# PatentRef (pypi · patentref-mcp)

PatentsView-compatible US patent API: claim trees, patent briefs and search, grants 1976 to now.

- Trust score: 61/100 (medium)
- Change this week: −12
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- pypi · `patentref-mcp`: 61/100 (this document), [markdown](https://verifymcp.io/servers/patentref-patentref-mcp/patentref-mcp.md), [page](https://verifymcp.io/servers/patentref-patentref-mcp/patentref-mcp)

## Channel facts

- Registry: `pypi`
- Package: `patentref-mcp`
- Version: `0.4.1`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 0 of 28 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 9 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3980 tokens (~265/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the PatentRef MCP server?

PatentRef runs locally as a PyPI package, launched with uvx patentref-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add patentref-patentref-mcp -- uvx patentref-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "patentref-patentref-mcp": {
      "command": "uvx",
      "args": [
        "patentref-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "patentref-patentref-mcp": {
      "command": "uvx",
      "args": [
        "patentref-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add patentref-patentref-mcp -- uvx patentref-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "patentref-patentref-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "patentref-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add patentref-patentref-mcp --command uvx --arg patentref-mcp
```

### Hermes

```yaml
mcp_servers:
  patentref-patentref-mcp:
    command: "uvx"
    args: ["patentref-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "patentref-patentref-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "patentref-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add patentref-patentref-mcp -t stdio -c uvx -a patentref-mcp
```

### Other

```json
{
  "mcpServers": {
    "patentref-patentref-mcp": {
      "command": "uvx",
      "args": [
        "patentref-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 61, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-19 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 75, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-17 (score 60, −14)

- [security regression] Malware scan: pass → unverified

### 2026-11-15 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 73, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-11 (score 57, +11)

- [security improvement] Source repository: fail → pass
- [functional regression] Security disclosure: unverified → fail
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 0% → 100%
- [functional improvement] Stability: unverified → 0.20
- [functional] Schema quality: good → excellent
- [functional] Package version: 0.4.0 → 0.4.1

### 2026-11-10 (score 46, −15)

- [security regression] Malware scan: pass → unverified

## MCP tools (15)

### `check_patent_status` (~254 tokens)

Patent status record

Get the expiry and maintenance-fee status record of one granted US patent: status (active, expired_term, expired_fee_nonpayment, withdrawn or unknown), its basis, reinstatement_possible with its legal basis, as_of, data_version, a versioned permalink, a one-sentence `plain` statement and next_steps. Record facts, not a legal opinion. Use it for one known patent number; use search_patents with the "lapse" field group for the status of many patents at once, and get_patent_brief for the claims together with the status. Read only. Needs PATENTREF_API_KEY; each call uses one request of the key's allowance (1,000 a month on a free key). API errors (400 bad argument, 403 missing or unknown key, 404 not found, 429 over the allowance) come back as the tool error with the HTTP status and reason, with no retry.

Input parameters:

- `patent_id` (string, required): A granted US patent number as PatentsView prints it, for example 10000000, D872010, RE31177 or PP36776. A US prefix and lower case are accepted; no commas or spaces inside the number.

### `search_patents` (~499 tokens)

Search US patents

Search granted US patents by field values with the PatentSearch v1 query grammar and return the matching rows, a page at a time. Use it to find patents by title words, dates, CPC class, assignee, inventor or other fields; use similar_patents to rank patents by closeness to a passage of text, check_patent_status for one known number, and search_disclosures for PatentRef registry records rather than patents. Query operators: _eq, _neq, _gt, _gte, _lt, _lte, _begins, _contains, _text_all, _text_any, _text_phrase, _and, _or, _not; dotted names reach nested fields. The "lapse" field group adds expiry_status, expiry_date_estimated, expiry_basis, reinstatement_possible, fee_status and lapse_date. For the next page, pass the last row's sort values as after. Field names and the full grammar: https://patentref.io/llms-full.txt. Read only. Needs PATENTREF_API_KEY; each call uses one request of the key's allowance (1,000 a month on a free key). API errors (400 bad argument, 403 missing or unknown key, 404 not found, 429 over the allowance) come back as the tool error with the HTTP status and reason, with no retry.

Input parameters:

- `after`: The paging cursor: the sort values of the last row of the previous page. Omitted: the top of the list.
- `f`: The fields to return, for example ["patent_id", "patent_title", "patent_date"]; add "lapse" for the expiry fields. Omitted: the API's default fields.
- `q` (object, required): The query: one JSON object with exactly one key, for example {"patent_title": "laser"} or {"_and": [{"_gte": {"patent_date": "2015-01-01"}}, {"cpc_current.cpc_group_id": "H01S3/00"}]}.
- `s`: The sort, a list of {field: "asc" or "desc"}, for example [{"patent_date": "desc"}]. Omitted: the API's default order.
- `size` (integer): Rows per page, 1 to 1000; a value outside that range is moved to the nearest limit.

### `similar_patents` (~249 tokens)

Patents similar to a text

Rank granted US patents by how close their title and abstract are to a passage of text, and return the n nearest with data_version and as_of. Use it when you have a description, an abstract or a claim and want related patents; use search_patents for exact filters such as dates, classes or names. The ranking is full-text bm25 over titles and abstracts, searched with the rarest words of the text, so the answer is a record of what the data holds, not a search opinion. Read only. Needs PATENTREF_API_KEY; each call uses one request of the key's allowance (1,000 a month on a free key). API errors (400 bad argument, 403 missing or unknown key, 404 not found, 429 over the allowance) come back as the tool error with the HTTP status and reason, with no retry.

Input parameters:

- `n` (integer): How many patents to return, 1 to 20; a value outside that range is moved to the nearest limit.
- `text` (string, required): The passage to match, for example a title and abstract, or a claim; up to 4,000 characters, the rest is cut.

### `get_claim_tree` (~297 tokens)

Claim tree of a patent

Get every claim of one granted US patent as a tree parsed from the claim text the USPTO published: per claim its number, category, dependency, preamble, transition, elements, term mentions (each "the" or "said" phrase linked to its earlier mention), claim references and flags, with structure_version, data_version, text_data_version and as_of. Every part carries start and end offsets into its claim's text (text[start:end] is the part). Use it when you need all claims in full detail; use get_patent_brief for a shorter answer that fits a token budget, and check_patent_status for the status alone. Flags are notes on the text and the data, not conclusions about the claims. A patent without claim text in the data answers 404. Read only. Needs PATENTREF_API_KEY; each call uses one request of the key's allowance (1,000 a month on a free key). API errors (400 bad argument, 403 missing or unknown key, 404 not found, 429 over the allowance) come back as the tool error with the HTTP status and reason, with no retry.

Input parameters:

- `patent_id` (string, required): A granted US patent number as PatentsView prints it, for example 10000000, D872010, RE31177 or PP36776. A US prefix and lower case are accepted; no commas or spaces inside the number.

### `get_patent_brief` (~339 tokens)

Patent brief within a token budget

Get a brief of one granted US patent that fits a token budget, in a fixed order: identity and dates, the status record with its basis, each independent claim as its elements with start and end offsets into the claim text, one line per dependent claim, and the claim term keys. The brief stops at the item that would go over max_tokens; truncated and omitted say what was left out, and tokens gives its size, never over max_tokens. Every claim and element carries an anchor: page + "#" + anchor opens it on the record page. Quotes are the claim text as published. Use it to read or summarize a patent within a context budget; use get_claim_tree for all claims in full structure, and check_patent_status for the status alone. Read only. Needs PATENTREF_API_KEY; each call uses one request of the key's allowance (1,000 a month on a free key). API errors (400 bad argument, 403 missing or unknown key, 404 not found, 429 over the allowance) come back as the tool error with the HTTP status and reason, with no retry.

Input parameters:

- `max_tokens` (integer): The token budget, 300 to 32000, counted as the UTF-8 bytes of the answer / 3, rounded up; a value outside that range is moved to the nearest limit.
- `patent_id` (string, required): A granted US patent number as PatentsView prints it, for example 10000000, D872010, RE31177 or PP36776. A US prefix and lower case are accepted; no commas or spaces inside the number.

### `rep_required` (~222 tokens)

Office representation rules

List the representation rules of a patent office: whether and when an applicant must act through a registered agent, each row with its official source URL and a verbatim quote. Use it for questions about needing a local agent; use fee_schedule for fees, route_windows for time limits, and rules_index for the offices and the act vocabulary. office takes US, EP, CN, JP, KR, AU or PCT. Read only. Needs PATENTREF_API_KEY; each call uses one request of the key's allowance (1,000 a month on a free key). API errors (400 bad argument, 403 missing or unknown key, 404 not found, 429 over the allowance) come back as the tool error with the HTTP status and reason, with no retry.

Input parameters:

- `act`: One act of the representation vocabulary that rules_index lists. Omitted: every act.
- `office` (string, required): The patent office code: US, EP, CN, JP, KR, AU, or PCT for the international phase. Lower case is accepted.

### `fee_schedule` (~247 tokens)

Office fee schedule

List the official fees of a patent office in force on a date: filing, search, examination, grant, renewal and other fees with their amounts, currency and entity tiers as the cited schedule prints them, each row with its official source URL and a verbatim quote. A row is in force when effective_from <= as_of < effective_to. Use it for what an office charges; use rep_required for agent rules and route_windows for time limits. office takes US, EP, CN, JP, KR, AU or PCT. Read only. Needs PATENTREF_API_KEY; each call uses one request of the key's allowance (1,000 a month on a free key). API errors (400 bad argument, 403 missing or unknown key, 404 not found, 429 over the allowance) come back as the tool error with the HTTP status and reason, with no retry.

Input parameters:

- `as_of`: The date the fees apply on, YYYY-MM-DD. Omitted: today (UTC).
- `office` (string, required): The patent office code: US, EP, CN, JP, KR, AU, or PCT for the international phase. Lower case is accepted.

### `route_windows` (~219 tokens)

Office time windows

List the generic time windows of a patent office, such as the PCT national phase time limit in months from the priority date, each row with its official source URL and a verbatim quote. Use it to learn how long a period an office allows; it never computes a last day for a specific application and takes no application number or date. Use fee_schedule for fees and pph_routes for Patent Prosecution Highway routes. office takes US, EP, CN, JP, KR, AU or PCT. Read only. Needs PATENTREF_API_KEY; each call uses one request of the key's allowance (1,000 a month on a free key). API errors (400 bad argument, 403 missing or unknown key, 404 not found, 429 over the allowance) come back as the tool error with the HTTP status and reason, with no retry.

Input parameters:

- `office` (string, required): The patent office code: US, EP, CN, JP, KR, AU, or PCT for the international phase. Lower case is accepted.

### `pph_routes` (~262 tokens)

Patent Prosecution Highway routes

List the Patent Prosecution Highway (PPH) rows of to_office whose cited source names from_office as a partner office, each with its official source URL and a verbatim quote, and to_office_pph_rows, the number of PPH rows held for to_office. Use it to see whether work done at one office can support a PPH request at another; use route_windows for time limits. An empty list means no PPH row of to_office names from_office. Read only. Needs PATENTREF_API_KEY; each call uses one request of the key's allowance (1,000 a month on a free key). API errors (400 bad argument, 403 missing or unknown key, 404 not found, 429 over the allowance) come back as the tool error with the HTTP status and reason, with no retry.

Input parameters:

- `from_office` (string, required): The office whose work product the PPH request relies on: US, EP, CN, JP, KR, AU or PCT. Lower case is accepted.
- `to_office` (string, required): The office the PPH request is filed with: US, EP, CN, JP, KR, AU or PCT. Lower case is accepted.

### `ai_use_statement_required` (~210 tokens)

Office AI-use statement rules

List the rows on whether a patent office requires a statement on the use of AI, each with its official source URL and a verbatim quote. An empty answer means the data holds no cited rule for that office; nothing follows from its absence. Use it for AI-use statement rules; use rep_required, fee_schedule or grace_period for the other rules of an office. office takes US, EP, CN, JP, KR, AU or PCT. Read only. Needs PATENTREF_API_KEY; each call uses one request of the key's allowance (1,000 a month on a free key). API errors (400 bad argument, 403 missing or unknown key, 404 not found, 429 over the allowance) come back as the tool error with the HTTP status and reason, with no retry.

Input parameters:

- `office` (string, required): The patent office code: US, EP, CN, JP, KR, AU, or PCT for the international phase. Lower case is accepted.

### `grace_period` (~217 tokens)

Office grace period law

List what the cited law of a patent office says about disclosures made before filing (the grace period), each row with its official source URL and a verbatim quote. Citations only: it does not say whether any disclosure falls inside the period. Use it to read an office's grace period text; use search_disclosures to find dated public disclosures in the PatentRef registry, and route_windows for other time limits. office takes US, EP, CN, JP, KR, AU or PCT. Read only. Needs PATENTREF_API_KEY; each call uses one request of the key's allowance (1,000 a month on a free key). API errors (400 bad argument, 403 missing or unknown key, 404 not found, 429 over the allowance) come back as the tool error with the HTTP status and reason, with no retry.

Input parameters:

- `office` (string, required): The patent office code: US, EP, CN, JP, KR, AU, or PCT for the international phase. Lower case is accepted.

### `rules_changelog` (~172 tokens)

Rules data changelog

List the releases of the patent office rules data from newest to oldest, each with its version, date and the rows it added, closed, changed or removed. Use it to see what changed since a version or date you used before; use rules_index for the current version, the offices and the vocabulary. Read only. Needs PATENTREF_API_KEY; each call uses one request of the key's allowance (1,000 a month on a free key). API errors (400 bad argument, 403 missing or unknown key, 404 not found, 429 over the allowance) come back as the tool error with the HTTP status and reason, with no retry.

Input parameters:

- `since`: A version x.y.z or a date YYYY-MM-DD; only releases after it are listed. Omitted: every release.

### `rules_index` (~156 tokens)

Rules data index

Describe the patent office rules data: its version and as_of date, the offices it holds with their row counts by rule kind, each rules tool with its parameters, and the act vocabulary. Call it before the other rules tools to learn which offices and act values exist; use rules_changelog for the history of changes. Takes no arguments, so nothing can be filtered here. Read only. Needs PATENTREF_API_KEY; each call uses one request of the key's allowance (1,000 a month on a free key). API errors (400 bad argument, 403 missing or unknown key, 404 not found, 429 over the allowance) come back as the tool error with the HTTP status and reason, with no retry.

### `build_facts` (~132 tokens)

Data build facts

Get the facts of the patent data build the API serves now: data_version, as_of, refreshed_at, the snapshot hash, superseded versions and the table delta. Use it to cite or check which data an answer came from, or to see when the data was last refreshed; it holds no patent data (use search_patents or check_patent_status) and no rules data (use rules_index). Takes no arguments. Read only. Sends no API key, so it uses none of a key's allowance. API errors come back as the tool error with the HTTP status and reason, with no retry.

### `search_disclosures` (~192 tokens)

Search registry disclosures

Search the public records of the PatentRef registry (dated technical disclosures) whose title or abstract match q, from newest to oldest, up to 20. Each record carries its permalink (https://patentref.io/r/ and the record's id), server_time, bundle_hash and proof_status; the submitter's text is inside user_content, as entered. A record shows what was published and when, not a patent or an opinion. Use it to find disclosures; use search_patents or similar_patents to find patents. Read only. Sends no API key, so it uses none of a key's allowance. API errors come back as the tool error with the HTTP status and reason, with no retry.

Input parameters:

- `q` (string, required): Web search syntax: words, "a phrase", -word to leave a word out, or between alternatives; up to 200 characters, the rest is cut.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/patentref-patentref-mcp/patentref-mcp#diagnostics

## Score history

- 2026-11-21: 61
- 2026-11-20: 76
- 2026-11-19: 76
- 2026-11-18: 75
- 2026-11-17: 60
- 2026-11-16: 74
- 2026-11-15: 74
- 2026-11-14: 73
- 2026-11-13: 73
- 2026-11-12: 57
- 2026-11-11: 57
- 2026-11-10: 46
- 2026-11-09: 61
- 2026-11-08: 46
- 2026-11-07: 61
- 2026-11-06: 61
- 2026-11-05: 38

## Common questions

### What is the PatentRef MCP server?

PatentRef is an MCP server listed in the public MCP registry as io.github.patentref/patentref-mcp. PatentsView-compatible US patent API: claim trees, patent briefs and search, grants 1976 to now. This page covers its PyPI package (patentref-mcp).

### Is the PatentRef MCP server safe to use?

PatentRef scores 61 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. 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 PatentRef MCP server expose?

PatentRef exposes 15 tools: check_patent_status, search_patents, similar_patents, get_claim_tree, get_patent_brief, and 10 more. Their descriptions and schemas cost roughly 3,667 tokens of context every time the server is loaded.

### Is the PatentRef MCP server still maintained?

PatentRef 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 licence is the PatentRef MCP server under?

PatentRef declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the PatentRef MCP server?

VerifyMCP ran 15 checks on PatentRef, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about PatentRef: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/patentref-mcp/
- Socket report: https://socket.dev/pypi/package/patentref-mcp
- Repository: https://github.com/patentref/patentref-mcp
- Website: https://patentref.io/docs/
- Changelog RSS feed: https://verifymcp.io/servers/patentref-patentref-mcp/patentref-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/patentref-patentref-mcp/patentref-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/patentref-patentref-mcp/patentref-mcp.json
- HTML version of this page: https://verifymcp.io/servers/patentref-patentref-mcp/patentref-mcp
