Skip to main content
Glama
rapid7-mcp

rapid7-mcp

by solomonneas

Rapid7 InsightIDR MCP Server

TypeScript 5.7 Node.js MCP SDK Rapid7 License: MIT

A Model Context Protocol (MCP) server that provides AI assistants with access to Rapid7 InsightIDR, a cloud-native SIEM for modern detection and response. Query investigations, search logs with LEQL, analyze alerts, track assets, monitor user behavior, and manage threat intelligence.

Features

Investigations

  • Search and filter investigations by status, priority, assignee, date range

  • Create, update, and manage investigation lifecycle

  • Add comments and retrieve associated alerts

  • Build investigation timelines

Log Search (LEQL)

  • Execute LEQL (Log Entry Query Language) queries across log sets

  • List available log sets (Firewall, DNS, DHCP, Endpoint, Cloud, Active Directory)

  • Retrieve individual log entries and aggregate statistics

  • LEQL syntax reference and examples

Alerts

  • List and filter alerts by severity, type, status, date

  • Get full alert details with evidence and indicators

  • Update alert status (open, investigating, closed)

  • Evidence extraction for investigation

Assets

  • Search endpoints by hostname, IP, OS, agent status

  • Full asset details: software inventory, vulnerabilities, agent info

  • Recent activity: logins, processes, network connections

User Behavior Analytics (UBA)

  • Search user accounts across the organization

  • Activity analysis: login patterns, locations, accessed assets

  • Risky user identification with behavior scoring

  • Anomaly detection and alert correlation

Threat Intelligence

  • IOC management: IPs, domains, file hashes

  • Add indicators to threat library

  • Search for threat indicator matches across logs

Saved Queries

  • List and manage saved LEQL queries

  • Create reusable queries with descriptions

  • LEQL syntax helper with examples

Related MCP server: rapid7-mcp-server

Architecture

┌────────────────────────────────────────┐
│           MCP Client (LLM)             │
└──────────────┬─────────────────────────┘
               │ MCP Protocol (stdio)
┌──────────────▼─────────────────────────┐
│         rapid7-mcp server              │
│                                        │
│  ┌──────────┐  ┌────────────────────┐  │
│  │ Prompts  │  │    Resources       │  │
│  │ 4 guides │  │ templates, LEQL,   │  │
│  │          │  │ detection rules    │  │
│  └──────────┘  └────────────────────┘  │
│                                        │
│  ┌──────────────────────────────────┐  │
│  │            Tools                  │  │
│  │  investigations │ logs │ alerts   │  │
│  │  assets │ users │ threats│queries │  │
│  └──────────────┬───────────────────┘  │
│                 │                       │
│  ┌──────────────▼───────────────────┐  │
│  │      InsightIDR REST Client      │  │
│  │      (client.ts + config.ts)     │  │
│  └──────────────┬───────────────────┘  │
└──────────────────┼─────────────────────┘
                   │ HTTPS
┌──────────────────▼─────────────────────┐
│      Rapid7 InsightIDR Platform API    │
│      https://<region>.api.insight.rapid7│
└────────────────────────────────────────┘

Installation

git clone https://github.com/solomonneas/rapid7-mcp.git
cd rapid7-mcp
npm install
npm run build

Configuration

Set environment variables:

export RAPID7_API_KEY="your-api-key"
export RAPID7_REGION="us"          # us, eu, ca, au, ap
export RAPID7_ORG_ID="your-org-id" # optional

Or use a .env file:

RAPID7_API_KEY=your-api-key
RAPID7_REGION=us
RAPID7_ORG_ID=your-org-id

MCP Client Configuration

Claude Desktop

{
  "mcpServers": {
    "rapid7": {
      "command": "node",
      "args": ["path/to/rapid7-mcp/dist/index.js"],
      "env": {
        "RAPID7_API_KEY": "your-api-key",
        "RAPID7_REGION": "us"
      }
    }
  }
}

OpenClaw

Add to your openclaw.json:

{
  "mcp": {
    "servers": {
      "rapid7": {
        "type": "stdio",
        "command": "node",
        "args": ["/path/to/rapid7-mcp/dist/index.js"],
        "env": {
          "RAPID7_API_KEY": "your-api-key",
          "RAPID7_REGION": "us"
        }
      }
    }
  }
}

Tool Reference

Tool

Description

search_investigations

List/filter investigations by status, priority, assignee

get_investigation

Get full investigation details with timeline

create_investigation

Create new investigation

update_investigation

Update status, assignee, disposition

add_investigation_comment

Add comment/note to investigation

get_investigation_alerts

Get alerts linked to an investigation

search_logs

Execute LEQL queries against log sets

list_log_sets

List available log sets

get_log_entry

Get specific log entry by ID

get_log_stats

Aggregate statistics for a time range

list_alerts

Get alerts with severity/type/status filters

get_alert

Full alert details with evidence

update_alert_status

Update alert status

get_alert_evidence

Get evidence/indicators from an alert

search_assets

Search endpoints by hostname, IP, OS

get_asset

Full asset details with software/vulns

get_asset_activity

Recent activity for an asset

search_users

Search user accounts

get_user_activity

User behavior analytics

get_risky_users

Users with abnormal behavior scores

list_threat_indicators

List IOCs in threat library

add_threat_indicator

Add new IOC

search_threat_activity

Search for IOC matches in logs

list_saved_queries

List saved LEQL queries

create_saved_query

Save a LEQL query for reuse

leql_help

LEQL syntax reference and examples

LEQL Query Examples

-- Find all blocked traffic from a source
where(source_address = 10.0.0.1 AND action = BLOCK)

-- Top talkers by connection count
groupby(source_address) calculate(count) sort(desc)

-- Failed logins for a specific user
where(user = "admin" AND result = FAILED_LOGIN)

-- HTTP errors by URL
where(status >= 400) groupby(url) calculate(count)

-- DNS queries to suspicious domains
where(query CONTAINS "malware") groupby(query) calculate(count)

-- Outbound connections on non-standard ports
where(destination_port != 80 AND destination_port != 443 AND direction = OUTBOUND)

Prompts

Prompt

Description

investigate-alert

Guided alert investigation workflow

hunt-ioc

Search for IOC across all log sources

user-behavior-review

Analyze user activity for anomalies

incident-timeline

Build chronological incident timeline

Resources

URI

Description

rapid7://investigation-templates

Common investigation templates

rapid7://leql-reference

LEQL syntax and examples

rapid7://detection-rules

Built-in detection rule catalog

Development

npm run build    # Compile TypeScript
npm run dev      # Watch mode
npm run test     # Run tests
npm run lint     # Lint check

License

MIT

Available Tools

26 tools
add_investigation_commentC

Add a comment or note to an InsightIDR investigation

Inputs: body (required), investigation_id (required), visibility.

add_threat_indicatorB

Add a new IOC (IP, domain, hash, etc.) to the InsightIDR custom threat library

Inputs: type (required), value (required), tags, severity, +3 more.

create_investigationA

Create a new InsightIDR investigation with a title, priority, and status

Inputs: title (required), status, priority, disposition, +1 more.

create_saved_queryB

Save a LEQL query for reuse in InsightIDR

Inputs: name (required), log_set_ids (required), leql_statement (required), description.

get_alertA

Get full details of a specific InsightIDR alert including its detection rule and metadata

Inputs: alert_id (required).

get_alert_evidenceC

Get evidence and indicators associated with an InsightIDR alert

Inputs: alert_id (required).

get_assetA

Get full details of an InsightIDR asset including installed software, vulnerabilities, and network interfaces

Inputs: asset_id (required).

get_asset_activityB

Get recent activity for an asset including logins, processes, and network connections

Inputs: asset_id (required), size, end_time, start_time, +1 more.

get_investigationA

Get full details of a specific InsightIDR investigation including its timeline

Inputs: investigation_id (required).

get_investigation_alertsB

Get all alerts associated with a specific investigation

Inputs: investigation_id (required), size, index.

get_log_entryC

Retrieve a specific log entry by its ID from a given log set

Inputs: log_id (required), log_set_id (required).

get_log_statsA

Get aggregate statistics for a log set over a time range using a LEQL query

Inputs: log_set_id (required), to, from, query, +1 more.

get_risky_usersA

Get users with abnormal behavior scores from InsightIDR's User Behavior Analytics (UBA)

Inputs: size, index, risk_level, min_risk_score.

get_user_activityC

Get user behavior analytics data: login times, locations, accessed assets, and anomalies

Inputs: user_id (required), size, end_time, start_time, +1 more.

leql_helpA

Get LEQL (Log Entry Query Language) syntax reference, examples, and common patterns for InsightIDR log searches

Inputs: topic.

list_alertsC

List InsightIDR alerts with optional filters for severity, type, status, and date range

Inputs: size, sort, type, index, +5 more.

list_log_setsA

List all available log sets in InsightIDR (Firewall, DNS, DHCP, Endpoint, Cloud, etc.)

Inputs: no named parameters.

list_saved_queriesB

List saved LEQL queries available in InsightIDR

Inputs: size, index, search.

list_threat_indicatorsC

List IOCs (IPs, domains, hashes) in the InsightIDR threat library

Inputs: size, type, index, search, +2 more.

search_assetsB

Search InsightIDR assets (endpoints) by hostname, IP address, OS, or agent status

Inputs: size, index, domain, search, +4 more.

search_investigationsA

List and filter InsightIDR investigations by status, priority, assignee, or date range

Inputs: size, sort, index, status, +4 more.

search_logsB

Execute a LEQL (Log Entry Query Language) query against a specific log set in InsightIDR

Inputs: query (required), log_set_id (required), to, from, +2 more.

search_threat_activityB

Search for threat indicator matches in InsightIDR logs — find where known IOCs have been seen

Inputs: size, index, end_time, start_time, +2 more.

search_usersB

Search user accounts monitored by InsightIDR by name, email, domain, or department

Inputs: name, size, email, index, +4 more.

update_alert_statusA

Update the status of an InsightIDR alert (open, investigating, or closed)

Inputs: status (required), alert_id (required), assignee_email.

update_investigationB

Update an existing investigation's status, priority, assignee, or disposition

Inputs: investigation_id (required), title, status, priority, +2 more.

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 26 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action, such as creating vs listing investigations or getting alert details vs listing alerts. The descriptions clearly differentiate between similar-sounding tools, ensuring no ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with underscores (e.g., create_investigation, list_alerts, get_asset). The verbs are appropriately chosen for the operation, and the naming is uniform throughout.

    Tool Count4/5

    With 26 tools, the count is slightly above the recommended range for a well-scoped server, but each tool serves a distinct purpose in the InsightIDR domain, covering investigations, alerts, assets, logs, and threat intelligence. No tools seem redundant.

    Completeness4/5

    The tool set covers CRUD-like operations for key entities (investigations, alerts, threats) and includes search and query capabilities. Minor gaps exist, such as the absence of delete tools for investigations or threat indicators, but core workflows are well-supported.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      C
      maintenance
      Connects AI assistants to the Vectra AI security platform to enable intelligent analysis of threat detection data and automated incident response workflows. It allows users to investigate threats, take response actions, and generate security reports using natural language.
      23
      6
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables querying Rapid7 InsightIDR logs using natural language through AI assistants, with support for time filtering, logset selection, and LEQL queries.
      6
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Brings the full AlertLogic MDR platform into AI assistants, exposing 473+ tools for incident response, log search, SOAR automation, and multi-account security operations at MSSP scale.
      MIT
    • A
      license
      B
      quality
      C
      maintenance
      Enables AI assistants to drive the UTMStack SIEM/XDR platform for triaging alerts, searching logs, running SQL, managing incidents, inspecting agents, creating/deleting correlation rules, managing data filters, and running commands on endpoints.
      44
      MIT