Adyntel for AI agents
Adyntel is a competitive intelligence API that surfaces the Google, LinkedIn, Meta and TikTok ads a company or domain is currently running. Marketers use it to research competitor advertising. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Adyntel.
Pull a competitor's LinkedIn ads
Retrieve the LinkedIn ads a specific company is currently running, using its domain or page ID.
Compare paid versus organic keywords
See which keywords a domain ranks for organically versus the ones it pays to advertise against.
Search TikTok ads by keyword
Find TikTok ads matching a keyword to see how competitors are positioning a product category.
8 Adyntel actions, graded by risk.
Every Adyntel action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- adyntel.get_google_ads_by_companyGet Google Ads By Company
- adyntel.get_linked_in_ads_by_companyGet LinkedIn Ads By Company
- adyntel.get_paid_vs_organic_keywordsGet Paid Vs Organic Keywords
- adyntel.search_tik_tok_ads_by_keywordSearch TikTok Ads By Keyword
- adyntel.get_meta_ads_by_company_or_pageGet Meta Ads By Company Or Page
- adyntel.get_google_shopping_search_statusGet Google Shopping Search Status
write
2Create and change things. Allow, or ask the user first.
- adyntel.meta_ad_searchSearch Meta Ads
- adyntel.start_google_shopping_searchStart Google Shopping Search
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Adyntel in three steps.
- 01Your users connect AdyntelThey add their Adyntel api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “search Meta Ads” can wait for the user to approve.
- 03Any agent can actYour agent calls Adyntel through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('adyntel', { read: 'allow', write: 'ask', // meta_ad_search destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Adyntel connects.
Users add their Adyntel api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Adyntel connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Adyntel from any agent.
Adyntel and Arc0, answered.
Can I use Adyntel with Claude, ChatGPT or Cursor?
Yes. Connect Adyntel to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Adyntel actions you allow.
How do users connect Adyntel?
Users add their Adyntel api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Adyntel actions can my agent take?
8 in total: 6 read, 2 write and 0 destructive, such as “search Meta Ads”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Adyntel?
Yes. Allow read actions and deny writes in the Adyntel policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Adyntel too?
Yes. The same Adyntel connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Adyntel into your agent.
Your users connect Adyntel once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan