hackshop MCP server
dev.hackshop/hackshop-mcphackshop.devstreamable-httpv0.0.6Scanned
Plan and build a physical body for your AI agent: boards, parts list, assembly and pairing.
10 tools: 4 change things and 6 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the hackshop MCP server can do
The hackshop MCP server is published by hackshop.dev, a domain the MCP Registry verified. It has 10 tools. It can create or change data (4 tools: plan_gadget, assess_hackability, check_firmware_compatibility and prepare_firmware_job), but cannot delete data. 6 tools only read.
1 tool brings in text other people can write (verify_firmware_artifact).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 0.0.6.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
10 tools
Changes things 4Claude Code: ask
assess_hackabilityLook up a device by id, exact name or substring and return hackability, brick risk, firmware links, curated firmware playbooks, community size, build page and agent platform suppor…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Look up a device by id, exact name or substring and return hackability, brick risk, firmware links, curated firmware playbooks, community size, build page and agent platform support. Input: `device_name` 1-200 chars.
Annotations the server declares
- title: Assess hackability
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_firmware_compatibilityFail-closed compatibility check for one firmware playbook.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Fail-closed compatibility check for one firmware playbook. Required model, codename, revision, SoC or firmware identifiers must exactly match a curated target; missing facts return unknown and mismatches return unsupported.
Annotations the server declares
- title: Check firmware compatibility
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
plan_gadgetDeterministically plan a physical body for an AI agent using Meta Muse boards.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Deterministically plan a physical body for an AI agent using Meta Muse boards. Partial intake answers produce remaining questions and an intake completion status. Inputs: `idea` 3-2000 chars (optional when `answers` or `needs` are given); `answers` {size, interaction, sensing, budget} using the intake option values; `platform` one of muse-esp32, muse-linux, any (default any); `budget_usd` number greater than 0, up to 100000; `owned_device_ids` up to 50 catalog ids; `needs` values: voice, screen, images, touch, camera, air-sensors, e-ink, battery, round, home-tunnel, big-screen, compute, linux; `size` one of pocket, desk, wall, hidden, any (default any); `limit` 1-5 (default 3). Boards that meet the hard needs and the budget rank first, cheapest first. Returns fit, notes, warnings, intake status, questions, picks with difficulty, terms and next steps.
Annotations the server declares
- title: Plan a Muse gadget
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
prepare_firmware_jobPrepare a non-executing firmware manifest after owner authorization and an exact compatibility match.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Prepare a non-executing firmware manifest after owner authorization and an exact compatibility match. Returns backup, recovery, sources, validation and stop points; never returns a flash command.
Annotations the server declares
- title: Prepare a firmware job manifest
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 6Show 6 read-only tools
find_firmware_playbooksFind curated owner-authorized firmware, local-protocol and cloud-replacement playbooks.No findings
Why it is in this group
- The name "find_firmware_playbooks" says "find": a word for reading.
Description, as the server wrote it Find curated owner-authorized firmware, local-protocol and cloud-replacement playbooks. Results rank less-invasive paths first and contain research guidance rather than device compatibility approval.
Annotations the server declares
- title: Find firmware playbooks
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
find_reverse_engineering_examplesSearch Hackshop's curated hardware reverse-engineering examples and research methods.No findings
Why it is in this group
- The name "find_reverse_engineering_examples" says "find": a word for reading.
Description, as the server wrote it Search Hackshop's curated hardware reverse-engineering examples and research methods. With no query, returns the newest dated examples first. Evidence labels distinguish reproduced work, documented implementations, author demos and analysis methods; they do not imply compatibility with similar-looking hardware.
Annotations the server declares
- title: Find reverse-engineering examples
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_build_planReturn the complete deterministic build plan for a catalog device id: difficulty, board-specific flash warnings, parts, shopping list with buy_options, prices checked date and purc…No findings
Why it is in this group
- The name "get_build_plan" says "get": a word for reading.
Description, as the server wrote it Return the complete deterministic build plan for a catalog device id: difficulty, board-specific flash warnings, parts, shopping list with buy_options, prices checked date and purchase policy, steps, machine-readable assembly with verify checks, commands, links, caveats and an agent-ready brief. Input: `device_id` 1-200 chars.
Annotations the server declares
- title: Get a build plan
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_firmware_playbookReturn a curated firmware playbook with exact targets, prerequisites, backups, recovery, independent risk axes, sources, validation checks and the human-only destructive-action bou…No findings
Why it is in this group
- The name "get_firmware_playbook" says "get": a word for reading.
Description, as the server wrote it Return a curated firmware playbook with exact targets, prerequisites, backups, recovery, independent risk axes, sources, validation checks and the human-only destructive-action boundary.
Annotations the server declares
- title: Get a firmware playbook
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
intake_gadgetReturn four hardware-planning intake questions covering placement, interaction, room sensing and budget, with answer options and their planning meanings.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return four hardware-planning intake questions covering placement, interaction, room sensing and budget, with answer options and their planning meanings. No input.
Annotations the server declares
- title: Get the intake questions
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
verify_firmware_artifactCompare a caller-supplied filename, source URL and SHA-256 with Hackshop's curated metadata.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "compare": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "compare" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Compare a caller-supplied filename, source URL and SHA-256 with Hackshop's curated metadata. Hackshop does not fetch, upload or redistribute the artifact; absent hashes return unknown.
Annotations the server declares
- title: Verify firmware artifact metadata
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:52 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.hackshop.dev/mcp: tools/list returned 10 tools to an anonymous client, including plan_gadget (write), assess_hackability (write), check_firmware_compatibility (write), prepare_firmware_job (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools10 changed.~10 changedView diff
- Changed:assess_hackabilityChanges thingsannotations
- Changed:check_firmware_compatibilityChanges thingsannotations
- Changed:find_firmware_playbooksOnly readsdescriptionannotations
- Changed:find_reverse_engineering_examplesOnly readsannotations
- Changed:get_build_planOnly readsannotations
- Changed:get_firmware_playbookOnly readsannotations
- Changed:intake_gadgetOnly readsdescriptionannotations
- Changed:plan_gadgetChanges thingsdescriptionannotations
- Changed:prepare_firmware_jobChanges thingsannotations
- Changed:verify_firmware_artifactOnly readsannotations
Install
Pinned to version 0.0.6. Values in angle brackets are yours to fill in.
claude mcp add --transport http hackshop https://www.hackshop.dev/mcpclaude mcp add --transport http hackshop https://www.hackshop.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__hackshop__intake_gadget",
"mcp__hackshop__get_build_plan",
"mcp__hackshop__find_reverse_engineering_examples",
"mcp__hackshop__find_firmware_playbooks",
"mcp__hackshop__get_firmware_playbook",
"mcp__hackshop__verify_firmware_artifact"
],
"ask": [
"mcp__hackshop__plan_gadget",
"mcp__hackshop__assess_hackability",
"mcp__hackshop__check_firmware_compatibility",
"mcp__hackshop__prepare_firmware_job"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as hackshop. Review it before you use it.
Capability tags behind 1 rule
- mcp__hackshop__verify_firmware_artifact untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.hackshop/hackshop-mcp/verify?hash=d6f57760c849fb6fda38678d6e3b70e5e763509a2a7a1be352c9f310ccfb9711" | jq -e '.changed == false'Pinned hash d6f57760c849, from Nov 15, 2026, 02:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.hackshop/hackshop-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.hackshop/hackshop-mcp)Source: MCP Registry. Synced Oct 21, 2026, 18:11 UTC.
hackshop MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the hackshop MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 4 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the hackshop MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the hackshop MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the hackshop MCP server have?
- 10 tools: 4 write, 6 read. plan_gadget, assess_hackability, check_firmware_compatibility, prepare_firmware_job, intake_gadget, get_build_plan, find_reverse_engineering_examples, find_firmware_playbooks and 2 more.
Does the hackshop MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the hackshop MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the hackshop MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 1, 2026. Every change is on this page and in its Atom feed.