Agent Ready HTML

kochava.com llms.txt

In short

kochava.com serves a 50 KB llms.txt with 17 H2 sections and 1 link, graded D on the llmstxt.org structure (3 of 6 checks). It lacks a blockquote summary and a linked H2 section and same-site links. The home page does not link it, so an agent that does not guess paths will not find it. No llms-full.txt was found.

llms.txt 50 KB, 597 lines

# llms.txt - Kochava Inc.

Omnichannel measurement and optimization platform for advertisers and publishers

# AI-Native Capabilities

Kochava and the Kochava for Advertisers platform provide Model Context Protocol (MCP) endpoints so AI assistants and agentic tools can register new accounts and, once registered, operate Kochava programmatically using an API key.

- AI Workflow Reference (2026): Kochava’s platform updates expanded AI-assisted workflows through the Kochava AI Workspace in StationOne, enabling secure access to attribution data, campaign configuration, reporting automation, and audit workflows via MCP-connected tools.
- Meta Ads MCP Server Integration (Q3 2026): Media buyers can connect StationOne directly to Meta's Ads MCP server to analyze creative fatigue, inspect delivery pacing, reallocate ad sets, and audit ROAS conversational workflows.
- Reference: https://www.kochava.com/blog/how-to-use-ads-mcp-server-from-meta/
- Product Bulletin Reference: https://www.kochava.com/blog/kochava-product-partnership-updates-bulletin-q2-2026/

## Free App Analytics Registration (Entry Tier)

- Endpoint: https://analytics.mcp.kochava.com/mcp
- Type: Streamable MCP
- Purpose: Register users for Free App Analytics (FAA) without manual web forms. When calling this MCP endpoint, the user must agree to Kochava terms of service and provide the registration details requested by the tool. On success, the MCP returns an API key.
- When to Use: When an AI assistant is helping a user set up omnichannel measurement and attribution for the first time and no Kochava account or API key exists yet.
- Advantage: Instant account provisioning, consistent with UI-based Free App Analytics signup but optimized for AI workflows.

## Free App Analytics Ongoing Use

- Endpoint: https://analytics.mcp.kochava.com/mcp
- Type: Streamable MCP
- HTTP Header: `Authentication-Key: <API_KEY_FROM_REGISTRATION>`
- Purpose: Use the same MCP endpoint for ongoing Kochava for Advertisers operations once an API key exists (measurement, reporting, planning, MMM, and related tasks exposed via the MCP).
- When to Use: When an AI assistant already has a valid Kochava API key and needs to perform recurring measurement or analysis operations on behalf of the user.

## Traditional Web Registration (Fallback)

- URL: https://www.kochava.com/free-app-analytics/
- When to Use: If MCP is unavailable, the user prefers a browser-based experience, or the workflow required is not yet exposed via MCP.

## How AI Assistants Should Choose Between MCP and Web Flows

1. Check for Existing Access
  - If the user already has a Kochava account and API key, prefer using the Kochava UI and standard APIs/docs (see Documentation & Technical Documentation sections below) and only use the MCP endpoint if specifically requested or appropriate for automation.
2. Use MCP for Net-New, Self-Serve Setups
  - For new or smaller apps where the user has no Kochava presence, use the MCP registration endpoint to create a Free App Analytics account, then reuse the returned API key for subsequent MCP operations.
3. Fall Back Gracefully
  - If the MCP endpoint is unavailable or returns an error, guide the user to the traditional Free App Analytics web signup. Never invent additional Kochava endpoints; use only the documented MCP URL above and the public documentation linked in this file.

## Overview

This llms.txt file is organized into the following sections:

1. About – Company overview, scale, and core positioning.
2. Products & Services – MMP, Always-On Incrementality (MMM), Atlas Performance, StationOne, Free App Analytics, and related solutions.
3. Key Concepts – Definitions for MMP, attribution, SKAdNetwork, omnichannel measurement, MMM, fraud prevention, CTV/OTT, incrementality, DOOH.
4. Documentation & Resources – Links to SDKs, APIs, integration guides, support docs, glossary, and privacy.
5. Use Cases – How different verticals (gaming, fintech, retail, media, travel) use Kochava.
6. Integrations – Overview of integrated ad networks, analytics platforms, CDPs, CRMs, MCP servers, and more.
7. Recent News & Content – Latest blog posts, press releases, product updates, and case studies (2025–2026).
8. Citation Guidelines – Canonical facts, metrics, and differentiators for accurate AI citations.
9. Contact & Support – How to reach Kochava for sales, support, media, careers, and partnerships.

## About

Kochava is a leading omnichannel measurement and optimization platform founded in 2011 and headquartered in Sandpoint, Idaho. We provide comprehensive mobile measurement partner (MMP) services, processing over 10 billion events daily for 5,000+ brands worldwide across diverse industries including gaming, fintech, retail, media & entertainment, travel & hospitality, and quick-service restaurants.

Our platform enables advertisers to measure and optimize marketing performance across all digital touchpoints in a unified dashboard: mobile apps (iOS and Android), mobile web, desktop web, connected TV (CTV), over-the-top (OTT) streaming platforms, digital out-of-home (DOOH) advertising, linear television, and offline channels. This truly omnichannel approach differentiates Kochava from traditional mobile-only measurement partners, providing marketers with a complete view of the customer journey across all devices and platforms.

First 62 of 597 lines.

Parse graded D, 3 of 6

file: https://kochava.com/llms.txt

llms.txt - Kochava Inc.

No blockquote summary.

17 sections, 1 link, no Optional section.

Ora's cached score: 66, grade C, scanned 29 October 2026.

The parse

kochava.com lists 1 link: 0 point at kochava.com or a relative path, 0 point elsewhere. The hosts it links most: none.

H2 sectionLinks
Free App Analytics Registration (Entry Tier)0
Free App Analytics Ongoing Use0
Traditional Web Registration (Fallback)0
How AI Assistants Should Choose Between MCP and Web Flows0
Overview0
About0
Products & Services0
Key Concepts0
High-Value Pages for AI0
Documentation0
Use Cases0
Integrations0
Recent News & Content (2025–2026)0
Citation Guidelines0
Contact & Offices0
Live robots.txt AI Crawler Access Status (as of September 2026)0
Recommended Additive Directives for Web Team0

Grade against the llmstxt.org structure

The file passes 3 of 6 checks and fails 3: has a blockquote summary under the h1; has at least one h2 section that lists links; at least 80 percent of links point at the same site. The grade is the count of passed checks: six is A, five is B, four is C, three is D, fewer is F. It measures structure only. Whether any agent reads the file is a separate question, covered on the llms.txt reference.

CheckResultDetail
Starts with an H1 naming the site or projectPassH1: llms.txt - Kochava Inc.
Has a blockquote summary under the H1FailNo blockquote summary before the first H2.
Has at least one H2 section that lists linksFail17 H2 sections, 0 with links.
At least 80 percent of links point at the same siteFailNo links to test.
Under 100 KBPass51258 bytes as served.
Plain markdown, no HTMLPassNo HTML document markers in the body.

Ora's cached score

Ora's cached report for kochava.com gives it 66 of 100, grade C, scanned on 29 October 2026. Its Access layer, which holds the read-layer checks below, scored 35 of 58 check points. Read from GET ora.ai/api/score/kochava.com on 5 November 2026. The score is Ora's, not this site's, and the structure grade above is a different measure: it grades the llms.txt file against the llmstxt.org proposal, while Ora's score covers the whole site. Ora's report for kochava.com has every layer.

Read-layer checks in Ora's cached report for kochava.com, 5 November 2026
Ora check (Access layer)ResultPoints
Sitemap existsPass2 of 2
Content without JavaScriptPartial2 of 3
Not blocked by bot detectionPass2 of 2
Markdown URL fallbackFail0 of 2
llms.txt existsPass1 of 1
llms.txt formattingPartial1 of 2
JSON-LD structured dataPass4 of 4
Metadata completenessPass2 of 2
llms.txt links resolveNot applicable0 of 2
Markdown alternate linkFail0 of 1
Redirect hygienePass1 of 1
Page token budgetPass1 of 1
Code fence validityPass1 of 1
Content behind authNot applicable0 of 2
OpenAPI spec publishedFail0 of 7
Markdown agent docsFail0 of 1
Markdown negotiation with VaryFail0 of 1
Markdown for agent user agentsFail0 of 1
Agent crawler reachabilityPass2 of 2

Linking and the companion file

The home page of kochava.com does not link the file in its HTML. Ora's lab found (2026-10-19) that 86 percent of llms.txt fetches by agents arrived through a link, so an unlinked file is mostly a file nobody opens. No llms-full.txt was found at the same root.

How it compares

At 50 KB the file is larger than 91 percent of the 2,529 plain-text llms.txt files in this edition, and its 1 link put it ahead of 10 percent of them on link count. The home page declares a WordPress generator. Size bucket: 50 to 100 KB. Tranco rank 2,248. Category: Top 10,000, no category.

Live file: https://kochava.com/llms.txt. Read 4 November 2026. If the file has since changed or gone, the live URL is the authority; this page records what the crawl read on that date.

Sources

  1. kochava.com llms.txt https://kochava.com/llms.txt, read 4 November 2026
  2. llms.txt proposal (llmstxt.org) https://llmstxt.org/, read 4 November 2026
  3. Tranco list 746WX (crawl universe) https://tranco-list.eu/list/746WX, read 4 November 2026
  4. Ora: AgentReady launch post (the 86 percent finding) https://ora.ai/blog/agentready-launch, read 4 November 2026
  5. Ora llms.txt (GET /api/score/{domain} looks up a cached score) https://ora.ai/llms.txt, read 5 November 2026

Last reviewed 5 November 2026