# Agnost AI

**Canonical:** https://apis.io/providers/agnost-ai/  
**Website:** https://docs.agnost.ai  
**APIs profiled:** 14

Agnost AI is a production monitoring and product-analytics platform for teams building chat and voice AI agents. It continuously reads production agent conversations, MCP tool calls, and OpenTelemetry traces, clusters recurring intents, feature requests, frustration, and failure patterns, and catches agent failures that offline evals miss. It then turns the highest-impact patterns into reviewed fixes, including pull requests against prompts, tools, and agent harnesses. Agnost is OpenTelemetry-native, works with any LLM and framework, and ships SDKs for Python and TypeScript conversation tracking, MCP-server analytics (Python, TypeScript, Go), plus a hosted OAuth-protected MCP server for querying your dashboard from Claude Desktop, Cursor, and any MCP client. Founded in 2025 and part of Y Combinator's Summer 2026 (S26) batch.

## Kin Score — 52.6 / 100 (developing)

Scored 2026-08-17 under rubric 0.11.0. Trend: flat (+0.0 from 52.6).

| Facet | Score |
|---|---|
| Discoverability | 92.6 |
| Contract Quality | 54.6 |
| Governance | 20.8 |
| Operational Transparency | 26.3 |
| Developer Ergonomics | 69.0 |
| Commercial Clarity | 50.0 |

## Agent readiness — 43.9 (agent-ready)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | no |
| MCP Server | yes |
| Auth Clarity | yes |
| Idempotency | no |
| Error Semantics | documented |
| OpenAPI Examples | partial |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | derived |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Self-serve signup — onboarding: self-serve, pricing: unknown, trial: no (confidence: medium).

## APIs (14)

- **Agnost AI Alerts API** — Alert configuration and monitoring
- **Agnost AI API Keys API** — API key management
- **Agnost AI Auth API** — OAuth authentication callbacks
- **Agnost AI Billing API** — Stripe billing management
- **Agnost AI Classification API** — LLM-based classification operations
- **Agnost AI Connections API** — External integrations (Slack)
- **Agnost AI Conversations API** — Conversation message and span retrieval
- **Agnost AI Dashboard API** — Analytics and metrics for the dashboard
- **Agnost AI Onboarding API** — First-run helpers used during organization setup
- **Agnost AI Organizations API** — Organization management
- **Agnost AI SDK API** — Event ingestion endpoints used by SDKs
- **Agnost AI Sentiments API** — Sentiment and intent analysis
- **Agnost AI SOPs API** — Standard Operating Procedures
- **Agnost AI System API** — Health checks, webhooks, internal endpoints

## MCP servers (2)

- **Agnost MCP Server** — Hosted, OAuth 2.1-protected MCP server (streamable-HTTP) for querying your Agnost dashboard from Claude Desktop, Cursor, and any MCP client.
- **agnost-ai-mcp.yml**

## Security (3)

- **Agnost Ai Authentication** — apiKey/http · 3 schemes
- **Agnost Ai Domain Security** — TLSv1.3 · HSTS
- **Agnost Ai Trust Center** — trust center published

## Tags

Company, AI Agents, Agent Analytics, Observability, OpenTelemetry, Model Context Protocol, Conversational AI, Monitoring, Developer Tools, Analytics

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/agnost-ai/). Scores are computed from the provider's own public artifacts under a published rubric.