Name: Trademark search
Author: foreverworks

Trademark search MCP

Check whether a name is already a registered or pending trademark in the US or the EU.

Grade A Local · stdio No auth needed 6 tools v0.1.2 MIT

No reviews yet by foreverworksnpm Runs on your machine, nothing hosted

100/100

trust score

tools declared

local

runs on your machine

—

downloads a day

What it does

Check whether a name is already a registered or pending trademark in the US or the EU.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user trademark-search-mcp '--' npx -y @foreverworks/mcp-trademarks

# 2 — ask your agent for something these tools do
#   health, search_marks, get_mark and 3 more

Trademark search costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publisher

foreverworks15 servers

8 categories

All 15 servers

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Trademark search as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user trademark-search-mcp '--' npx -y @foreverworks/mcp-trademarks

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

Nothing is required, but it can take USPTO_TSDR_API_KEY_FILE (For US mark histories and documents: path of a file holding a USPTO TSDR API key.), EUIPO_CLIENT_ID_FILE (For EU marks: path of a file holding the EUIPO app's client id.), EUIPO_CLIENT_SECRET_FILE (For EU marks: path of a file holding the EUIPO app's client secret.) if you want to set them.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

6 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

Which trademark registers this server can search right now: each source's state (ok, not_configured with what it needs, pending while the register approves access, failing),

No parameter schema on file.

Is a name already a registered or pending trade mark? Searches one name in each office at once and answers per office:

Parameter	Type	Required	Notes
name	string	yes	—
offices	array	no	EM (EUIPO), US (USPTO), RO (OSIM), WO (WIPO). Default: all of them.
classes	array	no	Nice classes, e.g. [9, 42] for software and SaaS. Default: every class.
goods	string	no	—
match	string	no	exact: the mark is the name. word: it contains the name. similar (default): also what sounds alike or is a letter off, where the office's source can tell.
status	string	no	live (default): registered and pending marks only. all: dead ones too.
limit	integer	no	Marks listed per office; the counts cover every candidate examined.

One mark by its office and number (as search_marks lists it): status, owners, every class with its goods and services

Parameter	Type	Required	Notes
office	string	yes	US or EM.
id	string	yes	The office's number: a USPTO serial number (8 digits), an EUIPO application number (9, leading zeros included).

Where a US mark stands and every step its file records, newest first (filed, examined, office actions, published,

Parameter	Type	Required	Notes
office	string	yes	US: case files come from USPTO's TSDR; other offices say where to read them.
id	string	yes	The USPTO serial number (8 digits), as search_marks lists it.

The documents in a US mark's file, newest first: each one's date, type code and description (an office action, a

Parameter	Type	Required	Notes
office	string	yes	US: case files come from USPTO's TSDR; other offices say where to read them.
id	string	yes	The USPTO serial number (8 digits), as search_marks lists it.

Saves the documents of a US mark's file that a type code (from mark_documents) and a date window pick, as one PDF

Parameter	Type	Required	Notes
office	string	yes	US: case files come from USPTO's TSDR; other offices say where to read them.
id	string	yes	The USPTO serial number (8 digits), as search_marks lists it.
type	string	no	A document type code from mark_documents, e.g. "OOA" (an office action).
from	string	no	Only documents dated on or after this day.
to	string	no	Only documents dated on or before this day.

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Trademark search or to call it, at any volume.

ATrust score 100 / 100

Release 0.1.2 · scanned 3 Nov 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score100

Findings0 threat · 0 capability

Capabilityminimal

Coveragesource

Verificationsource

Surface digest7fb75a1715d2ed8496e577a693c94fa5621ce2c238b4ef889f4b66977407dcc7

Score vectorthreat 100 → client 100

Term	Level	What it prices	Points
capability-exposure	minimal	capability blast radius (minimal) — client exposure if the model is manipulated	−0
verification-discount	source	publisher verification (provenance) — cryptographic build provenance ties the artifact to its source	−0
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (6 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.

Tool	Capability tags	Why the tag was assigned
health	no tags
search_marks	no tags
get_mark	no tags
mark_history	no tags
mark_documents	no tags
download_mark_documents	untrusted-input	untrusted-input: keyword "download"

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digest7fb75a1715d2ed84

Scanned2026-11-03

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.