Install Jentic One Beta

Connect the Jurisprudencias.ai API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Jurisprudencias.ai 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%2Fjurisprudencias.ai%2Fjurisprudencias" | sh

Step 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%2Fjurisprudencias.ai%2Fjurisprudencias" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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.

Capabilities

What an agent can do with Jurisprudencias.ai API.

List the Brazilian courts available for search with the number of decisions held for each

Search one court's decisions by text with exact phrases, OR alternatives, and NOT or minus-term exclusions

Narrow a decision search to a publication window with pub_from and pub_to or a trial window with trial_from and trial_to

Sort search results by publication_date or trial_date and page through them

GET STARTED

Start building with Jurisprudencias.ai API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Jurisprudencias.ai API for, with concrete tasks.

★ Agent Legal Research via Jentic

An AI agent assisting a Brazilian lawyer searches the relevant court's decisions for a legal thesis, using quoted phrases and exclusions to tighten the results, then fetches the full ementa of the strongest matches by case number. Through Jentic the agent discovers the search and lookup operations by intent and calls them with your stored token, so precedent research returns citable decisions rather than summaries from memory.

Search the stj court for '"dano moral" atraso voo -internacional' published since 2024-01-01, sorted by publication_date, then look up the top three by case number and summarise each ementa

Labor Court Precedent Monitoring

Labor law teams run the same TST or regional TRT search on a schedule with a pub_from date set to the last run, so newly published decisions on a topic such as overtime or dismissal surface as they appear. Results sorted by publication_date put the newest rulings first.

Search the tst court for 'horas extras' with pub_from set to last Monday and list the new decisions with their case numbers

Citation Checking for Briefs

Before filing, a paralegal or drafting assistant looks up every case number cited in a brief in the right court and confirms the decision exists and its ementa supports the point being made. The lookup returns the complete decision record, so the check does not depend on a court website.

For each case number cited in the draft, look up the decision in its court and flag any number that returns no decision

Key Endpoints

3 endpoints — the jurisprudencias.

METHOD

PATH

DESCRIPTION

GET

/api/v1/courts

List available courts

GET

/api/v1/courts/{court_id}/decisions

Search a court's decisions by text

GET

/api/v1/courts/{court_id}/decisions/lookup

Get a decision by case number

GET

/api/v1/courts

List available courts

GET

/api/v1/courts/{court_id}/decisions

Search a court's decisions by text

GET

/api/v1/courts/{court_id}/decisions/lookup

Get a decision by case number

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring Jurisprudencias.ai by hand means sending its jur_ bearer token, learning the court identifiers for the STF, STJ, TST, TRT, TRF, TJ courts, and CARF, and writing queries in its websearch syntax. Through Jentic you install once, import Jurisprudencias.ai from the API Directory, store the token once, and your agent calls it.

Permission scoping

Jurisprudencias.ai puts the court id in the URL path (/api/v1/courts/{court_id}/decisions), so a rule can pin your agent to one court, such as the STJ, and the search or lookup operations you pick. You choose the operations it may call, and the API itself is read-only.

Credential isolation

Your Jurisprudencias.ai token 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 'search Brazilian court decisions' or 'get a decision by case number', and Jentic returns the matching Jurisprudencias.ai operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Jurisprudencias.ai API through Jentic.

What authentication does the Jurisprudencias.ai API use?

The Jurisprudencias.ai API authenticates with a bearer token prefixed jur_, sent in the Authorization header, per its OpenAPI spec. Tokens are issued from the API tokens page of your Jurisprudencias.ai account. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time.

Is there a Jurisprudencias.ai MCP server?

You don't need an MCP server to give your agent Jurisprudencias.ai. Jentic connects it directly from the API Directory: import it, store your token once, and your agent searches and fetches court decisions as it needs to. Operations are discovered on demand, so no extra server's tool definitions sit in your agent's context.

Can I limit what my agent is allowed to do with the Jurisprudencias.ai API?

Yes. The court id is in the path, so you can write a rule that allows only the decision search and lookup under /api/v1/courts/stj/, letting a research agent work in the STJ and nowhere else. The API is read-only, so the main reason to scope is keeping an agent to the courts that matter for a matter, and every call it makes is logged.

What search syntax does the Jurisprudencias.ai API support?

Per its OpenAPI spec, the q parameter uses PostgreSQL websearch syntax: plain terms, "exact phrases" in quotes, OR between alternatives, and NOT or a leading minus to exclude a term. OR separates complete alternatives, and parentheses are ignored, so terms cannot be grouped.

What are the rate limits for the Jurisprudencias.ai API?

The Jurisprudencias.ai OpenAPI spec defines a 429 response for when the request limit is reached but does not publish the limit itself. Check https://jurisprudencias.ai for the current limits on your token.

How do I search court decisions with the Jurisprudencias.ai API through Jentic?

Search Jentic for an intent like 'search Brazilian court decisions', import Jurisprudencias.ai from the API Directory, and store your token once. Your agent then calls GET /api/v1/courts/{court_id}/decisions with a court id such as stj and a q search term, and fetches a full decision with GET /api/v1/courts/{court_id}/decisions/lookup and the case number in n. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Jurisprudencias.ai API

AI ReadinessAI-Aware (B+)69/100

See full scorecard

Official vendor OpenAPI document · agent-readyData EnrichmentData Transformationbearer3 EndpointsREST

For Agents

Search Brazilian court decisions by text in the STF, STJ, TST, TRT, TRF, TJ courts, and CARF, filter by publication or trial date, and fetch a full decision by case number.

Use for: Search STJ decisions about moral damages for flight delays, Find all TST rulings on overtime published in 2025, Get the full ementa for this case number in the STF, List the courts I can search

Not supported: Does not handle case filing, docket tracking, or legislation text. Use for searching and retrieving published Brazilian court decisions only.

The Jurisprudencias.ai API searches published decisions from Brazilian courts, including the STF, STJ, and TST, the regional labor courts (TRT), the federal regional courts (TRF), the state courts (TJ), and the CARF tax appeals board. A full-text search runs against one court at a time with exact phrases in quotes, OR alternatives, and NOT or minus-term exclusions, filtered by publication or trial date ranges and sorted by either date. A lookup by case number returns the complete decision including its full ementa, and a courts listing reports which courts are available and how many decisions each holds.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

100

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

99%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

100%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: B-Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

50%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: C-Signals: 4

59%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

43%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1

60%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: ASignals: 1

83%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Jurisprudencias.ai API to your agent

Capabilities

Start building with Jurisprudencias.ai API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Jurisprudencias.ai API

Jentic AI Readiness Score

Jurisprudencias.ai API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness