MCP servers › io.github.itAlex240 › rack-architect-mcp
MCP server · registry snapshot 2026-11-03 · last tested 2026-11-03
io.github.itAlex240/rack-architect-mcp
by itAlex240 · GitHub account (the registry's namespace rule)repository: same ownerSource ↗
Hosted Remote MCP & 3D/2D Rack-as-Code planner, 5-stage validator, CAD SVG/BOM & STL generator. — the publisher's description
Summary
io.github.itAlex240/rack-architect-mcp is a remote and local MCP server listed in the official MCP registry at version 0.7.7, under the namespace of the GitHub account itAlex240. Its linked repository, github.com/itAlex240/rack-architect-mcp, belongs to the same GitHub account. On 2026-11-03 ProtocolProbe connected to it in read-only mode and read its inventory: 12 tools, 4 resources and 5 prompts.
Record checks
5 of 5 record checks met · 4 do not apply
- 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)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: not an npm or PyPI package
- Not ranked by stars: 1 star (ranked from 10)
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Operate this server? Correct a fact · README badge · Run the checks yourself
Key facts
- Runs
- remote and local package
- Transport
- server-sent events, standard input/output, streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Package
- MCP bundle
- Repository
- public
- Tools
- 12
- Last tested
- 2026-11-03
Tool list size
17,627 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (12 tools). Counted with Anthropic's token counter on 2026-11-03, from the tool list we read on 2026-11-03. Median across 25,738 counted servers: 2,858 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-03 (mcp.rackarchitect.dev), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (0.7.7).
Observed fact
This server accepted a session without any credential and lists 5 tools whose name or declaration suggests they change data (init_rack, modify_equipment, disconnect_cables, plan_external_endpoints, export_deliverables). That is our reading of the names; we did not call them. Source: our connection, 2026-11-03.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-03
- Mode
- read-only (no tool calls)
- Latest version
- 0.7.7, published 2026-11-02 (registry, as of the 2026-11-03 snapshot)
- First listed version
- 2026-10-28 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 28 versions listed, 2026-10-28 to 2026-11-02; 28 in the 90 days before the 2026-11-03 snapshot.(versions still listed in the registry only)
Most recent 12 versions
0.7.7· 2026-11-020.7.6· 2026-11-020.7.4· 2026-10-290.7.3· 2026-10-290.7.2· 2026-10-290.7.1· 2026-10-290.7.0· 2026-10-290.6.7· 2026-10-290.5.0· 2026-10-290.4.12· 2026-10-280.4.11· 2026-10-280.4.10· 2026-10-28
- Registry data
- snapshot 2026-11-03
- Package and repository
- checked 2026-11-03
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry; repository link does not open; repository archived; no push in over 365 days. Does not apply: listed version cannot be installed or is withdrawn. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
Version 0.7.6 (published 2026-11-02) → 0.7.7 (published 2026-11-02), between the registry lists of 2026-11-02 and 2026-11-03.
The publisher’s GitHub release note for v0.7.7 (“🏗️ RackArchitect MCP v0.7.7 — 3D/2D Rack Planner, CAD Blueprints & 3D-Print Files (.STL)”), published 2026-11-02.
Read the release note (the publisher’s text, shown as plain text, cut at 4,000 characters)
<div align="center">
# 🏗️ RackArchitect MCP `v0.7.7` — 3D/2D Rack Planner, Hosted Remote MCP (`mcp.rackarchitect.dev`), CAD Blueprints & 3D-Print Package (`.STL`)
**Welcome to RackArchitect MCP `v0.7.7`!**
Whether you are a **complete beginner with zero coding experience** who just wants to plan a compact 10-inch mini-rack or 19-inch server rack in your browser and 3D-print custom modular brackets, or an **AI / DevOps engineer** orchestrating racks via our **zero-install Hosted Remote MCP endpoint (`https://mcp.rackarchitect.dev/mcp`)** — everything is explained step by step below (**English first, followed by the full German version / Deutsche Version weiter unten**).
<p align="center">
<a href="https://mcp.rackarchitect.dev/">
<img src="https://raw.githubusercontent.com/itAlex240/rack-architect-mcp/main/docs/assets/rack-architect-hero-demo.gif" alt="RackArchitect MCP — Live 3D Digital Twin, X-Ray Z-Depth Plug Clearance, Autonomous MCP Self-Correction & 2D CAD Blueprints" width="100%" />
</a>
</p>
> **✨ What's New in the Last 3 Releases (`v0.7.5` – `v0.7.7`):**
> - **Dual Security Audit Hardening, 10x Faster 3D Cable Router & Read-Only Viewer Token Isolation (`v0.7.7`):** Separated public HMAC-SHA256 `viewerToken` URLs (`/?session=<viewerToken>`) from the write-capable `Mcp-Session-Id` header, enforced read-only remote viewer WebSockets (`60 commands/min` limit), confined local `export_deliverables` `output_dir` to the project workspace (with `fs.realpathSync` symlink checks), added local DNS-rebinding `Host` header guards (`421`), tightened proxy trust & IPv6 `/64` rate-limit bucketing, removed `saltHex` persistence from `telemetry.json`, and accelerated 3D Catmull-Rom cable routing via 3D AABB culling and collinear spline compaction.
> - **Accurate Remote MCP Crawler Telemetry, Idle Probe Session Cleanup & Resilient Registry Publishing (`v0.7.6`):** Automated MCP directory crawlers and liveness monitors (`mcpbeat`, `AgentRankProbe`, `SealKeeperBot`, `EveryMCP-Probe`, `mcptry.com`, …) are now counted as `registry-probe` instead of inflating `other-mcp` on the Grafana dashboard, never-used crawler sessions are released after `10 min` idle instead of `2 h`, and the MCP Registry publish step now retries up to 5 times.
> - **Precision 5/5 TDQS MCP Tool Descriptions Across All 12 Tools (`v0.7.5`):** Refined all 12 `MCP_TOOL_DEFINITIONS` descriptions in `@rack-mcp/core-domain` into crisp, parenthetical-free 4-sentence contracts with explicit catalog ordering/bounds (`search_catalog`, `get_device_blueprint`), deterministic export filenames and overwrite vs. zero-disk remote URL behavior (`export_deliverables`), top-level `blueprint` wrapper and cross-field constraints (`define_custom_blueprint`, `init_rack`, `mount_equipment`, `modify_equipment`, `plan_external_endpoints`), and undo/redo history exclusions (`undo_redo`).
<details>
<summary>🗄️ <b>View Earlier Releases (v0.1.0 – v0.7.4) in the Release Archive</b></summary>
<br />
- **`v0.7.4`** — Synchronized Agent Skill (`SKILL.md`), 5 EIA-310 Archetypes (`10"`/`19"`/`6"`) & 100% exact schema/prompt parity across all 21 diagnostic codes, 20 cable types, and 67 blueprints.
- **`v0.7.3`** — Official Dual-Stack HTTPS domain `https://mcp.rackarchitect.dev` (`/mcp`, `/sse`, `/?session=<uuid>`) & multi-origin CSWSH/CORS compatibility for legacy `sslip.io` links.
- **`v0.7.2`** — Collision-free rear-cavity 3D cable routing (`resolveEffectivePortZone`), detour-aware open-`U` pass-through portal scoring, true 3D `(z, y)` 2D Side-Cutaway projection & 2-Section 3-Tier Power/PoE DAG + Multi-Track Wiring Plan.
- **`v0.7.1`** — Crisp 6-scene animated 3D/2D Hero showcase GIF (`docs/assets/rack-architect-hero-demo.gif`) embedded in `README.md` and Release Notes.
- **`v0.7.0`** — Privacy-first GDPR-compliant Remote MCP usage, active AI client & wire-traffic telemetry (`GET /metrics` Prometheus & `GET /api/telemetry` JSON with salted HMAC-SHA256 `Today`/`7d`/`30d` visitor deduplicaSource: the official MCP Registry list on 2026-11-02 and on 2026-11-03; release notes from the GitHub Releases API, checked 2026-11-03.
What it is
What does this server offer?
Observed inventoryNone of its 12 tools are described as changing anything. For 12 the reading was uncertain, so no mark is shown.
- search_catalogon 109 other servers
“Search and filter the local hardware catalog to discover compatible rackmount devices, modular carriers, and sub-modules before mounting.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs
querystring“Optional case-insensitive substring filter matching slug, manufacturer, or model name (omit to match all).”form_factorstring“Primary rack width or mounting form-factor filter (shorthands "10inch", "19inch", and "6inch" match both direct rackmount equipment and modular carriers of tha…”mount_typestring“Optional alias for form_factor to filter by physical mounting style ("rackmount-10", "rackmount-19", "rackmount-6", "sub-module", or "shelf-standing"); combine…”categorystring“Functional hardware category filter (e.g., "switch", "router", "ups", "pdu", "patch-panel", "modular-carrier", "mini-pc", "sbc").”max_depth_mmnumber“Maximum allowed chassis depth in millimeters (inclusive upper bound).”min_poe_budget_wattsnumber“Minimum required PSE PoE output power budget in watts (inclusive lower bound).”accepted_slot_typestring“Sub-module slot compatibility token matching either a sub-module slot_compatibility or a carrier slot accepted_slot_type (e.g., "mini-pc-1liter", "sbc-rpi5", "…”
- get_device_blueprint
“Retrieve the complete hardware specification, millimeter port coordinates, electrical and PoE ratings, and carrier slot geometry for a single catalog blueprint.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
slugstringrequired“Exact lowercase kebab-case hardware catalog blueprint slug to retrieve (discoverable via search_catalog).”
- define_custom_blueprint
“Validate and register a custom hardware blueprint into the active catalog so unlisted equipment can be mounted.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
blueprintobjectrequired“Complete custom hardware blueprint specification; ports may be defined via explicit ports[], repeating port_groups[] macros, or both.”
- init_rack
“Initialize a new rack project and destructively reset the active rack.yaml state to an empty enclosure with the specified width standard, U height, and rail depth.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
7 inputs, 3 required
project_namestring“Human-readable project name stored in rack.yaml.”standardstringrequired“Mechanical rack width standard ("19inch" = 482.6mm, "10inch" = 254.0mm, "6inch" = 152.4mm).”u_heightintegerrequired“Total usable vertical rack height in Rack Units (1U = 44.45mm, 1..60U).”rail_depth_mmnumberrequired“Front-to-rear mounting rail depth in millimeters along the Z-axis (max 2000mm).”enclosure_typestring“Enclosure door style ("open-frame", "closed-glass-front", or "closed-vented-front").”front_door_clearance_mmnumber“Available clearance in millimeters between front mounting rails (Z=0) and a closed front door.”rear_clearance_mmnumber“Available clearance in millimeters behind the rear mounting rails (Z=rail_depth_mm) for power plugs and bending radii.”
- mount_equipment
“Mount a new hardware device instance onto a rack unit or into a modular carrier bay in the active rack.yaml project and run 5-stage validation.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
7 inputs, 2 required
instance_idstringrequired“Unique project-wide instance identifier for this mounted device (e.g., "ups-u1", "sw-core-01").”blueprint_slugstringrequired“Catalog or custom hardware blueprint slug to instantiate.”hostnamestring“Optional logical hostname or display label shown in elevations and schematics.”u_positioninteger“1-indexed lowest Rack Unit (U) when mounting directly onto the rack rails (mutually exclusive with parent_carrier_id/slot_id).”facestring“Target rack mounting face ("front" or "rear") for direct rackmount equipment.”parent_carrier_idstring“Mounted parent modular-carrier instance_id when mounting a sub-module (requires slot_id; mutually exclusive with u_position).”slot_idstring“Target bay slot_id inside parent_carrier_id when mounting a sub-module (e.g., "left-bay", "keystone-1").”
- modify_equipment
“Move, rename, or destructively remove an existing mounted device or child sub-module in the active rack, recalculate 3D cable splines, and re-run 5-stage validation.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
11 inputs, 2 required
instance_idstringrequired“Existing mounted device or child sub-module instance_id to modify.”actionstringrequired“Modification operation: "move" relocates a device, "rename" updates its hostname, and "remove" deletes the device instance.”u_positioninteger“New 1-indexed U position when action is "move" on a direct rackmount device (takes precedence over new_u_position).”new_u_positioninteger“Optional alias for u_position when action is "move".”facestring“New mounting face ("front" or "rear") when action is "move" on a rackmount device (takes precedence over new_face).”new_facestring“Optional alias for face when action is "move".”parent_carrier_idstring“Target parent carrier instance_id when action is "move" on a child sub-module.”slot_idstring“Target slot_id inside parent_carrier_id when action is "move" on a child sub-module.”hostnamestring“New logical hostname when action is "rename" (takes precedence over new_hostname).”new_hostnamestring“Optional alias for hostname when action is "rename".”remove_connected_cablesboolean“When action is "remove", whether to automatically disconnect all cables and external endpoints attached to the removed device (default: true).”
- connect_cables
“Connect or update a batch of up to 128 power and network cables between mounted device ports in the active rack, computing 3D Catmull-Rom splines, commercial length bins, and PoE or power budgets.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
cablesarrayrequired“Batch of one or more cable connections to upsert by cable_id, route in 3D, and validate (max 128 per call).”
- disconnect_cables
“Remove specific cables by identifier or strip all cables attached to a mounted device or modular carrier from the active rack, then re-evaluate PoE budgets and plug clearances.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs
cable_idsarray“Specific cable_id values to disconnect (can be combined with instance_id; at least one of cable_ids or instance_id must be provided).”instance_idstring“Mounted device or modular-carrier instance_id whose attached cables (including child sub-module cables) should all be disconnected.”
- plan_external_endpoints
“Terminate external building or room cable drops onto the rear RJ45 ports of a mounted patch panel without consuming rack U slots, and optionally auto-create labeled Cat6A front patch cables to a moun…”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
8 inputs, 1 required
patch_panel_instance_idstringrequired“Mounted patch panel instance_id whose rear ports receive the incoming building cable drops.”start_port_numberinteger“1-indexed starting port number on the patch panel (defaults to next free rear port or 1).”entry_positionstring“Rear building cable conduit entry point into the rack frame.”groupsarray“Batch groups of external drops (e.g., 10x PoE cameras, 5x Wi-Fi APs, 5x room LAN outlets).”endpointsarray“Individual external building/room drops to terminate on the rear of the patch panel.”auto_connect_switch_instance_idstring“Optional switch instance_id to automatically patch from the front of the patch panel using labeled Cat6A cables.”auto_connect_switch_start_portinteger“1-indexed starting Ethernet port number on auto_connect_switch_instance_id (e.g., 1 for eth1).”clear_existingboolean“If true, destructively clears existing external_endpoints (and their front patch cables) on patch_panel_instance_id before planning.”
- validate_rack
“Inspect the active rack.yaml state and run all 5 deterministic validation stages covering mechanical bounds, 3D depth and plug clearances, PoE and power budgets, cable compatibility, and thermal limi…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- export_deliverables
“Generate 2D elevation and wiring SVGs, a Markdown BOM, a binary 3D GLB scene, and parametric OpenSCAD or watertight STL 3D-print models for the active rack project.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs
formatsarray“Deliverable formats to generate and write to disk (defaults to all 6 formats; carrier-scad and carrier-stl emit files when modular carriers are mounted).”output_dirstring“Optional target filesystem directory for generated files in local stdio mode (defaults to the directory of the active rack.yaml file; ignored on hosted remote …”
- undo_redo
“Traverse the per-project in-memory history ring buffer of up to 50 snapshots to revert the latest rack mutation or reapply a reverted mutation, updating rack.yaml atomically.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input, 1 required
actionstringrequired“History traversal direction: "undo" reverts the most recent state mutation, "redo" reapplies a reverted mutation.”
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 2026-11-03.
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
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 100% of 48
- Tools with a description
- 100% of 12
- Typical description length
- 868 characters
The tool set
Counted from the listing
- Tools
- 12
- Size of the list
- about 51,895 tokens for an agent to load (characters ÷ 4)
- Naming
- 12 of 12 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 12 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 remote endpoint (Streamable HTTP)
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://mcp.rackarchitect.dev/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"rack-architect-mcp": {
"url": "https://mcp.rackarchitect.dev/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"rack-architect-mcp": {
"type": "http",
"url": "https://mcp.rackarchitect.dev/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"rack-architect-mcp","type":"http","url":"https://mcp.rackarchitect.dev/mcp"}'Claude Code
claude mcp add --transport http rack-architect-mcp https://mcp.rackarchitect.dev/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"rack-architect-mcp": {
"type": "streamableHttp",
"url": "https://mcp.rackarchitect.dev/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"rack-architect-mcp": {
"httpUrl": "https://mcp.rackarchitect.dev/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.rack-architect-mcp] url = "https://mcp.rackarchitect.dev/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"rack-architect-mcp": {
"url": "https://mcp.rackarchitect.dev/mcp"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://mcp.rackarchitect.dev/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
- No config: the MCP bundle is a file to install in a client that supports bundles, not a command.
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; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). 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.
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint mcp.rackarchitect.dev/mcp | Session opened | matches | our test · 2026-11-03 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-03 |
| Repository github.com/itAlex240/rack-architect-mcp | Opens publicly | matches | api.github.com · 2026-11-03 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.itAlex240
- GitHub owner
- a personal account (itAlex240)
- Repository
- github.com/itAlex240/rack-architect-mcp
- Stars
- 1
- 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 · 2026-11-03; security policy read from GitHub · 2026-11-02.
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.
Tool list changes
Our reads compared · no tool calledHosted endpoint mcp.rackarchitect.dev/mcp
1 of 2 comparisons between consecutive reads showed a change (3 reads, 2026-10-30 to 2026-11-03; versions 0.7.4 to 0.7.7).
Last change seen between our reads on 2026-11-02 (version 0.7.6) and 2026-11-03 (version 0.7.7).
Changed (8):
define_custom_blueprint: input schemadisconnect_cables: input schemaexport_deliverables: description, input schema, annotationsget_device_blueprint: input schemamodify_equipment: input schemamount_equipment: input schemaplan_external_endpoints: input schemasearch_catalog: input schemaCompared from the tool lists our read-only connection recorded, separately for each hosted endpoint and each package: each tool's name, title, description, input schema and annotations (the order of keys and of tools is ignored). We see a list only when we read it: a change is shown between the two reads where we first saw it, and anything after 2026-11-03 is not known yet. No tool was called. How it is compared
Choosing
Record checks
Public records · not a safety rating5 of 5 record checks met · 4 do not apply
- Not ranked by downloads: not an npm or PyPI package
- Not ranked by stars: 1 star (ranked from 10)
- 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.
- Does not applyPackage names its licence with a standard (SPDX) identifierNot an npm or PyPI package.
- Does not applyThe version the registry lists can be installed and is not withdrawnNot an npm or PyPI package.
- Does not applynpm package carries build provenance (attestation)PyPI packages have no npm-style attestation.
- Does not applyNo known critical or high advisory in the package or its dependenciesNot an npm or PyPI package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-03 (security policy 2026-11-02). 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, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about io.github.itAlex240/rack-architect-mcp
Answered from the data aboveWho publishes io.github.itAlex240/rack-architect-mcp?
The registry ties the namespace io.github.itAlex240 to the GitHub account itAlex240; only its owner can publish under it. Its linked repository, github.com/itAlex240/rack-architect-mcp, belongs to the same GitHub account. These are facts from the registry and GitHub, not a rating.
Is io.github.itAlex240/rack-architect-mcp safe to install?
We do not rate servers as safe or unsafe. 5 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Does io.github.itAlex240/rack-architect-mcp need an API key or sign-in?
It opened a session without any credential on 2026-11-03. The registry entry declares no required credential; no declaration is not a guarantee.
Has io.github.itAlex240/rack-architect-mcp been security tested?
Partly. 4 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.
Does io.github.itAlex240/rack-architect-mcp publish a security policy?
Yes: its repository has a public security policy (github.com/italex240/rack-architect-mcp/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.
Where is the source code of io.github.itAlex240/rack-architect-mcp?
In github.com/itAlex240/rack-architect-mcp, 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.
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
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. 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: exercised
- Fake assistant turns: exercised
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: not applicable
4 exercised11 not run (reason given)3 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 15 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 - 12Hidden content
audience-hidingChecks resources that hide content from the user.exercised - 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.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 server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.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 server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.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 - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable
Source: our own test, 2026-11-03, 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 a read-only session with the server's remote endpoint
- 1,886 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 12 tools, 4 resources, 5 prompts.
- 9,992 msFinished: 4 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.itAlex240/rack-architect-mcp: MCP server record.” Data checked 2026-11-03. https://protocolprobe.com/mcp/servers/io.github.itAlex240/rack-architect-mcp
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.itAlex240/rack-architect-mcp)
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