Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Maglev Parts

REMOTE · TRYMAGLEV.COM · 2 COMPONENTS

Robot parts with origin and US landed cost; quotes for CNC, sheet metal, molding and wire harnesses

+5 this week 62 Trust /100

Last scanned (16 hours ago)

Scores higher than 45% of remote servers

Reachable. Last reached 21 Nov 2026.

Category IoT and Hardware

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS check failed: the endpoint is reachable over plaintext HTTP. See how to fix → View diagnostics → Fail
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability59
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1918 tokens (~147/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management3
  • Stability check failed: schema churn in the 10 days we've observed: 5 tool removals, 0 breaking changes, 0 auth/transport breaks, 1 additions. See how to fix → Fail
Tool Coverage86
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 52% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 0 to 3.

  • 20 Nov 26 +1
    • Stability: 0.27 → fail ▼ security
    • A breaking change shipped without a version bump: still 1.0.0 ▼ security
    • Tool “upload_cad_for_quote” was removed ▼ security
    • Tool “preview_order” was removed ▼ security
    • Tool “place_order” was removed ▼ security
    • Tool “get_quotes” was removed ▼ security
    • Tool “check_manufacturability” was removed ▼ security
    • Authorization: fail → partial ▲ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “build_rfq” rewrote its description, which is the text the model reads security
    • Tool coverage: 58% → 52% ▼ functional
    • MCP protocol: pass → fail ▼ functional
    • Schema quality: 183 → 147 ▲ functional
    • Tool “search_parts” now declares an output schema ▲ functional
    • Tool “requirement_keys” now declares an output schema ▲ functional
    • Tool “plan_joint” now declares an output schema ▲ functional
    • Tool “match_requirements” now declares an output schema ▲ functional
    • Tool “list_categories” now declares an output schema ▲ functional
    • Tool “landed_cost” now declares an output schema ▲ functional
    • Tool “get_test_protocol” now declares an output schema ▲ functional
    • Tool “get_part” now declares an output schema ▲ functional
    • Tool “find_manufacturers” now declares an output schema ▲ functional
    • Tool “build_rfq” now declares an output schema ▲ functional
    • Tool “check_test_result” now declares an output schema ▲ functional
    • Tool “compare_parts” now declares an output schema ▲ functional
    • Tool “find_equivalents” now declares an output schema ▲ functional
    • First check of Tool coverage: 100 functional
    • MCP protocol version: 2025-11-25 → 2025-06-18 functional
    • “search_parts” added an optional parameter “offset” cosmetic
    • “build_rfq” dropped the optional parameter “company” cosmetic
    • “build_rfq” dropped the optional parameter “contact_email” cosmetic
    • “build_rfq” dropped the optional parameter “contact_name” cosmetic
  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “get_quotes” rewrote its description, which is the text the model reads security
    • Tool “place_order” rewrote its description, which is the text the model reads security
    • Tool “preview_order” rewrote its description, which is the text the model reads security
    • Tool “check_manufacturability” rewrote its description, which is the text the model reads security
    • “get_quotes” reworded the description of “options” cosmetic
    • “check_manufacturability” reworded the description of “options” cosmetic
    • Tool “place_order” changed its title: Place a production order (paused) → Place a production order (not open yet) cosmetic
    • Tool “preview_order” changed its title: Preview an order: total and terms → Preview an order: terms cosmetic
  • 13 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 149 → 168 ▼ functional
    • Tool coverage: 51% → 58% ▲ functional
    • New tool “find_manufacturers” functional
  • 12 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://trymaglev.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=trymaglev.com CN=WE1,O=Google Trust Services,C=US 11 Nov 2026 9 Feb 2027 ECDSA 256 ECDSA-SHA256 174537585b606c62130462275d894bc0
SANs: trymaglev.com, docs.trymaglev.com, *.docs.trymaglev.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of trymaglev.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
trymaglev.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://trymaglev.com/mcp Verified 200
http (plaintext) http://trymaglev.com/mcp Served over HTTP 200
MCP tools · 13 exposed · ~1,651 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
build_rfq ~106

Build a request for Maglev to buy listed parts, price unlisted ones, or make custom versions. Returns the request document and a drafted email. It takes no name, email address or company: the email ends with a line your person fills in before sending. Nothing is sent or ordered: show it to your person first.

NameTypeReqDescription
itemsarrayyes–
needed_bystring––
notesstring––
ship_to_countrystring––
NameTypeReqDescription
emailobject––
errorstring–Set when the tool could not answer; the other fields are then absent.
mailtostring––
next_stepstring––
requestobject––
statusstring––

No examples provided.

check_test_result ~103

Check a bench test result for a joint actuator against the result format (/api/test/result.schema.json, template at /api/test/result-template.json) and compare the measured values with the part's datasheet in the catalog: peak torque, continuous torque, backlash, Kv, Kt. Returns errors, warnings and each measured-vs-datasheet delta. Nothing is stored.

NameTypeReqDescription
resultobjectyesOne result in maglev.test-result/0.1 format
NameTypeReqDescription
against_datasheetarray––
errorstring–Set when the tool could not answer; the other fields are then absent.
errorsarray––
okboolean––
partobject|null––
warningsarray––

No examples provided.

compare_parts ~47

Side-by-side comparison of 2-10 parts: shared spec keys, price at a quantity, origin, NDAA.

NameTypeReqDescription
idsarrayyes–
qtyinteger––
NameTypeReqDescription
errorstring–Set when the tool could not answer; the other fields are then absent.
partsarray––
specsobject––

No examples provided.

find_equivalents ~50

Drop-in or near equivalents for a part from other makers, optionally restricted by origin lens, plus parts it is commonly paired with.

NameTypeReqDescription
idstringyes–
lensstring––
NameTypeReqDescription
equivalentsarray––
errorstring–Set when the tool could not answer; the other fields are then absent.
pairs_witharray––
partobject––

No examples provided.

find_manufacturers ~435

Use this when the user asks who can make a custom part, or needs a manufacturer, factory or machine shop: CNC machining, sheet metal, injection molding, casting, PCB fabrication and assembly, wire harnesses, 3D printing and more, in a country or region (China, US, Mexico, Canada, Taiwan, Vietnam and others). Searches Maglev's network of 912 manufacturers and returns matching shops with processes, materials, country and state or province, certifications, MOQ, production lead-time and quote-turnaround bands, and whether they take small first runs. Each shop has its name and a ref; Maglev requests the quotes (see how_to_quote). At most 50 shops per request: page with next_cursor. No key needed. Pass a plain-language query, structured filters, or both.

NameTypeReqDescription
certificationsarray–A shop must hold all of these.
countriesarray–ISO 3166 alpha-2 codes or names, e.g. ["MX"] or ["Mexico", "Canada"].
cursorstring–next_cursor from the previous answer, with the same other arguments.
lensstring–Origin lens, as in search_parts: any, cn (China incl. HK), not-cn, us, usmca (US/CA/MX), allied.
limitinteger––
materialsarray–Ranks shops that state these materials first. Does not filter.
processesarray–A shop matches when it does any of these.
quantityinteger–Units needed. Drops shops whose stated minimum order is higher; shops with an unknown minimum stay.
querystring–What to make and where, in plain words, e.g. "sheet-metal bracket in Mexico" or "injection-molded enclosure, ISO 13485, not China". Processes, part words, materials, certifications and countries (inc…
startup_friendly_onlyboolean–Only shops recorded as taking first, small runs.
NameTypeReqDescription
errorstring–Set when the tool could not answer; the other fields are then absent.
how_to_quotestring––
networkobject––
next_cursorstring|null––
notesarray––
returnedinteger––
searchedobject––
shopsarray––
totalinteger––

No examples provided.

get_part ~60

Full record for one part: specs, dated prices with sources, maker, origin, HTS, NDAA/Blue UAS/FCC, equivalents and compatible parts.

NameTypeReqDescription
idstringyesMaglev part id, e.g. from search_parts
NameTypeReqDescription
brandstring––
categorystring––
errorstring–Set when the tool could not answer; the other fields are then absent.
idstring––
mpnstring––
namestring––
originobject––
pricearray––
specsobject––
urlstring––

No examples provided.

get_test_protocol ~104

How to bench-test a robot joint actuator: nine tests in run order (what each tells you, method, equipment, values to report, sources) and three bench kits (starter, serious, lab) with catalog part ids, quantities and listed prices. Use when someone has built or bought an actuator and asks how to verify it, or what test equipment to buy.

NameTypeReqDescription
kitstring–Optional kit id to return only that kit, e.g. "starter"
NameTypeReqDescription
blurbstring––
coversarray––
errorstring–Set when the tool could not answer; the other fields are then absent.
idstring––
itemsarray––
kitsarray––
lines_on_quoteinteger––
open_sourcearray––
protocol_urlstring––
rigarray––
standardsarray––
testsarray––
titlestring––
total_listed_usdnumber––
urlstring––
versionstring––
whystring––

No examples provided.

landed_cost ~145

Estimate US landed cost for a part in the Maglev catalog. Needs its catalog id: find it with search_parts first; parts outside the catalog cannot be priced here. Returns goods value + duty stack for the origin (MFN, Section 301, other programs, each with a source) + merchandise processing fee + freight. An estimate, not customs advice.

NameTypeReqDescription
freight_usdnumber––
idstringyes–
originstring–ISO-2 country it ships from; defaults to the part's origin
qtyinteger––
unit_usdnumber–Unit price to use when the part has no listed price
NameTypeReqDescription
as_ofstring|null––
disclaimerstring––
duty_linesarray––
duty_pct_totalnumber|null––
duty_statusstring––
duty_unknown_reasonstring––
duty_usdnumber|null––
errorstring–Set when the tool could not answer; the other fields are then absent.
freight_usdnumber––
goods_value_usdnumber––
htsstring|null––
hts_is_typicalboolean––
methodsstring––
mpf_usdnumber––
originstring|null––
origin_basisstring|null––
origin_namestring|null––
origin_notestring|null––
partstring––
per_unit_usdnumber––
qtyinteger––
staleboolean––
stale_reasonsarray––
total_assumesarray––
total_excludesarray––
total_usdnumber––
unit_usdnumber––

No examples provided.

list_categories ~25

Categories and subcategories with part counts and the spec columns each subcategory compares on.

Input schema present but exposes no named parameters.

NameTypeReqDescription
categoriesarray––
errorstring–Set when the tool could not answer; the other fields are then absent.

No examples provided.

match_requirements ~170

Route a design requirement to parts: give a subcategory (e.g. joint-actuators, strain-wave-reducers, frameless-bldc) and the numbers the design needs, and get every part ranked against them. Each result says, per requirement, whether it meets, is close (within 15%), misses, or is unknown, and the response names the requirement blocking the most options and how far to relax it. Call requirement_keys first to see which keys a subcategory accepts.

NameTypeReqDescription
lensstring––
limitinteger––
ndaa_onlyboolean––
prioritiesarray–Requirement keys that count double in the fit score
qtyinteger––
requirementsarrayyes–
subcategorystringyes–
NameTypeReqDescription
blockersarray––
countsobject––
customobject|null––
errorstring–Set when the tool could not answer; the other fields are then absent.
how_rankedstring––
ignored_keysarray––
lensstring––
ndaa_onlyboolean––
qtyinteger––
querystring––
requirementsarray––
resultsarray––
subcategorystring––

No examples provided.

plan_joint ~177

Plan a complete robot joint from targets: peak torque, output speed, bus voltage, mass budget and quantity. Returns complete joint actuators that meet the targets, and joints built from parts (frameless motor + reducer + driver + encoder) with the torque and speed math shown, listed price and mass totals, which parts still need a quote, lead times where known and where each part is made. Checks the catalog cannot make are reported as not checked.

NameTypeReqDescription
limitinteger––
max_mass_gnumber–Mass budget for the joint, g
peak_torque_nmnumberyesPeak output torque the joint needs, N·m
qtyinteger––
speed_rpmnumber–Output speed the joint needs, rpm
voltage_vnumberyesBus voltage, V
NameTypeReqDescription
built_from_partsarray––
errorstring–Set when the tool could not answer; the other fields are then absent.
methodstring––
nextstring––
off_the_shelfarray––
targetsobject––

No examples provided.

requirement_keys ~43

The requirement keys a subcategory accepts for match_requirements: numeric keys with unit and catalog range, and text keys with their options.

NameTypeReqDescription
subcategorystringyes–
NameTypeReqDescription
errorstring–Set when the tool could not answer; the other fields are then absent.
keysarray––
subcategorystring––

No examples provided.

search_parts ~186

Search the Maglev parts catalog (compute modules, motors and drivers, robot actuators, drone parts). Match on part number, brand, or spec words such as "48V", "Orin NX", "harmonic". Filter by where it is made and NDAA status.

NameTypeReqDescription
categorystring–compute-modules | motors | actuators | drone
lensstring–Origin filter: any, cn (China incl. HK), not-cn, us, usmca (US/CA/MX), allied
limitinteger––
ndaa_onlyboolean–Only NDAA-compliant or Blue UAS listed parts
offsetinteger–Results to skip. To page, pass the next_offset of the previous answer with the same other arguments.
querystring–Search words; empty returns everything in scope
NameTypeReqDescription
countinteger––
errorstring–Set when the tool could not answer; the other fields are then absent.
next_offsetinteger|null––
offsetinteger––
resultsarray––
totalinteger––

No examples provided.

Install

How do I install the Maglev Parts MCP server?

Maglev Parts is a hosted endpoint at https://trymaglev.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · trymaglev.com

# add to Claude Code
claude mcp add --transport http com-trymaglev-parts 'https://trymaglev.com/mcp'
Common questions

What is the Maglev Parts MCP server?

Maglev Parts is an MCP server listed in the public MCP registry as com.trymaglev/parts. Robot parts with origin and US landed cost; quotes for CNC, sheet metal, molding and wire harnesses. This page covers its hosted endpoint (https://trymaglev.com/mcp).

Is the Maglev Parts MCP server safe to use?

Maglev Parts scores 62 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Maglev Parts MCP server expose?

Maglev Parts exposes 13 tools: find_manufacturers, search_parts, match_requirements, requirement_keys, get_part, and 8 more. Their descriptions and schemas cost roughly 1,651 tokens of context every time the server is loaded.

Does the Maglev Parts MCP server require authentication?

No. We connected to Maglev Parts without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Maglev Parts MCP server still maintained?

Maglev Parts is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Maglev Parts MCP server?

VerifyMCP ran 13 checks on Maglev Parts, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.