Is AB Tasty Flagship agent-ready?

AB Tasty Flagship scores Band B on The Headless Index. Its JAIRF rating is not available because no machine-readable spec was scored. Its strongest area for agent use is headless operation; its weakest is schema observability.

Does AB Tasty Flagship publish an OpenAPI spec?

No published OpenAPI specification was found when AB Tasty Flagship was scored. That caps its JAIRF dimensions and forces agents to rely on documentation or reverse engineering to operate it.

What is AB Tasty Flagship's Headless Index score?

AB Tasty Flagship scores 67/100 on the Headless Index thesis-fit rubric and sits in Band B in the Feature Flags & Config category. The score weighs API-first design, headless operation, MCP and agent posture, schema observability, and webhooks.

03 / Scorecard / Feature Flags & Config

AB Tasty Flagship

Headless Index

67/100

JAIRF

N/A

Verified

AUG 20, 2026

Methodology v1 · JAIRF v1.0.0

AB Tasty Flagship earns Band B in the Feature Flags & Config category of The Headless Index, with a thesis-fit score of 67/100. Its strongest dimension is headless operation (16/20); its weakest scored dimension is schema observability (10/20). No public OpenAPI specification was found when AB Tasty Flagship was scored, which limits how far an agent can go without human integration work.

Editorial verdict

AB Tasty Flagship is solidly built for programmatic consumption. The Headless Index thesis-fit score of 67/100 lands it in the upper-middle of the index, and JAIRF is recorded as N/A for this vendor because no public OpenAPI specification was reachable for the open-source scorer. In practice, vendors at this tier ship most of the primitives agents need, with one or two surfaces still leaning on documentation rather than discovery, and the rest of this verdict explains where AB Tasty Flagship lands inside that pattern. On the API surface, the question is whether the API is the product or a layer beneath the dashboard. Two hosts do the work: the Remote Control API at api.flagship.io for management and decision.flagship.io for evaluation, both behind clientId and clientSecret credentials. SDK coverage is wide and versioned (@flagship.io/js-sdk 5.2.1, @flagship.io/react-sdk, flagship-python-sdk, flagship-go-sdk, flagship-java, flagship-android, flagship-flutter-sdk) with OpenFeature providers alongside. An agent can drive this product across most practical workflows, with a handful of edges where documentation reading still beats schema discovery. On headless operability: This is the part the crawler could not see. flagship-io/abtasty-cli is a real Cobra-based CLI with a Homebrew tap, managing projects, campaigns, flags, targeting keys, goals, users, environments and panic mode on top of the Remote Control API. A GitHub Action and VS Code extension exist too (flagship-io/abtasty-action). Credentials themselves must still be minted by a Super Admin in the platform.^[1] On the MCP and agent-integration axis, which is the fastest-moving criterion in the index: AB Tasty ships an MCP server under its own organisation with named tools: decision_api_get_flags, decision_api_get_campaigns, decision_api_activate_campaign and resource_loader_api_load_featexp_resources (github.com/flagship-io/mcp-server), plus assistant prompts and a separate agent-skills repository. The bias is toward evaluation and SDK onboarding rather than full campaign management, and it is absent from the MCP registry, so agents must find it by hand.^[2] Event posture closes the loop: an agent that cannot react to state changes is reduced to polling. Webhooks exist and the event list is short: Flag created, Flag removed, Campaign.status.changed, plus six project and account access-grant events. Payloads combine event-specific fields with common metadata. Everything else is missing, no signature header, no documented retry or replay behaviour, and subscriptions are created by hand in the Integration Hub (Integrations, Feature Experimentation panel) rather than through an API. Net assessment: AB Tasty Flagship can be operated by agents for the majority of practical workflows. The closest thing to a gap is schema observability^[3], which integrators should sanity-check against their own use case before committing. Strong fit for agent-driven use cases.

Verdict by Headless Index pipeline (auto)

// AI-drafted from the evidence layer. Editorial review pending.

Scores

Scorecard detail

Headless Index · 5 sub-criteria

API-first design intent14/20

scored

Two hosts do the work: the Remote Control API at api.flagship.io for management and decision.flagship.io for evaluation, both behind clientId and clientSecret credentials. SDK coverage is wide and versioned (@flagship.io/js-sdk 5.2.1, @flagship.io/react-sdk, flagship-python-sdk, flagship-go-sdk, flagship-java, flagship-android, flagship-flutter-sdk) with OpenFeature providers alongside. The weakness is not the API, it is that the API is documented only as GitBook prose.

signals (4)

+AI review appliedReviewer: Editorial review on 2026-08-19
−OpenAPI specNot found across 34 probe paths
·GraphQL endpointDiscovered at https://www.abtasty.com/graphql, introspection disabled or scoped
−SDKs maintainedNone detected in vendor org

cite (1)

github.sdks@2026-08-19

Headless operation16/20

scored

This is the part the crawler could not see. flagship-io/abtasty-cli is a real Cobra-based CLI with a Homebrew tap, managing projects, campaigns, flags, targeting keys, goals, users, environments and panic mode on top of the Remote Control API. A GitHub Action and VS Code extension exist too (flagship-io/abtasty-action). Credentials themselves must still be minted by a Super Admin in the platform.

signals (9)

+AI review appliedReviewer: Editorial review on 2026-08-19
−API operations exposedNo OpenAPI spec; operations count unknown
·Docs pages crawled0 pages (crawler: none)
·Auth schemes documentedAuth documentation page not reached by crawler
·Setup / quickstart docsNot reached by crawler
·Billing docsNot reached by crawler
·Teams / org docsNot reached by crawler
·CLI docsNot reached by crawler
·Schema / data model docsNot reached by crawler

cite (1)

github.sdks@2026-08-19

MCP & agent posture16/20

scored

AB Tasty ships an MCP server under its own organisation with named tools: decision_api_get_flags, decision_api_get_campaigns, decision_api_activate_campaign and resource_loader_api_load_featexp_resources (github.com/flagship-io/mcp-server), plus assistant prompts and a separate agent-skills repository. The bias is toward evaluation and SDK onboarding rather than full campaign management, and it is absent from the MCP registry, so agents must find it by hand.

signals (4)

+AI review appliedReviewer: Editorial review on 2026-08-19
−Official MCP serverNone found in vendor's GitHub org or the official MCP registry
−Community MCP serversNone found
−Agent-friendly SDKsNo TypeScript/JavaScript SDK published (agents commonly run in TS/JS)

cite (1)

github.sdks@2026-08-19

Schema observability10/20

scored

No machine-readable contract exists. Neither api.flagship.io nor decision.flagship.io serves an OpenAPI document, no schema file sits in the flagship-io repositories, and there is no introspectable GraphQL. What AB Tasty does publish is unusually agent-friendly prose: an llms.txt index and a markdown twin of every page (append .md to any docs.abtasty.com URL). Good for reading, useless for cold client generation.

signals (3)

+AI review appliedReviewer: Editorial review on 2026-08-19
−OpenAPINot discovered across 34 standard probe paths
·GraphQL introspectionGraphQL endpoint at https://www.abtasty.com/graphql but introspection is disabled, scoped, or behind authentication

cite (1)

ai_review_browser.schema@2026-08-19

Webhooks & events11/20

scored

Webhooks exist and the event list is short: Flag created, Flag removed, Campaign.status.changed, plus six project and account access-grant events. Payloads combine event-specific fields with common metadata. Everything else is missing, no signature header, no documented retry or replay behaviour, and subscriptions are created by hand in the Integration Hub (Integrations, Feature Experimentation panel) rather than through an API.

signals (2)

+AI review appliedReviewer: Editorial review on 2026-08-19
·Webhook docs pageNot reached by crawler within budget (0 pages crawled). Cannot confirm whether vendor offers webhooks.

cite (1)

github.sdks@2026-08-19

JAIRF · 6 dimensions

JAIRF · N/A

This vendor does not publish a public OpenAPI specification. JAIRF cannot be computed. The Headless Index score and editorial verdict carry the readiness assessment.

No public OpenAPI specification discovered during collection

Band rationale:B band: JAIRF=N/A HeadlessIndex=67

04 / Embed

Show AB Tasty Flagship's score on your site.

Drop a live badge into your README, footer, or marketing page. It updates automatically when we re-score, and every embed is a dofollow link back here.

Get embed code

Peers in Feature Flags & Config

FlagsmithB

Headless Index 68/100

ConfigCatB

Headless Index 68/100

BucketB

Headless Index 64/100

See full Feature Flags & Config ranking →

FAQ

AB Tasty Flagship and agent readiness

Is AB Tasty Flagship agent-ready?: AB Tasty Flagship scores Band B on The Headless Index. Its JAIRF rating is not available because no machine-readable spec was scored. Its strongest area for agent use is headless operation; its weakest is schema observability.
Does AB Tasty Flagship publish an OpenAPI spec?: No published OpenAPI specification was found when AB Tasty Flagship was scored. That caps its JAIRF dimensions and forces agents to rely on documentation or reverse engineering to operate it.
What is AB Tasty Flagship's Headless Index score?: AB Tasty Flagship scores 67/100 on the Headless Index thesis-fit rubric and sits in Band B in the Feature Flags & Config category. The score weighs API-first design, headless operation, MCP and agent posture, schema observability, and webhooks.