Install Jentic One Beta

Connect the Adaptador API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Adaptador 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%2Fcomunidad.madrid%2Fcomunidad" | 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%2Fcomunidad.madrid%2Fcomunidad" | 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 Adaptador API.

Create a work-item record with its address and subjects

Retrieve a single work item by its UUID

Update a work item, its address, or its subjects

Withdraw a work item through a logical delete

GET STARTED

Start building with Adaptador API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Adaptador API for, with concrete tasks.

★ Regional Work-Item Automation via Jentic

AI agents reach the Adaptador operations through Jentic without handling the OAuth flow. An agent searches by intent, receives the matching operation schema, and creates or revises a work-item record end to end. Jentic obtains and injects the OAuth access token at execution time, so the agent never sees the secret while it maintains records in the Comunidad de Madrid backend.

Search Jentic for 'create a Comunidad de Madrid work item', load the POST /trabajos schema, and create the record with Jentic-managed OAuth

Work-Item Lifecycle Management

An agent walks a work item through its full lifecycle: it creates the record, reads it back to confirm state, applies updates to the address or subjects, and finally withdraws it with a logical delete when the item closes. The Adaptador keeps each record addressable by a stable UUID, so the agent can revisit and revise the same item across sessions.

Call POST /trabajos to create the record, then GET /trabajos/{uuid_trabajo} and PUT /trabajos/{uuid_trabajo} to read and revise it

Address Page Maintenance

Beyond the work items themselves, an agent maintains the address pages tied to each record. It registers a new address, looks one up by id, and revises or removes it as the underlying information changes. This keeps the address data attached to a work item accurate without a human editing the intranet directly.

Call POST /paginas to register an address, then GET /paginas/{id_pagina} to read it back by id

Key Endpoints

8 endpoints — the adaptador api exposes work-item and address-page records from a comunidad de madrid intranet backend to ai agents over a rest interface.

METHOD

PATH

DESCRIPTION

POST

/trabajos

Create a work-item record

GET

/trabajos/{uuid_trabajo}

Retrieve a work item by its UUID

PUT

/trabajos/{uuid_trabajo}

Update a work item, its address, or its subjects

DELETE

/trabajos/{uuid_trabajo}

Withdraw a work item through a logical delete

POST

/paginas

GET

/paginas/{id_pagina}

Look up an address page by its id

POST

/trabajos

Create a work-item record

GET

/trabajos/{uuid_trabajo}

Retrieve a work item by its UUID

PUT

/trabajos/{uuid_trabajo}

Update a work item, its address, or its subjects

DELETE

/trabajos/{uuid_trabajo}

Withdraw a work item through a logical delete

POST

/paginas

GET

/paginas/{id_pagina}

Look up an address page by its id

Why Jentic?

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

Setup

Wiring the Adaptador API by hand means obtaining an OAuth 2.0 access token from the Comunidad de Madrid authorization server, refreshing it, and sequencing the work-item and address-page calls yourself. Through Jentic you install once, import the Adaptador API from the API Directory, store the OAuth credential, and your agent calls it.

Permission scoping

The Adaptador API puts the work-item UUID and address-page id in the URL path, so a rule can pin your agent to one work item or page and the operations you choose. You decide which operations it may call, so a logical delete or an update stays out unless you grant it.

Credential isolation

Your Comunidad de Madrid OAuth 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 'create a work item' or 'update an address', and Jentic returns the matching Adaptador operation with its input schema so the agent calls the right endpoint without reading the reference docs.

FAQs

Specific to using Adaptador API through Jentic.

What authentication does the Adaptador API use?

The Adaptador API secures its operations with OAuth 2.0, declared as an oauth2 scheme in its OpenAPI spec, so your agent presents a bearer access token from the Comunidad de Madrid authorization server. Through Jentic, the token is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's prompt or logs.

Can I create and update work items with the Adaptador API?

Yes. Create a work item with POST /trabajos, retrieve it with GET /trabajos/{uuid_trabajo}, and apply changes to the record, its address, or its subjects with PUT /trabajos/{uuid_trabajo}.

What are the rate limits for the Adaptador API?

The OpenAPI spec does not specify rate limits; check the Comunidad de Madrid documentation for current limits. Through Jentic, requests run from your own instance, so you control the pacing of the agent's calls.

How do I create a work item with the Adaptador API through Jentic?

Search Jentic for 'create a Comunidad de Madrid work item', load the returned POST /trabajos operation with its input schema, and your agent submits the record with the OAuth token injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Is there a Comunidad de Madrid Adaptador MCP server?

You don't need an MCP server to give your agent the Adaptador API. Jentic connects it directly from the API Directory: import it, store your OAuth credential, and your agent calls it, discovering operations on demand instead of loading a separate server's tool definitions into its context.

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

Yes. The Adaptador API puts the work-item UUID and address-page id in the URL path, so a rule can scope your agent to one work item or page and the operations you pick, such as reading a record without modifying it. You choose which operations it may call, so a logical delete or an update stays out unless you add it.

Comunidad Madrid Adaptador API

AI ReadinessNon-Ready (F)40/100

See full scorecard

Community OpenAPI document · agent-readyProductivityTask Managementoauth28 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Create, read, update, and withdraw Comunidad de Madrid work-item and address-page records over REST. Secured with OAuth 2.0.

Use for: I want to create a new work item in Comunidad de Madrid, Fetch a work item by its UUID, Update the address on an existing work item, Withdraw a work item with a logical delete

Not supported: Does not cover municipality, province, or scholarship data in this adapter. Use for work-item and address-page records only.

The Adaptador API exposes work-item and address-page records from a Comunidad de Madrid intranet backend to AI agents over a REST interface. Agents create a work item with its address and subjects, read or revise it by UUID, and withdraw it through a logical delete. A companion set of operations registers and maintains the address pages tied to each work item. Every operation is secured with OAuth 2.0.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

96%

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: A-Signals: 4

47%

Example Density

How richly the API is illustrated with examples.

92%

Example Validity

Percentage of examples that conform to their schemas.

75%

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: FSignals: 4

61%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

OperationId Quality

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

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: FSignals: 1

35%

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: C+Signals: 1

59%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Adaptador API to your agent

Capabilities

Start building with Adaptador API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Comunidad Madrid Adaptador API

Jentic AI Readiness Score

Adaptador

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