Install Jentic One Beta

Connect the Juspronto: superfície pública para agentes (conector MCP e OAuth) to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Juspronto: superfície pública para agentes (conector MCP e OAuth), 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%2Fjuspronto.com.br%2Fjuspronto" | 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%2Fjuspronto.com.br%2Fjuspronto" | 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 Juspronto: superfície pública para agentes (conector MCP e OAuth) API.

Send JSON-RPC 2.0 messages to the Juspronto connector to list and call the tools the lawyer authorised, such as reading open deadlines and the day's hearings

Request scopes such as prazos:read, processos:read, dashboard:read, and autos:read, plus write scopes like prazos:write and minutas:write where the lawyer grants them

Read who connected through the OIDC userinfo endpoint

GET STARTED

Start building with Juspronto: superfície pública para agentes (conector MCP e OAuth) API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Juspronto: superfície pública para agentes (conector MCP e OAuth) API for, with concrete tasks.

★ Agent Deadline Review via Jentic

An AI agent working for a Brazilian law firm calls the Juspronto connector each morning with the read scopes the lawyer granted, lists the available tools, and reads open and overdue deadlines plus the day's hearings. Through Jentic the agent finds the connector operation by intent and calls it with the OAuth token held by your own instance, then reports what needs attention without the lawyer opening the app.

Send initialize, then tools/list, to the Juspronto connector, call the tool that returns overdue deadlines, and summarise them by case for the lawyer

Draft Preparation for Lawyer Approval

With the minutas:write scope granted, an agent saves and updates pending drafts inside Juspronto for a lawyer to review and approve. Per the scope's own description, nothing is filed with the court, so the lawyer stays the one who approves and files.

Using a token with minutas:write, call the connector tool that saves a pending draft for case number 0001234-56.2026.8.26.0100 so the responsible lawyer can review it

Connecting a New Agent Client

A developer building an agent client registers it with dynamic client registration by posting its redirect_uris, sends the lawyer to the authorize endpoint with a code_challenge and the requested scope, and exchanges the returned code for tokens. The discovery documents describe the authorization server and protected resource so the client can configure itself.

Fetch the authorization server metadata, register a client with redirect_uris, and build the authorize URL with code_challenge_method S256 and scope 'prazos:read processos:read dashboard:read autos:read'

Key Endpoints

22 endpoints — the juspronto api is the public agent surface of juspronto, a practice management system for brazilian law firms.

METHOD

PATH

DESCRIPTION

POST

/api/mcp

Send a JSON-RPC message to the connector

POST

/api/mcp-oauth/register

GET

/api/mcp-oauth/authorize

Start the authorization flow

POST

/api/mcp-oauth/token

Exchange a code or refresh a token

GET

/api/mcp-oauth/userinfo

Get the connected person

GET

/.well-known/oauth-authorization-server

Get authorization server metadata

POST

/api/mcp

Send a JSON-RPC message to the connector

POST

/api/mcp-oauth/register

GET

/api/mcp-oauth/authorize

Start the authorization flow

POST

/api/mcp-oauth/token

Exchange a code or refresh a token

GET

/api/mcp-oauth/userinfo

Get the connected person

GET

/.well-known/oauth-authorization-server

Get authorization server metadata

Why Jentic?

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

Setup

Wiring Juspronto by hand means registering an OAuth client, running the PKCE flow with the right scopes and resource, refreshing tokens, and speaking JSON-RPC 2.0 over an event-stream response. Through Jentic you install once, import Juspronto from the API Directory, connect once with the scopes you choose, and your agent calls it.

Permission scoping

Juspronto carries the tool name inside the JSON-RPC request body, so Jentic rules bound which operations your agent may call, such as the connector call and userinfo, not which tool. Juspronto's own OAuth scopes, chosen by the lawyer at consent, decide which tools appear, and you choose the operations it may call so client registration is not included unless you add it.

Credential isolation

Your Juspronto 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 'read law firm deadlines' or 'register an OAuth client', and Jentic returns the matching Juspronto operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Juspronto: superfície pública para agentes (conector MCP e OAuth) API through Jentic.

What authentication does the Juspronto API use?

The Juspronto OpenAPI spec declares two schemes for the connector endpoint: OAuth 2.1 authorization code with PKCE S256 for a public client, where the minimum scopes are prazos:read, processos:read, dashboard:read, and autos:read, and an HTTP bearer key created by a partner or manager in Juspronto's settings, which reads but does not write. The userinfo endpoint takes the OAuth token. The discovery documents, OAuth registration, authorize, and token endpoints, health check, and Markdown pages are open. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time.

Is there a Juspronto MCP server?

Yes - Juspronto offers an official MCP server, and its connector endpoint at /api/mcp is that server. You can also connect it through Jentic: your agent gets the full 22-endpoint surface from the spec without loading another server's tool definitions into its context, your credential is injected at call time by your self-hosted instance instead of living in an MCP config, and your rules decide which operations the agent may call.

Can I limit what my agent is allowed to do with the Juspronto API?

Yes, at two levels. In Juspronto the lawyer picks scopes on the consent screen, for example granting only prazos:read and dashboard:read so an agent can read deadlines and the agenda but write nothing. In Jentic you can write a rule that allows only the connector call and userinfo operations and leaves out client registration, and every call the agent makes is logged. Tool names travel inside the JSON-RPC body, so Jentic rules bound operations, not individual connector tools.

Can an agent file documents with a court through the Juspronto API?

No. Per its OpenAPI spec, nothing is filed with a court through the connector. The minutas:write scope saves and updates pending drafts for a lawyer to review and approve inside Juspronto.

What are the rate limits for the Juspronto API?

The Juspronto OpenAPI spec defines a 429 response with a Retry-After header and notes a per-address hourly cap on OAuth client registrations, without publishing the numbers. Juspronto publishes its plans and limits on its Markdown pricing page at https://juspronto.com.br/precos.md.

How do I read my firm's deadlines with the Juspronto API through Jentic?

Search Jentic for an intent like 'read law firm deadlines', import Juspronto from the API Directory, and complete the OAuth connection once with the read scopes. Your agent then calls POST /api/mcp with a JSON-RPC initialize message, then tools/list and tools/call to read deadlines. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Juspronto: superfície pública para agentes (conector MCP e OAuth)

AI ReadinessAI-Ready (A-)75/100

See full scorecard

Official vendor OpenAPI document · agent-readyProductivityTask Managementoauth2, bearer22 EndpointsREST

For Agents

Read a Brazilian law firm's deadlines, cases, agenda, and case records in Juspronto, and with write scopes create deadlines, tasks, and draft documents for lawyer review, through one JSON-RPC connector authorised by OAuth.

Use for: List all of my firm's deadlines that are overdue, Get today's hearings and meetings from Juspronto, Retrieve the latest filings for this case, Save a draft petition for the lawyer to review

Not supported: Does not handle court filing, billing, or case law search. Use for reading and updating a Brazilian law firm's Juspronto deadlines, cases, and drafts only.

The Juspronto API is the public agent surface of Juspronto, a practice management system for Brazilian law firms. Its core is a single JSON-RPC 2.0 connector endpoint that lets an authorised agent read the firm's deadlines (prazos), cases and their filings, the day's agenda, and imported case records (autos), and, with the matching scopes, create deadlines, tasks, and draft documents that a lawyer reviews and approves inside Juspronto. Access is granted through OAuth 2.1 with PKCE and dynamic client registration, where the lawyer picks the permissions on a consent screen, or through a read-only key created by a partner or manager. Public discovery documents, including OAuth metadata, the server card, llms.txt, and the pricing page in Markdown, are served without authentication. Nothing is filed with a court through the connector.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

98%

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).

75%

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

10%

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

39%

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: BSignals: 4

77%

Description Coverage

Coverage of descriptions across API elements.

18%

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

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

58%

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: A-Signals: 1

75%

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

85%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Juspronto: superfície pública para agentes (conector MCP e OAuth) to your agent

Capabilities

Start building with Juspronto: superfície pública para agentes (conector MCP e OAuth) API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Juspronto: superfície pública para agentes (conector MCP e OAuth)

Jentic AI Readiness Score

Juspronto: superfície pública para agentes (conector MCP e OAuth)

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