a health check on device 123, then give me a portal overview for shift handoff"
• "Forecast when memory on device 123 will hit 90%"
• "What's the blast radius if device 789 goes down?"
• "What diagnostics ran on device 123 today, and what did the scripts output?"

For power users, the server accepts LogicMonitor filter syntax directly, for example "Get devices where filter is 'displayName~prod,hostStatus:alive'".

Development

Running Tests

uv run pytest -v

Linting

uv run ruff check src tests
uv run ruff format src tests

Project Structure

src/lm_mcp/
├── __init__.py           # Package exports
├── analysis.py           # Scheduled analysis workflows and store
├── awx_config.py         # AAP connection configuration
├── config.py             # Environment-based configuration
├── exceptions.py         # Exception hierarchy
├── health.py             # Health check endpoints
├── logging.py            # Structured logging
├── server.py             # MCP server entry point
├── session.py            # Session context with optional persistence
├── registry.py           # Tool definitions and handlers (TOOLS + AWX_TOOLS)
├── validation.py         # Field validation with suggestions
├── auth/
│   ├── __init__.py       # Auth provider factory
│   ├── bearer.py         # Bearer token auth
│   └── lmv1.py           # LMv1 HMAC auth
├── client/
│   ├── __init__.py       # Client exports
│   ├── api.py            # Async HTTP client for LogicMonitor API
│   └── awx.py            # Async HTTP client for AAP controller API
├── completions/
│   └── registry.py       # Auto-complete definitions
├── prompts/
│   ├── registry.py       # Prompt definitions
│   └── templates.py      # Workflow template content
├── resources/
│   ├── registry.py       # Resource definitions
│   ├── schemas.py        # Schema content
│   ├── enums.py          # Enum content
│   ├── filters.py        # Filter content
│   ├── guides.py         # Tool categories, query examples, orchestration guide
│   ├── best_practices.py # Scenario-based best practices and anti-patterns
│   └── examples.py       # Example responses for key tools
├── transport/
│   ├── __init__.py       # Transport abstraction
│   └── http.py           # HTTP/SSE transport with analysis endpoints
└── tools/
    ├── __init__.py       # Tool utilities
    ├── alerts.py         # Alert management
    ├── alert_rules.py    # Alert rule CRUD
    ├── ansible.py        # Ansible Automation Platform tool handlers
    ├── baselines.py      # Metric baseline save/compare
    ├── collectors.py     # Collector tools
    ├── correlation.py    # Alert correlation, anomaly detection, metric correlation
    ├── cost.py           # Cost optimization
    ├── dashboards.py     # Dashboard CRUD
    ├── devices.py        # Device CRUD
    ├── escalations.py    # Escalation/recipient CRUD
    ├── event_correlation.py  # Change-alert correlation
    ├── forecasting.py    # Forecast, trend, seasonality, change points
    ├── imports.py        # LogicModule import
    ├── ingestion.py      # Log/metric ingestion
    ├── metrics.py        # Metrics and data
    ├── scoring.py        # Alert noise, availability, device health
    ├── sdts.py           # SDT management
    ├── session.py        # Session management tools
    ├── stats_helpers.py  # Shared statistical math utilities (incl. Holt-Winters, IQR, MAD)
    ├── topology_analysis.py  # Blast radius analysis
    ├── websites.py       # Website CRUD
    ├── workflows.py      # Composite workflow tools (triage, health_check, etc.)
    ├── metric_presets.py # Metric-type presets for auto-configuration
    └── ...               # Additional tool modules

examples/playbooks/
├── lm-remediate-disk-cleanup.yml
├── lm-remediate-service-restart.yml
├── lm-remediate-log-rotate.yml
└── lm-remediate-memory-cache-clear.yml

deploy/
├── Dockerfile            # Production Docker image
├── docker-compose.yml    # Full stack deployment
├── Caddyfile             # TLS proxy configuration
└── .env.example          # Environment template

Troubleshooting

"Failed to connect" in Claude Code

If claude mcp list shows ✗ Failed to connect, the server is missing environment variables. The -e flags must be included when adding the server:

# Remove the broken config
claude mcp remove logicmonitor

# Re-add with environment variables
claude mcp add logicmonitor \
  -e LM_PORTAL=yourcompany.logicmonitor.com \
  -e LM_BEARER_TOKEN=your-bearer-token \
  -- uvx --from lm-mcp lm-mcp-server

Note: Setting environment variables in your shell or .env file won't work—Claude Code spawns the MCP server as a subprocess with its own environment.

"Write operations are disabled"

Write operations (acknowledge, create SDT, etc.) are disabled by default. Set LM_ENABLE_WRITE_OPERATIONS=true in your environment.

"spawn uvx ENOENT" in Claude Desktop

Claude Desktop can't find uvx. Use the full path:

{
  "command": "/Users/yourname/.local/bin/uvx",
  "args": ["--from", "lm-mcp", "lm-mcp-server"]
}

Find your uvx path with: which uvx

Ingestion API Errors

The ingest_logs and push_metrics tools require LMv1 authentication. Bearer tokens don't work with ingestion APIs. Add LM_ACCESS_ID and LM_ACCESS_KEY to your configuration.

Rate Limit Errors

The server automatically retries rate-limited requests with exponential backoff. If you're consistently hitting limits, reduce request frequency or contact LogicMonitor support.

Authentication Errors

Verify your bearer token is correct and has appropriate permissions. API tokens can be managed in LogicMonitor under Settings → Users and Roles → API Tokens.

License

MIT License - see LICENSE file.