henry-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| henry_inspect_fileA | Inspect a single file statically and return a structured report. Use this first to understand a file's type, format, and key properties before comparing it with another file. Supported formats:
Args: path: Absolute or relative path to the file to inspect. limit: Maximum number of findings to return (default 1000). offset: Number of findings to skip (default 0). |
| henry_analyze_pairA | Compare an application file with a module file for static compatibility. Supported pairs:
The result is an evidence-backed inference, not a runtime guarantee. No files are loaded or executed. Args: app_path: Path to the application file (EXE or APK). module_path: Path to the module file (DLL or Kotlin source). limit: Maximum number of findings to return (default 1000). offset: Number of findings to skip (default 0). |
| henry_predict_failure_scenariosB | Predict likely failure scenarios for an app + module pair. Each scenario includes title, condition, symptom, cause, evidence, severity, confidence, and validation_needed. Only scenarios supported by static findings are produced. Args: app_path: Path to the application file. module_path: Path to the module file. limit: Maximum number of scenarios to return (default 1000). offset: Number of scenarios to skip (default 0). |
| henry_explain_findingA | Explain a previously produced finding by its ID. Use after henry_inspect_file, henry_analyze_pair, or henry_predict_failure_scenarios to understand why a particular observation or inference was reported. Args: finding_id: The ID of the finding to explain. |
| henry_resetA | Clear all stored analysis findings and reports. Use this to reset the analyzer's in-memory state between unrelated analysis sessions. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
The tools have largely distinct roles: inspect single files, compare a pair, predict pair failures, explain a finding, and reset state. The main possible confusion is between analyze_pair and predict_failure_scenarios, since both operate on app/module paths, but their descriptions clarify compatibility comparison versus scenario prediction.
All tools use a consistent henry_ prefix followed by snake_case verb-based names. The set follows a predictable naming convention throughout, with only henry_reset being a bare verb but still clear and consistent.
Five tools is well-scoped for a focused static analysis server. Each tool serves a clear purpose in the workflow, with no obvious bloat or missing cardinality issue.
The surface covers single-file inspection, pair analysis, failure prediction, finding explanation, and reset, which is most of the analyzer lifecycle. A minor gap is the lack of a list_findings or list_reports tool for discovering prior finding IDs without relying on earlier tool output.