Akta Pro MCP connector for AI agents

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

CALL ANY TOOL

17 read-only tools for company intelligence: resolve companies and industries, enrich firmographics, track news, hiring, reviews, and traffic, and generate filtered company lists.

aktapromcp_account_status

Account status

Report the current user's plan tier and credit balance. Free. No arguments, identity is taken from the authenticated API key. Call this when the user asks about their plan, credits, or limits, and consult it before attempting Subscription/Enterprise-only tools (headcount_trends, website_traffic, employee_reviews, product_reviews, job_posts, social_posts) or enterprise-only enrichment sections (Funding Detail, M&A and Investment) to pre-empt a 403. Returns: is_enterprise (bool), package_type (top_up | subscription | enterprise), credit_balance (remaining credits), currency.

Parameters

Name

Type

Required

Description

—

No parameters required

aktapromcp_company_data

Company data

aktapromcp_company_data_concise

Company data concise

aktapromcp_company_search

Search company

aktapromcp_employee_reviews

Employee reviews

aktapromcp_generate_company_list

List generate company

Run a company list: the companies matching your filters. Cost: 1.5 credits per call that returns companies + 0.2 per company, so 25 companies is 6.5 credits. A query matching nothing is FREE. The cost does not depend on the fields: this tool always returns the same identifying fields per company and never full enrichment, so screening a list is cheap and predictable. For depth, call company_data on the few uuids that matter, that is billed per section, on those companies only. Prerequisites, in order: list_filters() to see what exists, then get_filter_values() for every filter that has a `dropdown_type`. Use those values VERBATIM and never write one from memory, these are exact strings from akta-pro's data, so an invented value matches zero companies instead of erroring. Key this call by each entry's `filter`, the one name that field has everywhere. Send at least one selective filter. A very broad or unfiltered query is rejected, not slow, it exhausts the backend's query timeout. Always read `warnings` in the result. A value that was dropped there means the list is BROADER than what the user asked for, which otherwise looks exactly like a good answer; a `coerced` entry means a value was normalised to its canonical form (harmless, but worth trusting over your own spelling next time). A filter key that isn't in list_filters() is an error, not a warning, the call fails with the offending key named and costs nothing, so fix the key and retry rather than guessing. Each company comes back with uuid, name, website, product_category, company_type and hq_country, that is the whole row; there is no option to return more per company. Feed a `uuid` straight into company_data / news_signals for depth on one of them. `total_count` saturates at 500, meaning "500 or more", it is also the deepest page reachable, so narrow the filters rather than paging past it.

Parameters

Name

Type

Required

Description

filters

object

Required

The filters to apply, keyed by the `filter` from each list_filters() entry (its enrichment path). E.g. {"firmographic.company_type": "Private", "location.hq.country": ["USA"], "firmographic.founded_year": {"gte": 2018}}. Filters sharing a `same_element_group` must all match the SAME sub-object. Ranges are {"gte": .., "lte": ..} (inclusive, either bound optional), booleans true/false, name filters a case-insensitive substring. At least one filter is REQUIRED.

limit

integer

Optional

Companies to return.

offset

integer

Optional

Pagination offset.

sort_by

string

Optional

Sort field. Defaults to relevance. Band fields (revenue_estimate, valuation_estimate, employee_range) sort by band magnitude, not alphabetically.

sort_order

string

Optional

Sort direction, desc gives highest revenue / most funding / largest headcount / most recently founded first. Ignored while sort_by is relevance. One of: `asc`, `desc`.

aktapromcp_get_filter_values

Get filter values

aktapromcp_headcount_trends

Headcount trends

aktapromcp_industry_search

Search industry

aktapromcp_job_posts

Job posts

aktapromcp_list_filters

List filters

aktapromcp_news_detail

News detail

aktapromcp_news_signals

News signals

Fetch a list of news signals by company, industry, topic, or title (JSON). Typically provide one of `company`, `primary_company`, `industry`, `query`, or `title` to anchor the search. Cost: 0.1 credits per call + 0.01 per article. `company` matches any article mentioning the company; `primary_company` keeps only the articles the company is actually the subject of. Prefer `primary_company` for "news about X" / company-monitoring requests, and `company` when broad mention coverage matters. They are mutually exclusive, passing both is an error. To filter by news type/topic (e.g. "only product-related news"), call news_types() first to find the matching tag code(s), then pass them as type_codes. To filter by industry/sector, resolve codes with industry_search and pass them as `industry`, don't fall back to `query` for company or industry topics. Default to the compact list (full_enrichment=False), it's enough to read and triage results. Don't set full_enrichment=True unless the user explicitly needs every field on every article. This list never includes full article text (kept compact). Every result carries an `id`; pass those ids to `news_detail` to retrieve the complete article body for the ones you care about.

Parameters

Name

Type

Required

Description

blacklisted

array

Optional

Publisher domains to exclude (e.g. 'example.com').

company

string

Optional

News mentioning a specific company (anywhere in the article). akta-pro company uuid, the 7-character id from company_search (e.g. '00000l1'). This is the ONLY accepted form: company names ('Canva') and website domains ('canva.com') are rejected. Always call company_search first (it's free) and pass the `uuid` of the candidate you want; a domain can map to several distinct entities, so picking the right uuid is your decision to make, not the API's.

countries

array

Optional

Filter by the country of the event. ISO country codes (e.g. 'USA', 'GBR').

end_date

string

Optional

End of date range, YYYY-MM-DD. Default today.

entity_event

array

Optional

Filter to articles mentioning these event names.

entity_location

array

Optional

Filter to articles mentioning these locations.

entity_person

array

Optional

Filter to articles mentioning these people (names).

entity_product

array

Optional

Filter to articles mentioning these product names.

full_enrichment

boolean

Optional

Keep False (the default) for almost all queries, it returns a compact list (id, title, AI summary, URL, date, publisher), which is enough to read and triage results. Only set True if the user explicitly needs the full per-article metadata (industries, types, entities, company mentions, sentiment) for every result; it is much larger, especially for broad topic/query searches. Do NOT default to True.

group_articles

boolean

Optional

Group near-duplicate articles from the same event.

iab_codes

array

Optional

Filter by IAB content taxonomy codes.

industry

string

Optional

Comma-separated industry codes to filter by. For ANY industry / sector / market news request, FIRST call industry_search to resolve the industry to its code(s), then pass them here, this is far more precise than a free-text query. Prefer this over `query` whenever the topic is an industry or market.

iptc_codes

array

Optional

Filter by IPTC media topic codes.

limit

integer

Optional

Max articles to return (max 1000).

naics_codes

array

Optional

Filter by NAICS industry classification codes.

news_score

string

Optional

Filter by news relevance/quality tier. One of: `High`, `Medium`, `Low`, `all`.

offset

integer

Optional

Pagination offset.

primary_company

string

Optional

Like `company`, but returns ONLY articles where this company is the PRIMARY company the article is about, it drops articles that merely mention it in passing. Use this when the user wants news *about* a company rather than every article name-dropping it. Cannot be combined with `company`. akta-pro company uuid, the 7-character id from company_search (e.g. '00000l1'). This is the ONLY accepted form: company names ('Canva') and website domains ('canva.com') are rejected. Always call company_search first (it's free) and pass the `uuid` of the candidate you want; a domain can map to several distinct entities, so picking the right uuid is your decision to make, not the API's.

query

string

Optional

Open-ended free-text topic, e.g. 'crude oil prices'. Use ONLY as a last resort, if the request is about a specific company use `company` (via company_search), and if it's about an industry/sector/market use `industry` (via industry_search). Don't default to query for company or industry topics.

sentiment

string

Optional

Filter by article sentiment. One of: `positive`, `negative`, `neutral`, `all`.

sic_codes

array

Optional

Filter by SIC industry classification codes.

start_date

string

Optional

Start of date range, YYYY-MM-DD. Non-enterprise plans are limited to ~6 months back.

title

string

Optional

Search by text in the article title.

type_codes

array

Optional

Filter by news type/topic. These are tag codes from news_types() (e.g. 'SD01' for product launches, 'CM03' for M&A). To honor a request like 'only product-related news', call news_types() first, pick the matching code(s), and pass them here. Omit for all types.

aktapromcp_news_types

News types

aktapromcp_product_reviews

Product reviews

aktapromcp_social_posts

Social posts

aktapromcp_website_traffic

Website traffic

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Akta Pro MCP tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["aktapromcp"], toolNames: [
    "aktapromcp_company_search",
    "aktapromcp_company_data",
    "aktapromcp_news_signals"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Show funding and product news for Acme Robotics from the last 30 days" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["aktapromcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Show funding and product news for Acme Robotics from the last 30 days" }],
  tools,
});

// Execute the tool call with the user's vaulted Akta Pro API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["aktapromcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Show funding and product news for Acme Robotics from the last 30 days" }],
  tools,
});

// Tool call runs with the user's vaulted Akta Pro API key
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["aktapromcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "research_agent",
  model: "gemini-2.5-pro",
  instruction: "Akta Pro MCP tools scoped to this user",
  tools,
});

await agent.run("Show funding and product news for Acme Robotics from the last 30 days");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Akta Pro MCP tool. Click to copy, paste into your agent, done.

Company profiles

Copy the prompt

Copied

Find the Akta Pro record for acme.com.

Copy the prompt

Copied

Give me a concise company overview for Acme Robotics.

Copy the prompt

Copied

Show headcount trends by function for this company.

News and signals

Copy the prompt

Copied

Show funding news for Acme Robotics from the last 30 days.

Copy the prompt

Copied

List the news types I can filter by.

Copy the prompt

Copied

Get the full article text for these news signal ids.

Lists and market data

Copy the prompt

Copied

Build a list of fintech companies in Germany with 50 to 200 employees.

Copy the prompt

Copied

Pull recent job posts and employee reviews for this company.

Copy the prompt

Copied

Show my Akta Pro plan tier and credit balance.

SEE HOW AUTH WORKS

Each user connects their own Akta Pro API key once; Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Akta Pro MCP

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 MCP

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 MCP

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 MCP

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

See the same per-user auth pattern across other company data and research connectors.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

GTM and RevOps Teams

Outbound prospecting agent

Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.

GTM and RevOps Teams

Deal intelligence agent

Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.

GTM and RevOps Teams

Sales call prep agent

Reads tomorrow's calls from Google Calendar, mines past Granola notes and Attio history for context, and delivers each rep a prep brief in Slack, scoped to the calls that rep actually owns.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Akta Pro API key looks fine in a demo. In production every company lookup looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Akta Pro today. Ten connectors 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 as a shared key?

As the user. Each user connects their own Akta Pro API key once, and Scalekit sends it with every call. Audit logs attribute every action to that user, not a shared service account.

Where is the Akta Pro API key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Akta Pro?

Yes. Filter by tool name in listScopedTools to expose only what you want. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Akta Pro access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

What company data does Akta Pro MCP cover?

17 read-only tools. Start with aktapromcp_company_search: every other company tool accepts only the uuid it returns. From there the agent pulls firmographics, headcount trends, job posts, employee and product reviews, social posts, website traffic, and news signals, or builds company lists from filters. Many calls spend Akta Pro credits, and aktapromcp_account_status reports the plan tier and credit balance.

On this page

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