Fris Reverse MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FRIS_HOME | No | Path to the directory used for Fris state. | |
| FRIS_WORKSPACE | Yes | Path to the workspace folder containing only authorized APKs. | |
| FRIS_ALLOW_DOWNLOADS | No | Set to 0 to keep downloads disabled when tools are already installed, or 1 to allow the agent to install tools after explicit confirmation. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| capabilitiesC | Static capabilities and honest limitations |
| doctorA | Check local Java and installed tool integrity |
| install_toolsC | Download official engines only with dual operator consent |
| inspect_apkC | Bounded APK inventory, not signature verification |
| analyze_apkC | Run static engines and create evidence job |
| list_artifactsC | Page job file inventory |
| read_artifactC | Read untrusted text, byte offsets, max 16 KiB |
| review_manifestC | Review decoded manifest with evidence, not security verdict |
| inspect_headersC | Inspect conventional DEX and ELF headers without execution |
| compare_apksC | Compare APK identities and CRC32/size inventories |
| search_artifactsC | Bounded literal text search; excerpts may contain secrets |
| summarize_jobC | Write Markdown summary of engine evidence, not original source |
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 12 tools
Tools target distinct phases (inventory, analysis, artifact reading, manifest review, header inspection), and descriptions carefully scope boundaries. However, inspect_apk vs analyze_apk vs inspect_headers vs review_manifest could still be confused by an agent at first glance, since they all operate on APK contents with subtle differences.
Most tools follow a clear verb_noun pattern (inspect_apk, analyze_apk, list_artifacts, read_artifact, review_manifest, compare_apks, search_artifacts, summarize_job, install_tools). Two outliers—capabilities and doctor—deviate from the pattern but are readable and contextually sensible.
Twelve tools map well to a coherent APK static-analysis workflow: setup (doctor, install_tools, capabilities), analysis (inspect_apk, analyze_apk, inspect_headers, compare_apks, review_manifest), and evidence handling (list_artifacts, read_artifact, search_artifacts, summarize_job). Each tool appears to earn its place.
The surface covers the core lifecycle: environment checks, engine installation, inspection, analysis job creation, artifact inventory/read/search, comparison, manifest review, and summary. Minor gaps exist—no explicit job cleanup/deletion or artifact export tool—but core workflows are covered.