For Agents
Look up the live status, prosecution history, office actions, ownership, maintenance, and PTAB challenges of US patents and applications, resolve companies to patent portfolios, and set monitors that fire webhooks on new events.
Use for: Check whether patent 10123456 is still in force, I need to see the latest office action on application 16123456, Find all pending applications owned by a named company, List the PTAB challenges filed against a competitor's patent
Not supported: Does not file patent applications, cover non-US patent offices, or handle trademark records. Use for reading US patent and application status, prosecution, ownership, and PTAB data only.
The Patent Status API returns the current status of US patent applications and granted patents from its own copy of USPTO bulk data, in compact JSON with stable field names. It covers prosecution timelines, office actions with text, ownership assignments, maintenance fees and expiration, PTAB challenges, and patent claims and citations. Company and inventor names resolve to entity ids with portfolio statistics, examiner and art-unit allowance rates are available, and monitors send webhooks when watched applications, patents, or entities change. Every object carries a source block naming the USPTO bulk file it came from plus as_of and stale freshness flags.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Patent Status API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fpatentdata.ai%2Fpatentdata" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fpatentdata.ai%2Fpatentdata" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Patent Status API.
Check the current status of a US application, granted patent, or pre-grant publication by its number
Read an application's prosecution timeline and office actions, optionally with the examiner's rejection text via include_text
Look up ownership assignments for a patent or application, or search assignments received by an assignee since a recorded_after date
Confirm whether a patent is still alive from its maintenance fee record and expiration
Resolve a company or inventor name to an entity id and pull its applications, granted patents, and portfolio stats
Find PTAB proceedings against a patent or search them by petitioner, patent_owner, or status
Watch applications, patents, or entities with a monitor that posts events to your webhook_url
Patterns agents use Patent Status API for, with concrete tasks.
★ Agent patent status checks through Jentic
A legal or IP research agent finds the Patent Status operations through Jentic by intent, then calls GET /v1/applications/{application_number} or GET /v1/patents/{patent_number} for the current status, and follows up with transactions or office actions for detail. Each response includes the USPTO source file and a stale flag, so the agent can tell how fresh the answer is. Jentic injects the key at call time, so the agent never handles it.
Call GET /v1/applications/16123456 to read its status, then GET /v1/applications/16123456/transactions with since '2026-01-01' to list new prosecution events
Competitor portfolio research
Resolve a company name to an entity id with GET /v1/entities/search, then read GET /v1/entities/{entity_id}/stats for portfolio size, velocity, technology mix, examiners, PTAB exposure, and deals. GET /v1/entities/{entity_id}/applications with a status filter lists the pending pipeline, and GET /v1/entities/{entity_id}/patents lists granted patents, giving an analyst a portfolio picture without bulk-file processing.
Call GET /v1/entities/search with q 'Acme Robotics' and type company, take the top entity id, then GET /v1/entities/{entity_id}/applications with status 'pending'
Freedom-to-operate and validity checks
Before relying on or challenging a patent, confirm whether it is alive with GET /v1/patents/{patent_number}/maintenance, read its claims and CPC classes from GET /v1/patents/{patent_number}/claims, check PTAB challenges with GET /v1/patents/{patent_number}/ptab, and trace its citations in either direction. Ownership records from the assignments endpoint show who currently holds it.
For patent 10123456 call GET /v1/patents/10123456/maintenance, GET /v1/patents/10123456/ptab, and GET /v1/patents/10123456/assignments, then summarise whether it is in force, challenged, and who owns it
Docket monitoring with webhooks
Docketing teams create a monitor with POST /v1/monitors, passing the targets to watch and a webhook_url, plus optional event types and a signing secret. Matched events and their delivery status are readable from GET /v1/monitors/{monitor_id}/events, and GET /v1/events offers a pollable feed filtered by application_numbers, patent_numbers, or entity_ids for teams that prefer polling.
POST /v1/monitors with targets for applications 16123456 and 17234567 and webhook_url 'https://example.com/hooks/patents', then read GET /v1/monitors/{monitor_id}/events to confirm deliveries
35 endpoints — the patent status api returns the current status of us patent applications and granted patents from its own copy of uspto bulk data, in compact json with stable field names.
METHOD
PATH
DESCRIPTION
/v1/applications/{application_number}
Current status of one application
/v1/applications/status
Status of many applications in one call
/v1/applications/{application_number}/office-actions
Office actions with text
/v1/patents/{patent_number}/maintenance
Maintenance fees and expiration
/v1/entities/search
Resolve a company or inventor name to an entity id
/v1/search
Find patents and applications by keyword, CPC, date, and owner
/v1/monitors
Create a monitor with webhooks
/v1/applications/{application_number}
Current status of one application
/v1/applications/status
Status of many applications in one call
/v1/applications/{application_number}/office-actions
Office actions with text
/v1/patents/{patent_number}/maintenance
Maintenance fees and expiration
/v1/entities/search
Resolve a company or inventor name to an entity id
/v1/search
Find patents and applications by keyword, CPC, date, and owner
/v1/monitors
Create a monitor with webhooks
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Patent Status API by hand means choosing between its X-API-KEY header and bearer form, handling the credit-metered responses, and mapping USPTO number formats yourself. Through Jentic you install once, import the API from the API Directory, store the key once, and your agent calls it.
Permission scoping
The API puts the application number, patent number, and entity id in the URL path, so a rule can pin your agent to one application such as /v1/applications/16123456 and the read operations you pick. You choose the operations it may call, so actions like minting keys, creating checkout links, or deleting monitors are not included unless you add them.
Credential isolation
Your Patent Status API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'check a patent application status' or 'find a company's patents', and Jentic returns the matching Patent Status operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Patent Status API through Jentic.
What authentication does the Patent Status API use?
Per its OpenAPI spec, the Patent Status API accepts an API key in the `X-API-KEY` header or the same key as an HTTP bearer token in the Authorization header. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's context.
Can I check many patent applications at once?
Yes. POST /v1/applications/status takes an application_numbers list in the body and returns the status of each in one call. Application numbers are 8-digit strings. For ongoing tracking, a monitor created with POST /v1/monitors pushes events to your webhook instead of re-polling.
How do I find a company's pending applications through Jentic?
Search Jentic for 'find a company's pending patent applications', call GET /v1/entities/search with the company name to get its entity id, then call GET /v1/entities/{entity_id}/applications with status set to pending. To run it on your own infrastructure, install Jentic One from its GitHub repo.
What are the rate limits for the Patent Status API?
The API description in the OpenAPI spec states there are no rate limits per key. Usage is metered in credits instead, and each response carries an `X-Credits-Charged` header with what it cost. See https://patentdata.ai for current pricing.
How fresh is the patent data?
Every object carries a source block naming the USPTO bulk file and its file_date, an as_of date for the last ingest of that table, and a stale flag that is true when the copy is older than the product's update cadence. GET /health reports service and data freshness across tables.
Is there a Patent Status MCP server?
You don't need an MCP server to give your agent the Patent Status API. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls it. Operations are discovered on demand, so no extra tool definitions sit in the agent's context.
Can I limit what my agent is allowed to do with the Patent Status API?
Yes. For example, allow only GET operations under /v1/applications and /v1/patents, so the agent can read status, office actions, and maintenance records but cannot mint keys, create checkout links, or create and delete monitors. Every call it makes is logged by your Jentic One instance.
GET STARTED