Coval

Coval is the deployment-readiness platform for voice and chat AI agents. Teams simulate thousands of realistic conversation scenarios before launch, monitor real production calls, and improve reliability with metrics and human review. Coval supports inbound/outbound voice, standard chat, chat over WebSocket, chat A2A (JSON-RPC), voice-to-voice models (OpenAI Realtime, Gemini Live), SMS, Pipecat, and LiveKit agents. Its v1 REST API, TypeScript and Python SDKs, Homebrew CLI, and hosted MCP server let developers connect agents, define personas and test sets, launch simulation runs, ingest production conversations and OpenTelemetry traces, define deterministic/statistical/ML/LLM-judge metrics, and route critical calls to human reviewers. Coval is backed by General Catalyst and is SOC 2 Type II, GDPR, and HIPAA compliant.

Kin Score

This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.

How we profile Coval

Each block below is one kind of artifact we hold for Coval. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.

APIs 25

Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.

Individual APIs this provider publishes, each with its own machine-readable definition.

Coval Agents API

CRUD operations for AI agent configurations

Coval API Keys API

Manage API keys for your organization

Coval Audio API

Upload audio for evaluation and access conversation audio files

Coval Conversations API

Submit and manage real-world conversation monitoring evaluations

Coval Dashboards API

Dashboard CRUD operations

Coval Metric Outputs API

Retrieve metric computation results for simulations

Coval Metrics API

CRUD operations for custom evaluation metrics

Coval Monitor Events API

Monitor evaluation event history

Coval Monitors API

CRUD operations for monitor definitions

Coval Mutations API

CRUD operations for agent configuration mutations

Coval Organization Conversations Config API

Organization-level configuration for conversation metrics — the default and conditional metrics run on conversations.

Coval Personas API

Persona CRUD operations

Coval Reports API

CRUD operations for saved multi-run reports

Coval Review Annotations API

Annotation CRUD operations

Coval Review Projects API

Project CRUD operations

Coval Run Templates API

CRUD operations for reusable run configurations

Coval Runs API

Launch and manage simulation runs

Coval Scheduled Runs API

CRUD operations for scheduled evaluations

Coval Simulations API

Launch and manage individual simulation executions

Coval Tags API

CRUD operations for resource tags

Coval Test Cases API

Operations for managing test cases

Coval Test Sets API

Operations for managing test sets

Coval Traces API

OTLP trace ingestion for simulations and monitoring conversations.

Coval Webhooks API

CRUD operations for event webhooks

Coval Widgets API

Dashboard widget CRUD operations

Scroll within the panel for all 25 ·

MCP Servers 1

Model Context Protocol servers expose these APIs directly to AI agents. We profile them because agent-native access is the fastest-growing way this provider's capabilities actually get used.

Model Context Protocol servers that expose these APIs to AI agents.

coval-mcp.yml

MCP SERVER

Event Specifications 1

Not every API is request/response. AsyncAPI describes the event-driven and streaming side — the webhooks and channels — so the asynchronous half of the interface is documented the same way the synchronous half is.

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Coval Webhooks

ASYNCAPI

Security Posture 3

Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Coval Authentication

apiKey · 2 schemes

SECURITY

Coval Domain Security

TLSv1.2 · DMARC

SECURITY

Coval Trust Center

SOC 2 Type II, GDPR, HIPAA

SECURITY

Agentic Access 1

An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.

Recommended x-agentic-access execution contracts for AI agents.

Coval Agentic Access

151 operations · 86 acting

151 operations · 86 acting

AGENTIC

Resources

Every other property we hold for Coval — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.

← All providers · Data indexed from github.com/api-evangelist/coval · machine-readable index on apis.io