Akta Pro connector for AI agents

Tools your research agent reaches for on Akta Pro, scoped per user.

CALL ANY TOOL

Search company news signals with the signed-in user's API key.

aktapro_search_news

Search news

Search company news signals with filters for company, industry, sentiment, entities, and date range.

Parameters

Name

Type

Required

Description

blacklisted

string

Optional

Comma-separated publisher domains to exclude.

company

string

Optional

Company website URL or company UUID to filter news for. Mutually exclusive with primary_company.

countries

string

Optional

Comma-separated 3-letter ISO country codes to filter by.

end_date

string

Optional

End date filter, format YYYY-MM-DD. Defaults to today.

entity_event_list

string

Optional

Comma-separated events to filter by.

entity_location_list

string

Optional

Comma-separated locations to filter by.

entity_person_list

string

Optional

Comma-separated person names to filter by.

entity_product_list

string

Optional

Comma-separated products to filter by.

iab_code_list

string

Optional

Comma-separated IAB codes to filter by.

industry

string

Optional

Comma-separated industry codes to filter by.

iptc_code_list

string

Optional

Comma-separated IPTC codes to filter by.

limit

integer

Optional

Number of results to return. Default 10, max 1000.

naics_code_list

string

Optional

Comma-separated NAICS codes to filter by.

news_score_list

string

Optional

Filter by newsworthiness score: High, Medium, Low, or all (default).

offset

integer

Optional

Offset for pagination. Default 0.

primary_company

string

Optional

Company website URL or UUID where the company is the primary subject. Mutually exclusive with company.

query

string

Optional

Topic or keyword search. Mutually exclusive with title.

sentiment_list

string

Optional

Comma-separated sentiment filters: positive, negative, neutral, or all.

sic_code_list

string

Optional

Comma-separated SIC codes to filter by.

start_date

string

Optional

Start date filter, format YYYY-MM-DD.

title

string

Optional

Search by article title. Mutually exclusive with query.

type_list

string

Optional

Comma-separated news category filters.

unique_article

boolean

Optional

Group similar articles together.

Build your Agent

Same API key vault and scoped tool list across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
const sk = new ScalekitClient(
  process.env.SCALEKIT_ENVIRONMENT_URL,
  process.env.SCALEKIT_CLIENT_ID,
  process.env.SCALEKIT_CLIENT_SECRET,
);
const page = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["aktapro"], toolNames: [
    "aktapro_search_news",
  ]}, pageSize: 100,
});

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";
const sk = new ScalekitClient(
  process.env.SCALEKIT_ENVIRONMENT_URL,
  process.env.SCALEKIT_CLIENT_ID,
  process.env.SCALEKIT_CLIENT_SECRET,
);
const page = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["aktapro"], toolNames: [
    "aktapro_search_news",
  ]}, pageSize: 100,
});
const openai = new OpenAI();

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";
const sk = new ScalekitClient(
  process.env.SCALEKIT_ENVIRONMENT_URL,
  process.env.SCALEKIT_CLIENT_ID,
  process.env.SCALEKIT_CLIENT_SECRET,
);
const page = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["aktapro"], toolNames: [
    "aktapro_search_news",
  ]}, pageSize: 100,
});
const anthropic = new Anthropic();

import { ScalekitClient } from "@scalekit-sdk/node";
const sk = new ScalekitClient(
  process.env.SCALEKIT_ENVIRONMENT_URL,
  process.env.SCALEKIT_CLIENT_ID,
  process.env.SCALEKIT_CLIENT_SECRET,
);
const page = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["aktapro"], toolNames: [
    "aktapro_search_news",
  ]}, pageSize: 100,
});

Try these prompts

Copy a prompt into your agent. Each one maps to Akta Pro company news tools for the signed-in user.

Company coverage

Copy the prompt

Copied

What is the latest news on Acme Robotics this month?

Copy the prompt

Copied

Show negative sentiment articles about Globex from the last 14 days.

Copy the prompt

Copied

Find articles where Acme is the primary company, not just mentioned.

Topic and industry

Copy the prompt

Copied

Search company news for Series B funding in robotics this quarter.

Copy the prompt

Copied

List high newsworthiness articles on semiconductor supply chain.

Copy the prompt

Copied

Filter news to the US and DE, exclude tabloid publishers.

Entities and people

Copy the prompt

Copied

Find news that mentions Jane Doe and Acme Robotics together.

Copy the prompt

Copied

What products are showing up in recent Acme coverage?

Copy the prompt

Copied

Group similar articles so I see unique stories only.

SEE HOW AUTH WORKS

Your users connect once. Their Akta Pro API keys stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

Akta Pro

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Akta Pro

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Akta Pro

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Akta Pro

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Reuse the same per-user API key vault and audit chain on other research and company-intel connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Akta Pro key makes every company news search look like a bot. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_acct

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Akta Pro today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Akta Pro as the user or a shared key?

Per-user resolution. Each tool call uses the signed-in user's Akta Pro API key, so company news searches attribute to that user in the audit log.

Where is the Akta Pro API key stored?

In Scalekit's AES-256 vault, namespaced per tenant. You revoke access from one dashboard without rotating a shared secret across every agent.

Can I limit what the agent does in Akta Pro?

Yes. Filter tool names in listScopedTools (for example aktapro_search_news only) and Scalekit checks that scope before the API call.

What happens when a user revokes access?

The next Akta Pro tool call fails closed for that user. Other users and other connectors are unaffected. The revoke is logged.

Can the agent pull news for companies outside the user's plan?

Only within the signed-in user's own Akta Pro permissions and quota. Scalekit does not widen what that API key can already access.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit