Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PATENTREF_BASENoBase URL of the PatentRef API.https://patentref.io
PATENTREF_API_KEYYesYour PatentRef API key, obtained from https://patentref.io/api/v1/meta/signup/. Sent by every tool except build_facts and search_disclosures.
PATENTREF_TIMEOUTNoRequest timeout in seconds.30

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

PatentRef serves the USPTO PatentsView granted-patent corpus with the PatentSearch v1 grammar plus expiry facts. check_patent_status gives record facts (status, basis, as-of date, data version) and never a legal conclusion; quote its plain sentence rather than paraphrasing it. search_patents takes the v1 q/f/s grammar (https://patentref.io/llms-full.txt). Every answer carries data_version and as_of; cite them. get_claim_tree gives one patent's claims as a tree with every span located by offsets in the claim text as published; quote the claim text at those offsets, and read its flags as notes on the text, never as a conclusion about the claims. get_patent_brief gives one patent in a fixed order cut to fit max_tokens (identity, status, each independent claim's elements with their offsets, one line per dependent claim, the claim term keys; truncated and omitted say what the budget left out); quote its text fields as given and cite a claim or element by its page and anchor (page#anchor). The rules tools (rep_required, fee_schedule, route_windows, pph_routes, ai_use_statement_required, grace_period, rules_changelog, rules_index) answer rows of office rules, each with its official source URL and a verbatim quote, plus rules_version and as_of; quote the row and its citation_url. They take an office, never an application number or a priority date, and compute no date for an application.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
check_patent_statusA

The one-call verdict for one US patent: status (active, expired_term, expired_fee_nonpayment, withdrawn, unknown), basis entries, reinstatement_possible with its 37 CFR 1.378 basis, as_of, data_version, the versioned permalink, a one-sentence plain record statement and next_steps. Record facts only.

search_patentsA

Search granted US patents with the PatentSearch v1 grammar: q is one JSON object with one key (for example {"patent_title": "laser"} or {"_and": [{"_gte": {"patent_date": "2015-01-01"}}, {"cpc_current.cpc_group_id": "H01S3/00"}]}), f the fields to return (add "lapse" for the expiry group: expiry_status, expiry_date_estimated, expiry_basis, reinstatement_possible, fee_status, lapse_date), s the sort (for example [{"patent_date": "desc"}]), size up to 1000, after the cursor from the previous page's last sort values.

similar_patentsA

The n (1 to 20) US patents nearest to a title plus abstract by FTS5 bm25 over title and abstract, with data_version and as_of. A record of what the corpus contained, not a search opinion.

get_claim_treeB

The claims of one US patent as a tree, from the claim text the USPTO published: per claim its number, category, dependency, preamble, transition, elements, term mentions with the earlier mention each "the"/"said" phrase was matched to, claim references and flags; the relations between those parts; 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). Flags describe the text and the data only. GET /api/v1/structure/claims/<patent_id>/.

get_patent_briefA

A brief of one US patent that fits max_tokens (300 to 32000, default 2000), 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, each dependent claim on one line, and the claim term keys; the first item that does not fit ends the brief, and truncated and omitted say what was left out. tokens counts the answer by the stated proxy in tokenizer (UTF-8 bytes / 3, rounded up), never over max_tokens. Every claim and element carries anchor: page + "#" + anchor opens it on the record page. Quotes are the claim text as published. GET /api/v1/structure/brief/<patent_id>/?max_tokens=.

rep_requiredA

Representation rules of a patent office (office: US, EP, CN, JP, KR, AU, or PCT for the international phase): whether and when an applicant must act through a registered agent, each row with its official source and quote. act keeps the rows of one act of the vocabulary (rules_index lists it).

fee_scheduleA

Official fees of a patent office in force on as_of (YYYY-MM-DD, default today UTC): filing, search, examination, grant, renewal and other fees with their currency, each row with its official source and quote.

route_windowsB

Generic windows of a patent office, such as the PCT national phase time limit in months from the priority date. Never a last day for a specific application; it takes no application number or date.

pph_routesB

Patent Prosecution Highway rows of to_office whose cited source names from_office as a partner office.

ai_use_statement_requiredB

Rows on whether a patent office requires a statement on the use of AI. An empty answer means the dataset holds no cited rule for that office; nothing follows from its absence.

grace_periodB

What the cited law of an office says about disclosures before filing (the grace period). Citations only: it does not say whether any disclosure falls inside the period.

rules_changelogB

The rules dataset's releases, newest first, after since (a version x.y.z or a date YYYY-MM-DD).

rules_indexB

The rules dataset: its version and date, the offices with their row counts, the tools and the act vocabulary.

build_factsC

The build in service: data_version, as_of, refreshed_at, snapshot hash, superseded versions, table delta.

search_disclosuresA

Public records of the PatentRef registry (dated technical disclosures) whose title or abstract match q (web search syntax: words, "a phrase", -word, or), newest first, up to 20. Each record carries its permalink (https://patentref.io/r/), 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.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.5/5.0

Scored across 15 tools

Disambiguation4/5

The rule-lookup tools (rep_required, fee_schedule, route_windows, pph_routes, ai_use_statement_required, grace_period) each target a clearly different topic, and search_patents vs similar_patents vs search_disclosures are well separated. The main overlaps are get_claim_tree vs get_patent_brief (both return one US patent's claims with offsets/anchors) and the three metadata tools (rules_index, rules_changelog, build_facts), which all expose version/as_of information and could be mispicked.

Naming Consistency4/5

All names are snake_case and readable, with a clear internal split between verb-prefixed action tools (get_claim_tree, get_patent_brief, check_patent_status, search_patents, search_disclosures, build_facts) and bare-noun rule queries (fee_schedule, grace_period, rep_required). Mixing verb-first and noun-only conventions is a minor deviation but predictable within each group.

Tool Count5/5

15 tools is well within the comfortable range and each maps to a distinct data surface (patent structure, status, search, similarity, office rules, disclosures, dataset metadata). No obvious filler or trivially redundant tool.

Completeness4/5

Core lifecycle looks covered: search, status verdict with reinstatement basis, claim tree and brief, similarity, plus a rich office-rules surface with sourcing and a changelog. Gaps remain around non-US patent structure (claim tools are US-only), citations/family/applicant lookups, and full description text, but agents can work around these for the stated scope.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues