MCP servers › io.github.laaielichter › reverseport
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
io.github.laaielichter/reverseport
Reverse engineer anything. Port it anywhere. One MCP server for coding agents. — the publisher's description
Summary
io.github.laaielichter/reverseport is a local MCP server listed in the official MCP registry at version 1.8.0. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 34 tools, 0 resources and 0 prompts.
Record checks
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- met: Repository publishes a security policy (SECURITY.md)
- met: Package names its licence with a standard (SPDX) identifier
- met: The version the registry lists can be installed and is not withdrawn
- met: npm package carries build provenance (attestation)
- met: No known critical or high advisory in the package or its dependencies
- #6,287 of 15,112 packages by monthly downloads, tied with 9 others
- Not ranked by stars: 4 stars (ranked from 10)
- #772 of 1,074 packages meeting all 9 record checks, by downloads
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Key facts
- Runs
- local package
- Transport
- standard input/output
- Package
- npm · listed version current
- License
- MIT
- Dependencies
- no known high or critical advisories
- Repository
- public
- Tools
- 34
- Described as changing data
- 17 of 34 toolsAI-classified
- Mainly works on
- files and code on the machine it runs onAI-classified
- Topic
- developer-toolsAI-classified
- Last tested
- 2026-10-23
Worth knowing before you connect it
- 17 tools are described as changing something (re_archive, re_extract, re_strings, …): our AI model's reading of the descriptions, not something we tested. We did not call them.
- Its package is signed and carries a build record naming its source.
Each line comes from a section below, with its source and date.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-23
- Mode
- read-only (no tool calls)
- Latest version
- 1.8.0, published 2026-10-20 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-12 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 8 versions listed, 2026-10-12 to 2026-10-20; 8 in the 90 days before the 2026-10-23 snapshot.(versions still listed in the registry only)
Most recent 8 versions
1.8.0· 2026-10-201.7.0· 2026-10-201.6.0· 2026-10-191.5.0· 2026-10-191.4.0· 2026-10-191.3.0· 2026-10-191.2.0· 2026-10-191.0.0· 2026-10-12
- Registry data
- snapshot 2026-10-23
- Package and repository
- checked 2026-10-23
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Changes since the last refresh
New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.8.0 (published 2026-10-20).
Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.
What it is
What does this server offer?
Observed inventoryWhat it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on.
17 of 34 tools are described as changing something (creating, editing, deleting, sending or running).
- re_scanreads or searches
“Reconnaissance of a folder: detects the engine/framework (Godot, Unity, Unreal, GameMaker, RPG Maker, Ren'Py, LÖVE, Defold, Bevy, MonoGame, three.js/Phaser/Electron, Flutter, .NET, Go, Rust, Python…)…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
pathstringrequired“Folder to scan.”maxFilesinteger“Stop after this many files (default 50000).”
- re_graphreads or searches
“Builds the dependency graph of a project: imports/includes/requires, Godot res:// loads and scene resources, Unity script/prefab GUIDs, and type references (C#, GDScript class_name/autoloads, Java…).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
pathstringrequired“Project folder.”limitinteger“Files in portOrder (default 80; edges 40).”formatstring“json (default), mermaid or both.”
- re_symbolsreads or searches
“Code structure for one file or a whole folder (30+ languages: GDScript, C#, C/C++ incl.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
pathstringrequired“File or folder.”matchstring“Filter names (e.g.”limitinteger“Max files (default 60).”
- re_scenereads or searches
“Reads Godot .tscn/.tres/project.godot (Godot 3 and 4) and Unity .unity/.prefab/.asset (text serialization) into one neutral tree: node names, types, scripts, transforms (position, quaternion, scale),…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
filestringrequired“Scene/prefab/project file.”
- re_binaryreads or searches
“Inspects PE/EXE/DLL (incl.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
filestringrequired“Binary file.”stringsobject“String options: min, limit, match, maxMB, raw.”namesobject“Import/export name options: match, limit.”maxTypesinteger“.NET types to list (default 300).”
- re_archivereads or searchesdescribed as changing data
“Lists or extracts Godot .pck packs (also packs embedded in an exported .exe/.x86_64), ZIP family (apk, jar, ipa, nupkg, docx), tar and tar.gz (.unitypackage), Electron .asar, Ren'Py .rpa (2.0/3.0, in…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 1 required
filestringrequired“Archive/pack/executable.”actionstring“list (default) or extract.”matchstring“Only entries matching: substring, glob (*.gd, scenes/*.tscn) or /regex/.”limitinteger“Max entries listed/extracted (default 500).”outstring“Extraction folder (default: workspace/extracted/<file>).”maxBytesinteger“Extraction budget in bytes (default 4 GiB).”
- re_probereads or searches
“For unknown or custom formats: identifies the format at an offset, hex view, entropy map (text/code/compressed regions), embedded files (PNG, OGG, WAV, ZIP, GDPC, glTF, DDS, ELF/PE…) with offsets and…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
filestringrequired“File to probe.”offsetinteger“Start offset (default 0).”lengthinteger“Bytes in the hex view (default 256, max 4096).”maxMBinteger“MiB to scan for entropy/embedded files (default 512).”
- re_extractcreates or changes datadescribed as changing data
“Copies a byte range (e.g.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 2 required
filestringrequired“Source file.”offsetintegerrequired“Start offset.”lengthinteger“Bytes to copy.”namestring“Output file name.”
- re_comparereads or searches
“Compares two folders (added/removed/changed files), two packs/archives (entries, MD5 for Godot packs), two executables (imports, exports, sections) or any two files (first difference, changed regions…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
astringrequired“First folder/file (old).”bstringrequired“Second folder/file (new).”limitinteger“Max items per list (default 300).”
- re_refsreads or searches
“Audits a Unity project's GUID references: references to GUIDs no .meta file declares (dangling: missing scripts, pink materials), the same GUID in two .meta files (copies made outside Unity), assets …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
pathstringrequired“Unity project root, or any folder/file inside it.”limitinteger“Max items per list (default 200).”
- re_stringsdescribed as changing data
“Localisation: extracts user-facing text with stable ids from Godot scenes/resources and GDScript (text, tooltips, tr()), Unity YAML (m_Text, TextMeshPro) and C#, RPG Maker MV/MZ data (Show Text, choi…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
8 inputs, 1 required
pathstringrequired“Project folder.”actionstring“extract (default) or apply.”formatstring“extract: json (default), po, csv or all.”outstring“extract: folder for the catalog/.pot/.csv (default workspace/strings).”translationsstring“apply: translated .po, .csv (id|source + translation columns) or .json ({id|source: translation}).”langstring“Language code for the output (e.g.”matchstring“Only files whose path contains this.”limitinteger“Entries to return inline (default 500; the files hold all).”
- re_apicheckreads or searches
“Checks GDScript (and class names in C#, names in shaders) against name-only snapshots of the real Godot API (godot@3, godot@4.3, godot@4.7) plus the official 3→4 rename table.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
pathstring“A .gd/.cs/.gdshader file or a project folder.”contentstring“Code to check instead of path.”enginestring“Target: godot@4.7, godot@4.3, godot@3 (or just 4 / 3).”limitinteger“Max files in the result (default 300).”
Show 22 more tools
- port_upgradecreates or changes datadescribed as changing data
“Converts a Godot 3.x project to Godot 4 as a COPY (the source is never modified): the official rename table for classes, builtin types, functions, properties, signals, enums, colors, theme overrides,…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 1 required
pathstringrequired“Godot 3 project folder (has project.godot with config_version=4).”actionstring“check (default): report what would change.”outstring“apply: new or empty folder for the copy (default: workspace/upgrades/<name>-godot4).”limitinteger“Max items per list (default 300).”
- re_savereads or searches
“Peels the open layers of a save file (gzip/zlib, base64, LZ-String as RPG Maker MV/MZ uses, JSON, XML, INI/ConfigFile, Godot store_var) and lists every field with type, sample and a guessed role (hea…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 1 required
filestringrequired“The save file.”comparestring“A second save of the same game to diff against.”actionstring“inspect (default) or schema (write schema + data classes).”outstring“schema: folder for the files (default workspace/saves).”limitinteger“Max fields/changes (default 400).”
- re_decodereads or searches
“Turns what a Godot export leaves into editable text: compiled GDScript (.gdc: Godot 3 bytecode v10–13 and Godot 4.3+ binary tokens v100/v101, zstd-compressed or not) back to .gd with indentation, bin…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
pathstringrequired“A .gdc/.scn/.res/project.binary file or an extracted pack folder.”outstring“Output folder (default workspace/decoded/<name>).”limitinteger“Max files (default 2000).”
- re_il2cppreads or searches
“Reads a Unity IL2CPP global-metadata.dat (metadata versions 24–31; sections are recognised by validating their records, not by fixed offsets): assemblies with type counts, every type with namespace a…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 1 required
filestringrequired“global-metadata.dat (<Game>_Data/il2cpp_data/Metadata/ or Il2CppData/Metadata in WebGL builds).”matchstring“Only types whose name or methods contain this.”includeSystemboolean“Also list Unity/System/mscorlib types (default false).”outstring“Folder for the C# skeletons (default workspace/il2cpp/<game>).”limitinteger“Max types listed (default 400).”
- re_reportcreates or changes datadescribed as changing data
“Writes ARCHITECTURE.md for a project: stack, languages, entry points, mermaid module graph, cycles, most-used files, scene trees of the entry scenes, class table, possibly unused files and external d…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 1 required
pathstringrequired“Project folder.”outstring“Output .md path (default: workspace/reports).”
- re_lookupreads or searchesdescribed as changing data
“Recon without files: give one of query (a name), url (store/web/GitHub page), steamAppId, appStoreId or github.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
10 inputs
querystring“Name of the game, app or software.”urlstring“Steam, App Store, Google Play, GitHub or any public web page URL.”steamAppIdstring“Steam app id.”appStoreIdstring“Apple App Store id.”githubstring“Public GitHub repo: owner/repo or URL.”kindstring“auto (default), game, app or software.”sourcesarray“Limit sources (default all): steam, pcgamingwiki, wikidata, github, appstore, web.”mirrorboolean“GitHub: download the source text (code, scenes, configs) into the workspace.”maxFilesinteger“mirror: max files (default 400).”freshboolean“Skip the one-day cache.”
- re_blueprintcreates or changes datadescribed as changing data
“Turns a re_lookup dossier (lookupId) and/or name, genres, tags and a description into a clean-room rebuild spec that matches the original in function and feel: the systems it is made of, and per syst…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
12 inputs
lookupIdstring“Dossier id from re_lookup.”namestring“Name of the original (when there is no lookupId).”kindstring“game or app (default from the lookup, else game).”genresarray“Genres (e.g.”tagsarray“Tags/categories (e.g.”descriptionstring“What the original is and does.”enginestring“Engine of the original, if known.”targetstring“Target: godot, godot-csharp, unity, unreal, threejs, or web, flutter, react-native, swift, kotlin, electron, or a language.”perspectivestring“2d or 3d (default from the lookup).”archetypesarray“Force archetypes.”outputstring“Project skeleton folder (new or empty; default workspace/blueprints/<name>/project-<target>).”scaffoldboolean“Write the project skeleton (default true for engine targets).”
“Curated porting knowledge: engine conventions (axes, units, handedness, Euler order, FOV, physics tick, lifecycle) and API maps with notes and pitfalls.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
fromstring“Source engine (godot, godot-csharp, unity, unreal, threejs).”tostring“Target engine.”querystring“Filter entries (e.g.”topicstring“Exact topic (lifecycle, input, physics, events, scene tree, rendering…).”
- port_convertcalculates or converts
“Converts positions, rotations (quaternion [x,y,z,w] or Euler degrees in the source engine's convention), scales and camera FOV between godot, godot-csharp, threejs, gltf, bevy, unity, unity-xmirror, …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
9 inputs, 2 required
fromstringrequired“Source system.”tostringrequired“Target system.”positionarray“[x, y, z] in source units.”rotationarray“Quaternion [x, y, z, w].”eulerarray“Euler degrees in the source convention (godot, unity, threejs).”scalearray“[x, y, z].”fovnumber“Camera FOV in degrees (vertical; horizontal for unreal).”aspectnumber“Aspect ratio for FOV conversion (default 16/9).”physicsobject“Physics numbers to carry over; pass {} for the profile and differences only.”
- port_plancreates or changes datadescribed as changing data
“Plans a port of a project to another engine or language and creates the output project (scaffold).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
7 inputs, 2 required
sourcestringrequired“Source project folder.”tostringrequired“Target: godot, godot-csharp, unity, unreal, threejs or a language.”outputstring“Output folder (default: workspace/ports/<id>/output).”namestring“Project name for the target.”includestring“Regex: only source paths matching.”excludestring“Regex: skip source paths matching.”unrealVersionstring“EngineAssociation for Unreal targets (default 5.5).”
- port_unitreads or searchesdescribed as changing data
“Returns one unit with everything needed to port it: source text, symbols, the engine APIs it uses with their mapped equivalents and line numbers (apiHints), conventions, target path and naming rules,…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 1 required
planIdstringrequired“Port plan id from port_plan (port_status lists them).”unitstring“Unit id (u001…), or its source/target path.”fullboolean“Repeat the conventions and checklist even after the first finished unit (they are shortened after that).”
- port_writecreates or changes datadescribed as changing data
“Writes the ported file(s) for a unit into the output project (never outside it) and records progress.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
7 inputs, 2 required
planIdstringrequired“Port plan id from port_plan (port_status lists them).”unitstringrequired“Unit id or path.”contentstring“File content for the unit target.”filesarray“Several files (e.g.”copyboolean“Copy the source file unchanged (assets).”statusstring“done (default), partial or skipped.”notesstring“What is left or why it was skipped.”
- port_scenecreates or changes datadescribed as changing data
“Converts a scene deterministically: Godot .tscn → Unity prefab/scene spec (+ editor builder menu), three.js TypeScript builder module, Unreal scene spec (cm, Z-up) or Godot C# (script paths swapped);…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs
planIdstring“Port plan id from port_plan (port_status lists them).”unitstring“Unit id (u001…), or its source/target path.”filestring“Scene file (without a plan).”tostring“Target engine (without a plan).”outstring“Output file (without a plan).”
- port_shadercreates or changes datadescribed as changing data
“Translates shader code between engines as a faithful first draft: Unity ShaderLab (surface shaders → fragment() with ALBEDO/NORMAL_MAP/METALLIC/ROUGHNESS/EMISSION/ALPHA; vertex/fragment shaders → ver…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 1 required
filestring“Shader file (.shader, .gdshader, .glsl, .hlsl, .cginc).”contentstring“Shader code instead of file.”tostringrequired“Target: godot, threejs or unity.”outstring“Output file (default workspace/shaders/<name>.<ext>).”namestring“Shader name for the output.”
- port_tracereads or searchesdescribed as changing data
“action:"harness" returns (and with out writes) a small logger for the engine (ReversePortTrace.gd/.cs/.js/.h) that records the chosen properties of one node per physics tick to JSON with a fixed seed…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
10 inputs
actionstring“harness (default) or compare.”enginestring“harness: godot, unity, threejs or unreal.”nodestring“harness: node path to watch (default the harness's target).”propertiesarray“harness: properties to log (default ["position"]; velocity, rotation, custom fields).”ticksinteger“harness: ticks to record (default 300).”outstring“harness: write the logger to this file.”astring“compare: trace JSON from the original.”bstring“compare: trace JSON from the port.”tolerancenumber“compare: allowed error per sample (default 0.01).”axisMaparray“compare: reorder/negate b's vector components, e.g.”
- port_rpgmakercreates or changes datadescribed as changing data
“Ports an RPG Maker MV/MZ project (data/*.json, img/, audio/; also www/ of a deployed game) to a new Godot 4 project: every map becomes a scene whose layers are drawn from the original tileset images …”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 1 required
pathstringrequired“RPG Maker MV/MZ project folder (or the www/ folder of a deployed game).”outstring“New or empty folder for the Godot project (default workspace/ports/<name>-godot).”limitinteger“Max maps listed (default 300).”
- port_copy_assetscreates or changes datadescribed as changing data
“Copies every pending asset unit (textures, audio, models, fonts, video) of a plan into the output project.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 1 required
planIdstringrequired“Port plan id from port_plan (port_status lists them).”matchstring“Regex over source paths.”
- port_statusreads or searches
“Without planId: lists all port plans in the workspace with progress.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
planIdstring“Port plan id from port_plan (port_status lists them).”
- port_verifyreads or searches
“Checks a port: missing output files, units not ported yet, source-engine API leftovers, functions and signals from the source that do not exist in the port (lifecycle renames understood), PORT/TODO m…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
planIdstringrequired“Port plan id from port_plan (port_status lists them).”
- re_casecreates or changes datadescribed as changing data
“A ledger that keeps an investigation or port honest.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
33 inputs, 1 required
actionstringrequired“What to do.”caseIdstring“Case id (init returns it; list shows them).”questionstring“init: the concrete question the case answers.”targetstring“init: what is examined (folder, file, app, bug).”intentstring“init: kind of work (default investigate).”authorizedboolean“init: the user confirmed they own or may examine the target.”filestring“evidence: file to copy and hash.”contentstring“evidence/test: text to save instead of a file, e.g.”kindstring“evidence: kind (default source, or tool-result for content).”locatorstring“evidence: exact origin (file:line, offset, tool + arguments, URL); observed claim: exact place.”notestring“evidence: what it shows.”statementstring“claim: what you claim.”evidencearray“claim: evidence ids it rests on, e.g.”confidencestring“claim: observed, inferred (default) or unresolved.”alternativestring“claim: a competing explanation.”falsifierstring“claim: the check that would prove it wrong.”choosestring“decision: the route you pick.”insteadOfarray“decision: the alternatives you rejected.”whystring“decision: the trade-off.”claimsarray“decision: claim ids it rests on.”reversibleboolean“decision: can it be undone cheaply.”revisitWhenstring“decision: what would change your mind.”labelstring“test: test name.”logstring“test: saved log file (or give content).”exitCodeinteger“test: exit code of the run.”
and 8 more not listed here.
“Optional, any time: note what worked, what was confusing or slow, and what would help next time.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs
toolstring“Tool the note is about (if any).”ratinginteger“How well it served the task, 1 (poorly) to 5 (very well).”workedstring“What helped.”frictionstring“What got in the way: unclear text, wasted calls, too much output, errors without a next step…”suggestionstring“What would help.”agentstring“Who you are, if you like (client, model).”
- set_tool_profiledoes something else
“Switches how many tools are listed and how long their descriptions are: compact (small or older models, small context), standard (default), full (every engine tool).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
profilestringrequired“compact, standard or full.”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
- Says what the tool does
- 100% of 34 tools
- Says what it returns
- 92% of 25 tools
- States limits, defaults or errors
- 48% of 33 tools
- Says when to use it
- 100% of 34 tools
- Items covered per tool
- 3.4 of 4 on average
Counted from the listing
- Parameters with a description
- 100% of 182
- Tools with a description
- 100% of 34
- Typical description length
- 566 characters
The tool set
Counted from the listing
- Tools
- 34
- Size of the list
- about 12,443 tokens for an agent to load (characters ÷ 4)
- Naming
- 34 of 34 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 34 of 34 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the npm package reverseport
Our sandbox started this package on 2026-10-23 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below. The command runs the publisher’s code on your machine.
Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)
{
"mcpServers": {
"reverseport": {
"command": "npx",
"args": [
"-y",
"reverseport@1.8.0",
"mcp"
]
}
}
}Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"reverseport": {
"command": "npx",
"args": [
"-y",
"reverseport@1.8.0",
"mcp"
]
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"reverseport": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"reverseport@1.8.0",
"mcp"
]
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"reverseport","type":"stdio","command":"npx","args":["-y","reverseport@1.8.0","mcp"]}'Claude Code
claude mcp add --transport stdio reverseport -- npx -y reverseport@1.8.0 mcp
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 -- npx -y reverseport@1.8.0 mcp
- Arguments are written as the registry entry gives them; a named one as “--name value”, the form the registry documentation shows.
- This runs the publisher's code on your machine (npx). Read its README first.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
Can it be installed, and is it up to date?
Version pin · advisories
Listed version
- Registry lists
- 1.8.0
- Latest stable
- 1.8.0
- Status
- current
- Withdrawn
- no
Source: registry.npmjs.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.
Dependency advisories
Counted in the full dependency tree as resolved on 2026-10-23 (npm audit). Bars share one scale. The package itself has no known vulnerability (OSV.dev).
Integrity, provenance, license
- Integrity
- sha512-MzYV+8sCjYJYjcjfK…
- Signature
- signed and attested
- License
- MIT
Source: the package registry · 2026-10-23.
Usage
- Downloads
- 416 in the last month
Source: api.npmjs.org · 2026-10-23.
Does the registry listing match what we found?
Feature #6The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Published package can be started | Started and answered | matches | our test · 2026-10-23 |
| Version 1.8.0 on npm | Exists and can be installed | matches | npm · 2026-10-23 |
| Repository github.com/laaielichter/reverseport | Opens publicly | matches | api.github.com · 2026-10-23 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.laaielichter · 2 servers
- GitHub owner
- a personal account (laaielichter)
- Build record
- signed and attested
- Repository
- github.com/laaielichter/reverseport
- Stars
- 4
- Repository age
- 0–30 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- SECURITY.md
Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.
Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.
Choosing
Record checks
Public records · not a safety rating9 of 9 record checks met
- #6,287 of 15,112 packages by monthly downloads, tied with 9 others
- Not ranked by stars: 4 stars (ranked from 10)
- #772 of 1,074 packages meeting all 9 record checks, by downloads
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- MetSource repository link opensThe linked GitHub repository is public.
- MetRepository is not archivedNot archived.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- MetRepository publishes a security policy (SECURITY.md)SECURITY.md found.
- MetPackage names its licence with a standard (SPDX) identifierMIT
- MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
- Metnpm package carries build provenance (attestation)Signed, with a build attestation naming the source and workflow.
- MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards
Common questions about io.github.laaielichter/reverseport
Answered from the data aboveIs io.github.laaielichter/reverseport safe to install?
We do not rate servers as safe or unsafe. 9 of its 9 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its npm package carries a build-provenance attestation that names its source repository and build workflow. Its source repository opens publicly. Its repository had a push in the last 90 days. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. 17 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Has io.github.laaielichter/reverseport been security tested?
Partly. 2 of the 12 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.
What can io.github.laaielichter/reverseport do?
It lists 34 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, calculate or convert and do something else. We did not call any tool, so this describes the text, not the behaviour.
Can io.github.laaielichter/reverseport change or delete data?
17 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.
Does io.github.laaielichter/reverseport publish a security policy?
Yes: its repository has a public security policy (github.com/laaielichter/reverseport/blob/HEAD/SECURITY.md). That is the publisher's statement, not permission for us to test the server, and we call none of its tools.
Is the listed version current?
Yes. The registry lists 1.8.0, the latest stable release on npm.
Where is the source code of io.github.laaielichter/reverseport?
In github.com/laaielichter/reverseport, which opens publicly.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Similar servers
Same topic · AI-read
- io.github.Albasha0x0/corvusCorvusalso has tools that calculates or converts, creates or changes data, does something else, reads or searchescompare with this one
- io.github.4DA-Systems/victauriVictaurialso has tools that calculates or converts, creates or changes data, does something else, reads or searchescompare with this one
- io.github.ellmos-ai/ellmos-filecommander-mcpellmos FileCommanderalso has tools that calculates or converts, creates or changes data, does something else, reads or searchescompare with this one
- io.github.kivanccakmak/yaverYaveralso has tools that calculates or converts, creates or changes data, does something else, reads or searchescompare with this one
- io.github.yaver-io/yaverYaveralso has tools that calculates or converts, creates or changes data, does something else, reads or searchescompare with this one
- io.github.The-40-Thieves/codecalccodecalcalso has tools that calculates or converts, creates or changes data, does something else, reads or searchescompare with this one
Active servers whose topic is also “developer-tools” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Not probed (read-only run)
We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not applicable
- Consent handling: not applicable
- Sign-in metadata: not applicable
2 exercised10 not run (reason given)6 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 12 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
Source: our own test in an isolated sandbox, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted the published package in an isolated sandbox (read-only mode)
- 72,343 msConnected after 0 redirects.
- Read the inventory: 34 tools, 0 resources, 0 prompts.
- 73,150 msFinished: 2 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “io.github.laaielichter/reverseport: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.laaielichter/reverseport
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/io.github.laaielichter/reverseport)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.
Write to hello@protocolprobe.com · corrections log · methodology