Install Jentic One Beta

Connect the Adako REST API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Adako REST 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%2Fadako.ai%2Fadako" | 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%2Fadako.ai%2Fadako" | 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 Adako REST API.

Discover and describe the Adako tools available for connected ad accounts

Create paused Google Ads search and Performance Max campaigns for review

Approve or reject pending change proposals before they reach the ad platform

List connected ad accounts and check connection health per platform

Set up daily monitors on an ad account and review the changes they propose

GET STARTED

Start building with Adako REST API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Adako REST API for, with concrete tasks.

★ AI ad-ops agent with human approval

An AI agent managing paid search drafts changes but should not push them live on its own. Through Jentic the agent searches for 'create a Google Ads search campaign', loads the matching Adako tool with its input schema, and executes it with the account key injected at call time. The write returns a proposal rather than a live change, so a person approves it before anything reaches the ad platform.

Execute POST /api/v1/tools/google_create_search_campaign/execute to draft a paused campaign, then list it with POST /api/v1/tools/list_pending_proposals/execute for approval

Cross-platform account health check

An agent that oversees several ad platforms reports which accounts are connected and healthy before acting. Adako lists connected accounts and returns connection health per platform, so the agent can flag a broken connection early. It can also read plan and task usage so a batch of changes does not exceed the account's quota.

Call POST /api/v1/tools/list_connected_accounts/execute and POST /api/v1/tools/get_usage_status/execute, then report any unhealthy account

Daily monitoring and anomaly review

A team sets up daily monitors that watch spend and performance and propose corrective changes. Adako creates monitors, lists what each monitor proposed, and lets a reviewer approve or reject those actions. An agent can surface the day's proposed actions and apply only the ones a human confirms.

List proposed actions with POST /api/v1/tools/list_pending_actions/execute and apply an approved one with POST /api/v1/tools/manage_action/execute

Key Endpoints

235 endpoints — the adako api gives an ai assistant one http call for every advertising action it can take across google ads, meta ads, chatgpt ads, tiktok ads, and linkedin ads.

METHOD

PATH

DESCRIPTION

GET

/api/v1/tools

List every callable tool

GET

/api/v1/tools/{tool_name}

Describe one tool

POST

/api/v1/tools/search_tools/execute

Find the right tool for a job

POST

/api/v1/tools/list_connected_accounts/execute

List connected ad accounts

POST

/api/v1/tools/get_usage_status/execute

Read plan and task usage

POST

/api/v1/tools/google_create_search_campaign/execute

Create a paused Google Ads search campaign

POST

/api/v1/tools/list_pending_proposals/execute

List proposals waiting for approval

POST

/api/v1/tools/approve_proposal/execute

Approve and execute a pending proposal

GET

/api/v1/tools

List every callable tool

GET

/api/v1/tools/{tool_name}

Describe one tool

POST

/api/v1/tools/search_tools/execute

Find the right tool for a job

POST

/api/v1/tools/list_connected_accounts/execute

List connected ad accounts

POST

/api/v1/tools/get_usage_status/execute

Read plan and task usage

POST

/api/v1/tools/google_create_search_campaign/execute

Create a paused Google Ads search campaign

POST

/api/v1/tools/list_pending_proposals/execute

List proposals waiting for approval

POST

Why Jentic?

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

Setup

Wiring Adako by hand means issuing an API key, sending it as a bearer token with the right scopes, and handling the proposal-and-approval round trip that every write returns. Through Jentic you install once, import Adako from the API Directory, store the key once, and your agent calls it.

Permission scoping

Each Adako tool executes at its own path such as /api/v1/tools/google_create_search_campaign/execute, so a rule can pin your agent to the specific tools it may run. You choose which it may call, so the proposal-approval tool can stay off the agent's list and keep final sign-off with you.

Credential isolation

Your Adako API key is stored once, encrypted, by your own Jentic One instance and attached as the bearer token 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 Google Ads campaign' or 'check ad account health', and Jentic returns the matching Adako tool with its input schema so the agent runs the right operation without browsing the full tool list.

FAQs

Specific to using Adako REST API through Jentic.

What authentication does the Adako API use?

Adako authenticates with a bearer token per its OpenAPI spec: an Adako API key formatted as ak_live_... is sent in the Authorization header, and the key carries scopes such as ads:read and ads:write. Through Jentic the key is held by your own instance and attached per call, so an agent never handles it directly.

Does the Adako API change my ad campaigns immediately?

No. Reads run immediately, but a write creates a proposal that returns a proposal id and an approval URL, and nothing changes on the ad platform until that proposal is approved. Created campaigns are always paused, so an agent can draft changes while a person keeps control of what goes live.

What are the rate limits for the Adako API?

The OpenAPI spec expresses limits as a plan and task quota rather than a fixed request ceiling, and GET /api/v1/tools/get_usage_status reports the current usage. Check the Adako documentation for the per-plan task allowance before running large batches of changes.

Is there an Adako MCP server?

You do not need a separate MCP server to use Adako with your agent. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the same ad-management operations on demand without loading another server's tool definitions into its context.

How do I create a Google Ads campaign through Jentic?

Search Jentic for 'create a Google Ads search campaign', load the POST /api/v1/tools/google_create_search_campaign/execute operation, and run it with the account and campaign fields. It returns a paused proposal to approve. To run it on your own infrastructure, install Jentic One from its GitHub repo.

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

Yes. Each tool executes at its own path, so a rule can allow the agent to run only the tools a task needs, such as reading performance and drafting a campaign, while withholding proposal approval so changes still need your sign-off. The agent is bound to the operations you grant, and every call is logged.

Adako REST API

AI ReadinessFoundational (C+)59/100

See full scorecard

Official vendor OpenAPI document · agent-readyMarketingAdvertisingbearer235 EndpointsREST

For Agents

Manage ad campaigns across Google, Meta, ChatGPT, TikTok, and LinkedIn Ads for AI agents, where writes create a proposal to approve and new campaigns start paused.

Use for: List the ad accounts connected to Adako, Create a paused Google Ads search campaign, Check the connection health for each ad platform, Approve a pending change proposal

Not supported: Does not host landing pages, process ad payments, or generate creative assets. Use for managing ad campaigns across connected platforms only.

The Adako API gives an AI assistant one HTTP call for every advertising action it can take across Google Ads, Meta Ads, ChatGPT Ads, TikTok Ads, and LinkedIn Ads. Reads run immediately, while writes create a proposal that returns a proposal id and an approval URL, and nothing changes on the ad platform until that proposal is approved. Created campaigns are always paused. The surface includes account discovery, connection health, usage, daily monitors, and platform-specific tools such as creating campaigns, adding keywords and extensions, and reporting on performance.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

89%

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.

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: C-Signals: 4

51%

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.

50%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: D-Signals: 1

43%

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: A+Signals: 1

90%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Adako REST API to your agent

Capabilities

Start building with Adako REST API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Adako REST API

Jentic AI Readiness Score

Adako REST 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