rapid7-insightconnect-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| R7_REGION | No | Rapid7 region. Required with R7_API_KEY when environment configuration is selected. | |
| R7_API_KEY | No | Rapid7 API key. Required with R7_REGION when environment configuration is selected. | |
| R7_ALLOW_WRITES | No | Must be exactly 'true' or 'false' when set; defaults to 'false' for a complete env configuration. | false |
| XDG_CONFIG_HOME | No | Overrides the credential configuration directory when set to an absolute path. | |
| R7_SETUP_TIMEOUT | No | Setup-page window in seconds. Default 300. | 300 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| setupA | Configure Rapid7 credentials via a secure local page. Never ask for the key in chat. |
| list_workflowsA | Discover workflows, one bounded page at a time; filter by state or name. |
| get_workflowA | Read workflow definition and trigger details before execution. |
| execute_workflowC | Execute an active API-triggered workflow without input; may change external systems. |
| list_jobsA | Read jobs newest first; optionally filter by workflow or documented terminal status. |
| get_jobA | Read a job's status and available execution details. |
| cancel_jobA | Request job cancellation. Does not undo actions already performed. |
| list_global_artifactsB | Discover global artifacts, optionally filtered by name, sorted by name. |
| get_global_artifactB | Read global artifact metadata. |
| list_artifact_entriesB | Read artifact entities; upstream spec does not document pagination parameters. |
| export_snippetA | Export a known snippet definition; published version by default. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| config_resource | Non-secret local configuration and safety policy. |
TDQS
Scored across 11 tools
Each tool targets a distinct resource/action combination: workflows (list/get/execute), jobs (list/get/cancel), artifacts (list/get/list entries), and snippets (export). No two tools have overlapping purposes, and the descriptions clearly delineate their roles.
All tools follow a consistent verb_noun snake_case pattern (e.g., list_workflows, get_job, execute_workflow, export_snippet). The single exception, setup, is still a verb and fits the pattern. No mixed conventions or irregular naming.
With 11 tools, the set is well-scoped for the Rapid7 InsightConnect domain. It covers the essential resources (workflows, jobs, artifacts, snippets) without excess, and each tool has a clear purpose. This is within the ideal range for a domain-specific MCP server.
The surface covers core read and execution workflows for the domain. Minor gaps exist, such as no way to list snippets (only export a known one) and lack of create/update/delete operations for workflows/artifacts, but these may be intentional given the server's focus on discovery and execution. The noted lack of pagination parameters for list_artifact_entries is a small limitation.