Plan and build a physical body for your AI agent: boards, parts list, assembly and pairing.
Scored across 10 tools
Most tools have clearly distinct purposes: assess_hackability is a device lookup, get_build_plan produces a full build plan, and find vs get firmware playbooks are cleanly split. Some borderline overlap exists between assess_hackability and get_build_plan (both return device info) and between find_firmware_playbooks and find_reverse_engineering_examples (both curated search), but descriptions differentiate them.
All ten names follow a consistent snake_case verb_noun pattern (assess_, check_, find_, get_, prepare_, verify_, plan_) with object-first naming. 'intake_gadget' is the only slightly unusual verb usage but remains readable and consistent in format.
Ten tools is well within the ideal 3-15 range and each maps to a distinct stage of the workflow (assess, find, check, plan, prepare, verify). No tools appear redundant or padding the surface.
The surface covers the full research-to-prepare lifecycle: device assessment, playbook discovery, compatibility checks, build planning, firmware job prep and artifact verification. Minor gap: no standalone device catalog listing, so agents rely on assess_hackability substring matching to discover device_ids needed by get_build_plan.
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.
Inputs: device_name (required). Returns: object
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.
Inputs: observed (required), playbook_id (required). Returns: object
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.
Inputs: query (required), limit, device_id, intervention, +1 more. Returns: object
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.
Inputs: limit, query, method, category, +3 more. Returns: object
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.
Inputs: device_id (required). Returns: object
Return a curated firmware playbook with exact targets, prerequisites, backups, recovery, independent risk axes, sources, validation checks and the human-only destructive-action boundary.
Inputs: playbook_id (required). Returns: object
Return four hardware-planning intake questions covering placement, interaction, room sensing and budget, with answer options and their planning meanings. No input.
Inputs: no named parameters. Returns: object
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.
Inputs: idea, size, limit, needs, +4 more. Returns: object
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.
Inputs: observed (required), playbook_id (required), owner_authorized (required). Returns: object
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.
Inputs: sha256 (required), filename (required), source_url (required), playbook_id (required). Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Source-linked robotics projects, bills of materials and components for AI agents.
Connect your AI to your own devices, 3D printers, factory tools and a shared agent task pool.
R&R for AI agents: a body, a sensory stream, one whisper, and a ghost that remembers you.
Design circuits, simulate and verify embedded firmware, and lay out PCBs with AI agents.
Add one secure layer between your agents and this server.