// SCAN REPORT

Rapid7

26 tools. 7 can modify or destroy data without limits.

7 write tools that can modify data. Rate limits recommended.

Last updated: 29 Jun 2026

7 can modify or destroy data

19 read-only

26 tools total

Community server · catalogue entry verified 29/06/2026

How to control Rapid7 ↓

TOOL MAP

What Rapid7 exposes to your agents

Read (19) Write / Execute (7) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Rapid7 tools

Execute · High search_logs The tool executes arbitrary queries against a SIEM log system. Write · Medium add_investigation_comment This tool creates new data (comments/notes) and modifies the investigation record by appending information. Write · High add_threat_indicator This tool creates or adds data (threat indicators) to a security system's threat library. Write · Medium create_investigation This tool creates new data (investigation records) in the SIEM platform, making it a Write operation.

7 of Rapid7's 26 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Rapid7

PolicyLayer is an MCP gateway — it sits between your AI agents and Rapid7, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "add_investigation_comment": {
    "limits": [
      {
        "counter": "add_investigation_comment_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_alert": {
    "limits": [
      {
        "counter": "get_alert_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Rapid7 — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON RAPID7 →

Instant setup, no code required.

FULL CATALOGUE

All 26 Rapid7 tools

EXECUTE 1 tools

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

WRITE 6 tools

Write add_investigation_comment Add a comment or note to an InsightIDR investigation Write add_threat_indicator Add a new IOC (IP, domain, hash, etc.) to the InsightIDR custom threat library Write create_investigation Create a new InsightIDR investigation with a title, priority, and status Write create_saved_query Save a LEQL query for reuse in InsightIDR Write update_alert_status Update the status of an InsightIDR alert (open, investigating, or closed) Write update_investigation Update an existing investigation

READ 19 tools

Read get_alert Get full details of a specific InsightIDR alert including its detection rule and metadata Read get_alert_evidence Get evidence and indicators associated with an InsightIDR alert Read get_asset Get full details of an InsightIDR asset including installed software, vulnerabilities, and network interfaces Read get_asset_activity Get recent activity for an asset including logins, processes, and network connections Read get_investigation Get full details of a specific InsightIDR investigation including its timeline Read get_investigation_alerts Get all alerts associated with a specific investigation Read get_log_entry Retrieve a specific log entry by its ID from a given log set Read get_log_stats Get aggregate statistics for a log set over a time range using a LEQL query Read get_risky_users Get users with abnormal behavior scores from InsightIDR Read get_user_activity Get user behavior analytics data: login times, locations, accessed assets, and anomalies Read leql_help Get LEQL (Log Entry Query Language) syntax reference, examples, and common patterns for InsightIDR log searche Read list_alerts List InsightIDR alerts with optional filters for severity, type, status, and date range Read list_log_sets List all available log sets in InsightIDR (Firewall, DNS, DHCP, Endpoint, Cloud, etc.) Read list_saved_queries List saved LEQL queries available in InsightIDR Read list_threat_indicators List IOCs (IPs, domains, hashes) in the InsightIDR threat library Read search_assets Search InsightIDR assets (endpoints) by hostname, IP address, OS, or agent status Read search_investigations List and filter InsightIDR investigations by status, priority, assignee, or date range Read search_threat_activity Search for threat indicator matches in InsightIDR logs — find where known IOCs have been seen Read search_users Search user accounts monitored by InsightIDR by name, email, domain, or department

FAQ

Questions about Rapid7

How do I prevent bulk modifications through Rapid7? +

The Rapid7 server has 6 write tools including add_investigation_comment, add_threat_indicator, create_investigation. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Rapid7.

How many tools does the Rapid7 MCP server expose? +

26 tools across 2 categories: Read, Write. 19 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Rapid7? +

Register the Rapid7 MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Rapid7 tool call.

Deterministic rules across all 26 Rapid7 tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON RAPID7 →

Instant setup, no code required.

26 Rapid7 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.