Trademark search
NPM · @FOREVERWORKS/MCP-TRADEMARKS
Check whether a name is already a registered or pending trademark in the US or the EU.
Available components
Last scanned (34 minutes ago)
Scores higher than 61% of npm servers
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security99
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 7 of 23 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to foreverworks/mcps). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 2 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability62
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1210 tokens (~201/item across 6 items; 6 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 Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- 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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
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.
- 4 Nov 26 +11
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → 0.88 ▲ functional
- 3 Nov 26 68
First indexed and scored.
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 5 Nov 2026 · Analysed npm/@foreverworks/mcp-trademarks@0.1.2
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | foreverworks/mcps |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/foreverworks/mcps/.github/workflows/release.yml@refs/tags/release-2026-11-03.2 |
| Rekor log index | 3658024150 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:93e0bb070fcc663055b8350cb52dff61b9cd525142b75b42d4e6c19f534fcddfc7b22371a780a9426d2f7a45a1467244c5d0d1d68311a1bc1c9249a35 |
Background: How many MCP packages publish verified provenance →
Dependencies 23 packages
| Packages resolved | 23 |
|---|---|
| Stale | 7 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
download_mark_documents Save a mark's documents as a PDF ~188
Saves the documents of a US mark's file that a type code (from mark_documents) and a date window pick, as one PDF in the server's outbox, and answers its path, SHA-256 and size. Without a filter it is the whole file, which for an old mark runs to hundreds of pages. USPTO allows 4 of these a minute.
| Name | Type | Req | Description |
|---|---|---|---|
| from | string | – | Only documents dated on or after this day. |
| id | string | yes | The USPTO serial number (8 digits), as search_marks lists it. |
| office | string | yes | US: case files come from USPTO's TSDR; other offices say where to read them. |
| to | string | – | Only documents dated on or before this day. |
| type | string | – | A document type code from mark_documents, e.g. "OOA" (an office action). |
| Name | Type | Req | Description |
|---|---|---|---|
| from | string | – | – |
| id | string | yes | – |
| office | string | yes | – |
| path | string | yes | The PDF in the server's outbox |
| sha256 | string | yes | – |
| size | integer | yes | – |
| source | string | yes | – |
| to | string | – | – |
| type | string | – | – |
No examples provided.
get_mark One trade mark's details ~119
One mark by its office and number (as search_marks lists it): status, owners, every class with its goods and services (each cut at 600 characters), the dates the office publishes (filing and registration from both; the status date and expiry from EUIPO only, USPTO's search gives neither), and the office's page.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | The office's number: a USPTO serial number (8 digits), an EUIPO application number (9, leading zeros included). |
| office | string | yes | US or EM. |
| Name | Type | Req | Description |
|---|---|---|---|
| classes | array | yes | – |
| expires | string | – | – |
| filed | string | – | – |
| goodsAndServices | array | yes | – |
| id | string | yes | – |
| kind | string | – | – |
| link | string | yes | – |
| mark | string|null | yes | – |
| office | string | yes | – |
| owners | array | yes | – |
| registered | string | – | – |
| registrationNumber | string | – | – |
| source | string | yes | – |
| status | string | yes | – |
| statusDate | string | – | – |
| statusText | string | yes | – |
| translation | string | – | – |
No examples provided.
health Health ~74
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), whether it is an official API, what `similar` means there, and the offices it cannot search with the reason. Run this before concluding the MCP is broken.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| ok | boolean | yes | – |
| records | array | yes | The sources of status histories and documents |
| sources | array | yes | – |
| uncovered | array | yes | – |
No examples provided.
mark_documents A mark's documents ~120
The documents in a US mark's file, newest first: each one's date, type code and description (an office action, a specimen, a registration certificate), whether it came in or went out, and its pages, from USPTO's TSDR. download_mark_documents saves the ones picked by type and date.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | The USPTO serial number (8 digits), as search_marks lists it. |
| office | string | yes | US: case files come from USPTO's TSDR; other offices say where to read them. |
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | yes | – |
| documents | array | yes | – |
| id | string | yes | – |
| office | string | yes | – |
| source | string | yes | – |
No examples provided.
mark_history A mark's status history ~135
Where a US mark stands and every step its file records, newest first (filed, examined, office actions, published, opposed, registered, renewed, abandoned), each with its date and USPTO's code, from USPTO's official TSDR API. Also the status in USPTO's own words with its date and code, and the filing, registration, renewal and abandonment dates.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | The USPTO serial number (8 digits), as search_marks lists it. |
| office | string | yes | US: case files come from USPTO's TSDR; other offices say where to read them. |
| Name | Type | Req | Description |
|---|---|---|---|
| abandoned | string | – | – |
| category | string | – | The office's summary, e.g. LIVE/REGISTRATION/Issued and Active |
| events | array | yes | Every step the file records, newest first |
| filed | string | – | – |
| id | string | yes | – |
| link | string | yes | – |
| mark | string|null | yes | – |
| office | string | yes | – |
| registered | string | – | – |
| registrationNumber | string | – | – |
| renewed | string | – | – |
| source | string | yes | – |
| status | string | yes | – |
| statusCode | integer | yes | – |
| statusDate | string | – | – |
| statusText | string | yes | The office's own sentence for where the mark stands |
No examples provided.
search_marks Search trademark registers for a name ~456
Is a name already a registered or pending trade mark? Searches one name in each office at once and answers per office: the marks found, closest first (identical, then containing the name, then similar, the most alike first), each with its status (registered, pending, dead), owners, Nice classes, filing date, a link to the office's page and a similarity score from 0 to 100 computed here the same way for every office (spelling and sound), plus counts per relation; goods narrows to marks whose goods and services hold given words. US is USPTO's register, EM the EU register (EUTMs and international registrations designating the EU). An office that was not searched (no source, no credentials, a failure) says so and why: never read it as clear. Not legal advice: a conflict also depends on goods and services, and no score settles similarity.
| Name | Type | Req | Description |
|---|---|---|---|
| classes | array | – | Nice classes, e.g. [9, 42] for software and SaaS. Default: every class. |
| goods | string | – | Words that must appear together in a mark's goods and services, e.g. "computer software" or "mobile application". Applied where the office's source can (US); an office that cannot says goods_filter:… |
| limit | integer | – | Marks listed per office; the counts cover every candidate examined. |
| match | string | – | 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. |
| name | string | yes | The name as it would be written. Case, accents, spaces and punctuation do not make two marks different, but a register finds by words: search a compound spaced too ("Blue Night" also finds BLUENIGHT… |
| offices | array | – | EM (EUIPO), US (USPTO), RO (OSIM), WO (WIPO). Default: all of them. |
| status | string | – | live (default): registered and pending marks only. all: dead ones too. |
| Name | Type | Req | Description |
|---|---|---|---|
| classes | array | – | – |
| goods | string | – | – |
| match | string | yes | – |
| name | string | yes | – |
| offices | array | yes | – |
| status | string | yes | – |
No examples provided.
How do I install the Trademark search MCP server?
Trademark search runs locally as an npm package, launched with npx -y @foreverworks/mcp-trademarks. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @foreverworks/mcp-trademarks
claude mcp add com-foreverworks-trademarks -- npx -y @foreverworks/mcp-trademarks
What is the Trademark search MCP server?
Trademark search is an MCP server listed in the public MCP registry as com.foreverworks/trademarks. Check whether a name is already a registered or pending trademark in the US or the EU. This page covers its npm package (@foreverworks/mcp-trademarks).
Is the Trademark search MCP server safe to use?
Trademark search scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 Trademark search MCP server expose?
Trademark search exposes 6 tools: download_mark_documents, get_mark, health, mark_documents, mark_history, search_marks. Their descriptions and schemas cost roughly 1,092 tokens of context every time the server is loaded.
Is the Trademark search MCP server still maintained?
Trademark search is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Trademark search MCP server under?
Trademark search declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.