03 / Scorecard / AI Platforms

Vapi

Name: Vapi Agent Readiness Scorecard
Item: Vapi
Rating: 75
Author: Headless Index pipeline (auto)

Headless Index

75/100

denominator 80

JAIRF

71/100

AI-Aware

Verified

MAY 21, 2026

Methodology v1 · JAIRF v1.0.0

Editorial verdict

Vapi is solidly built for programmatic consumption. The Headless Index thesis-fit score of 75/100 lands it in the upper-middle of the index, and JAIRF v1.0.0 puts it at 71/100 (Level 2, AI-Aware). 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 Vapi lands inside that pattern. On the API surface, the question is whether the API is the product or a layer beneath the dashboard. Vapi is a voice AI agent platform: it combines STT (multi-provider), LLM (Claude, GPT, Gemini, etc.), TTS (ElevenLabs, PlayHT, Deepgram), and call orchestration into a single API. The REST API at api.vapi.ai exposes assistants, calls, phone numbers, blocks (workflow primitives), squads, tools, and analytics. SDKs in TypeScript, Python, and Swift. The product is API-first by design.^[1] Schema observability is the related test: can an agent introspect the contract from cold, or does it have to read prose documentation to do so? Public OpenAPI at api.vapi.ai/api-json. Schema discoverability is reference-class for voice-agent platforms.^[2] 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: Assistants, phone numbers (Twilio and Vonage integrations), calls, tools, blocks, squads, files, analytics, and workflow logic are all programmable. The Vapi dashboard handles credential management; everything else is API-driven. Test mode through the playground.^[3] On the MCP and agent-integration axis, which is the fastest-moving criterion in the index: Vapi is explicitly an agent platform. Assistants can be configured with arbitrary tools, including MCP-style external services. The agent-first positioning makes Vapi one of the more agent-native products in the category.^[4] Event posture closes the loop: an agent that cannot react to state changes is reduced to polling. On webhooks and events, the docs crawler did not locate a webhooks reference page or events catalog. Editorial review should confirm whether the vendor publishes events at all, and if so whether signing and replay are documented. Net assessment: Vapi can be operated by agents for the majority of practical workflows. The closest thing to a gap is headless operability^[5], 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 intent15/20

scored

Vapi is a voice AI agent platform: it combines STT (multi-provider), LLM (Claude, GPT, Gemini, etc.), TTS (ElevenLabs, PlayHT, Deepgram), and call orchestration into a single API. The REST API at api.vapi.ai exposes assistants, calls, phone numbers, blocks (workflow primitives), squads, tools, and analytics. SDKs in TypeScript, Python, and Swift. The product is API-first by design.

signals (6)

+AI review appliedReviewer: Editorial review on 2026-05-20
+OpenAPI specPublished, 79 operations
−GraphQL endpointNot discovered (5 probes; project-scoped endpoints require a real project ID)
+SDKs maintained15 (dotnet, go, javascript, kotlin, php, python, ruby, swift, typescript); top by stars: VapiAI/client-sdk-python (120 stars)
+SDK recency9 of 15 SDK repos pushed within 30 days (most recent SDK commit: 2026-05-15)
+npm weekly downloads236.9k across published packages; top: @vapi-ai/web @ 134.9k/week

cite (5)

openapi.url@2026-05-20
graphql.probes_tried@2026-05-20
github.sdks@2026-05-20
freshness.most_recent_sdk_commit@2026-05-20
github.sdks@2026-05-20

Headless operation10/20

scored

Assistants, phone numbers (Twilio and Vonage integrations), calls, tools, blocks, squads, files, analytics, and workflow logic are all programmable. The Vapi dashboard handles credential management; everything else is API-driven. Test mode through the playground.

signals (9)

+AI review appliedReviewer: Editorial review on 2026-05-20
·API operations exposed79 operations in OpenAPI spec
·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 (8)

openapi.operations_count@2026-05-20
docs.pages_crawled@2026-05-20
docs.pages_crawled@2026-05-20
docs.topics_found.setup@2026-05-20
docs.topics_found.billing@2026-05-20
docs.topics_found.teams@2026-05-20
docs.topics_found.cli@2026-05-20
docs.topics_found.schema@2026-05-20

MCP & agent posture20/20

scored

Vapi is explicitly an agent platform. Assistants can be configured with arbitrary tools, including MCP-style external services. The agent-first positioning makes Vapi one of the more agent-native products in the category.

signals (4)

+AI review appliedReviewer: Editorial review on 2026-05-20
+Official MCP serverhttps://github.com/VapiAI/mcp-server (51 stars, last commit 13 days ago)
−Community MCP serversNone found
+Agent-friendly SDKs6 TS/JS SDKs available; top: @vapi-ai/web (134.9k/week downloads)

cite (3)

mcp.official_server.url@2026-05-20
mcp.github_search_query@2026-05-20
github.sdks@2026-05-20

Schema observability15/20

scored

Public OpenAPI at api.vapi.ai/api-json. Schema discoverability is reference-class for voice-agent platforms.

signals (3)

+AI review appliedReviewer: Editorial review on 2026-05-20
+OpenAPIPublished at https://api.vapi.ai/api-json (OpenAPI 3.0.0, 79 operations)
−GraphQL introspectionNo GraphQL endpoint discovered (5 probes; some vendors use project-scoped endpoints that require a real project handle)

cite (2)

openapi.url@2026-05-20
graphql.probes_tried@2026-05-20

Webhooks & eventsUnknown

Unknown

Vapi webhooks deliver call status updates, conversation events, and function-call notifications with HMAC signing. The event-driven model is central because voice calls are inherently asynchronous.

signals (2)

+AI review appliedReviewer: Editorial review on 2026-05-20
·Webhook docs pageNot reached by crawler within budget (0 pages crawled). Cannot confirm whether vendor offers webhooks.

cite (1)

docs.pages_crawled@2026-05-20

JAIRF · 6 dimensions

FCFoundational Compliance

70/100

Structural validity, standards conformance, and parsability of the OpenAPI specification.

DXJDeveloper Experience & Tooling Compatibility

42.8/100

Documentation clarity, example coverage, response completeness, and ingestion health.

ARAXAI-Readiness & Agent Experience

45.4/100

Semantic clarity, intent expression, datatype specificity, and error standardization.

AUAgent Usability

100/100

Operational composability, complexity comfort, navigation affordances, and safety patterns.

SECSecurity

100/100

Authentication strength, transport security, secret hygiene, and OWASP risk posture.

AIDAI Discoverability

65/100

Descriptive richness, intent phrasing, workflow context, and registry signals.

Band rationale:B band: JAIRF=71 HeadlessIndex=75

04 / Embed

Show Vapi'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

Calibration

How THI compares to external scorers

Source	Score	Measures	Last checked
Fern Agent Score	not found	Documentation completeness and SDK shape (~22 checks)	—
CLIRank Agent Friendliness	86 · Good	CLI readiness, docs quality, and overall agent affordances	—
Cloudflare Is It Agent Ready?	blocked	Cloudflare's manual agent-readiness heuristic per vendor URL	—
Jentic Scorecard	—	JAIRF-based scorecard requiring a public OpenAPI specification	—

THI 75 vs external median 86, delta -11

THI display 75 vs external median 86 (delta -11). Within calibration band.

Peers in AI Platforms

ApifyA

Headless Index 75/100

ReplicateB

Headless Index 76/100

Hugging FaceC

Headless Index 74/100

See full AI Platforms ranking →