# Antecedint

> Prior-art retrieval, patent-space geometry, and §112 claim validation over 10.5M US
> patent applications. Available as a REST API and as an MCP server. Every call takes
> an API key as a bearer token.

REST base URL: `https://mcp.antecedint.com/api/v1`
MCP endpoint: `https://mcp.antecedint.com/api/v1/mcp` (POST only, stateless, JSON-RPC 2.0)

For the whole reference as one document, fetch [llms-full.txt](https://antecedint.com/llms-full.txt).

For company facts, pricing and positioning — the page to quote rather than infer — read [llms-info](https://antecedint.com/llms-info).

## REST endpoints

- `POST /prior-art`: Search 10.5M US patents for prior art against a claim.
- `POST /prior-art/claims`: Fetch claim text and abstracts for specific applications.
- `GET /patent-map/patent/:appNum`: Patent position and its nearest semantic neighbours.
- `GET /patent-map/patent/:appNum/citations`: Cited prior art resolved to patent-space positions.
- `POST /patent-map/locate`: Locate free text or an application in patent space.
- `GET /patent-map/whitespace`: Ranked gaps in patent space. Free.
- `GET /patent-map/points`: Sampled background point cloud.
- `POST /claim-validation/antecedent-basis`: Check a draft claim set for antecedent-basis defects. Free.
- `GET /claim-validation/antecedent-basis/:appNum`: Check the filed claims of an application.
- `POST /claim-validation/support`: Map claim terms to their specification support.
- `GET /claim-validation/support/:appNum`: Support map for a filed application and its parents.
- `POST /warmup`: Start the inference hub ahead of a search. Free.
- `GET /warmup`: Whether the inference hub is warm. Free.
- `GET /patent-intel/cpc/:code`: CPC symbol with its art-unit distribution and children.
- `GET /patent-intel/classification/:number`: CPC classification for a publication or application number.
- `GET /patent-intel/art-unit/:artUnit`: Art-unit profile, statistics and examiner roster.
- `GET /patent-intel/examiners`: Search examiners by name or art unit.
- `GET /patent-intel/examiner/:examiner`: Examiner statistics and behavioural profile.
- `GET /guidance/mpep/:sectionId`: One MPEP section with its rules and required examiner actions.
- `GET /guidance/epo/:sectionId`: One EPO Guidelines section with its rules and citations.
- `GET /guidance/form-paragraph/:code`: One office-action form paragraph, with its statute and MPEP section.
- `GET /guidance/form-paragraphs`: Form paragraphs filtered by rejection type or MPEP section.
- `GET /guidance/graph/:nodeId`: One-hop cross-references into and out of a guidance section.
- `GET /guidance/design-code/:code`: One USPTO design search code.

## MCP tools

- `search_prior_art`: Semantic prior-art search over 10.5M+ US patents for a claim and/or abstract.
- `get_patent_claims`: Fetch full claim text and abstracts for specific US application numbers, up to 25 per call.
- `get_patent_neighborhood`: Given a US application number, return its position in Antecedint's semantic patent space plus its nearest semantic neighbors (similar patents with similarity scores).
- `get_patent_citations`: For a US application number, return its cited prior art (examiner-cited references flagged and listed first) resolved to patent-space positions.
- `locate_in_patent_space`: Semantic search into patent space: give free text (or a US application number) and get the nearest patents with similarity scores plus a landing position.
- `check_antecedent_basis`: Check a claim set for §112(b) antecedent-basis defects.
- `map_claim_support`: Map every claim term to the specification passages that give it meaning, with exact locations (section, paragraph number, char offsets).
- `find_whitespace`: List analyzed gaps ("whitespace") in patent space ranked by opportunity score.
- `lookup_cpc_code`: Look up a CPC classification symbol: what it covers, where it sits in the scheme, and which art units actually examine it.
- `get_patent_classification`: Get the CPC symbols assigned to a published application or granted patent, from the USPTO Master Classification File.
- `get_art_unit_profile`: Profile one USPTO art unit: what technology it examines, its examiner roster, and how it behaves — allowance and rejection rates, time to first action, interview receptiveness, RCE tolerance and estimated prosecution cost.
- `find_examiner`: Find USPTO examiners by surname or art unit, returning ids and names to pass to get_examiner_profile.
- `get_examiner_profile`: Statistics for one USPTO examiner, by id or by surname-first name (e.g.
- `warm_up`: Start the encoder before you need it.
- `get_mpep_section`: One MPEP section, with keyRules and examinerActions separated from the prose that obliges them.
- `get_epo_guideline`: One section of the EPO Guidelines for Examination, in the same shape as get_mpep_section because the flow that reaches it is the same flow one step later: an applicant with a US rejection usually has a European family member.
- `get_form_paragraph`: The literal paragraph an examiner pasted into an office action, by its code.
- `find_form_paragraphs`: Every form paragraph an examiner could have reached for, filtered by rejection type or by the MPEP section it rests on.
- `get_guidance_graph`: What a guidance section points at and what points at it, one hop, both directions.
- `get_design_code`: One USPTO design search code, e.g.

## Documentation

- [REST reference](https://antecedint.com/docs/api): every endpoint, with parameters, responses and curl examples.
- [MCP server](https://antecedint.com/docs/mcp): transport, authentication, limits, and the tool reference.
- [OpenAPI 3.1](https://antecedint.com/openapi.json): machine-readable REST specification.
- [How usage is counted](https://antecedint.com/docs/usage): the credit tariff, the ceilings, and the response headers.

## Research

- [Benchmarks](https://antecedint.com/docs/benchmarks): recall against BM25 and three neural baselines on a 97,913-query examiner-citation holdout, plus DAPFAM and the negative results.
- [Benchmark methodology](https://antecedint.com/docs/methodology): the standard a number has to meet before it is published, and the harness that produces it.
- [The assay doctrine](https://antecedint.com/docs/assay): what a measurement has to do before it counts as evidence.
- [How we measure prior-art retrieval](https://antecedint.com/research/how-we-measure-prior-art-retrieval) (2026-08-26): The harness behind the 45.3% recall@100 figure: where the ground truth comes from, how the holdout is split, and which experiments failed.
- [Research index](https://antecedint.com/research), and its [RSS feed](https://antecedint.com/research/feed.xml).