outbrain-mcp.yml
Outbrain (Teads) publishes NO Model Context Protocol server today. Teads has publicly announced one as an upcoming feature of the Teads AI Chatbot SDK — the developer portal page for it is headed "🚧 In Development", targets "2026", and directs interested developers to their Teads Partner Manager or ai-sdk@teads.com for beta consideration. Nothing is callable. The tools below are a DERIVED candidate surface computed from the operations Outbrain actually publishes in its Apiary blueprint, offered as a design starting point — no endpoint exists and none is invented here.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Descriptor
Candidate descriptor · transport
Tools
list_marketers— List the marketer (customer) accounts the token can access.get_marketer— Retrieve a single marketer account, optionally with extraFields.list_campaigns— List all campaigns associated with a marketer.get_campaign— Retrieve a single campaign.create_campaign— Create a new campaign under a budget.update_campaign— Update an existing campaign.list_promoted_links— List the promoted links (ad creatives) on a campaign.create_promoted_link— Create a promoted link on a campaign.list_budgets— List the budgets belonging to a marketer.create_budget— Create a budget for a marketer.report_campaign_performance— Retrieve campaign-level performance statistics for a marketer over a date range.report_periodic_performance— Retrieve periodic (daily/weekly/monthly) performance statistics for a marketer.report_publisher_performance— Retrieve performance statistics for a marketer broken down by publisher.search_geo_locations— Search Outbrain geo-location targeting entities by term.search_interests— Search interest-targeting segments by term.list_segments— List the audience segments belonging to a marketer.request_teads_report— Trigger an asynchronous Teads analytics report.get_teads_report_status— Poll the status of a Teads analytics report and retrieve its download URL.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.