# Chalk

**Canonical:** https://apis.io/providers/chalk/  
**Website:** https://chalk.ai  
**APIs profiled:** 1

Chalk is a real-time AI/ML data platform ("Context Engine") that lets teams define features, embeddings, LLM outputs, and prompts once in Python and serve them everywhere — training, real-time inference, and agents — computed on infrastructure the customer controls. Instead of stitching together a feature store, vector database, retrieval and prompt tooling, orchestration, and a sandbox runtime, Chalk unifies them: features are point-in-time correct, served in single-digit milliseconds, and deployed via a branch-based model inside the customer's own cloud. It exposes a REST API and gRPC client libraries (Python, TypeScript, Go, Java, C#), a first-party CLI, OAuth 2.0 authentication, and MCP-scoped agent access. Backed by Felicis and General Catalyst.

## Kin Score — 38.8 / 100 (thin)

Scored 2026-08-30 under rubric 0.17.2. Trend: flat (+0.0 from 38.8).

| Facet | Score |
|---|---|
| Discoverability | 75.9 |
| Contract Quality | 0.0 |
| Governance | 18.2 |
| Contract Governance | 18.2 |
| Operational Transparency | 44.7 |
| Developer Ergonomics | 73.8 |
| Commercial Clarity | 42.1 |
| Access Clarity | 42.1 |

## Agent readiness — 10.8 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | served |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |
| Delegated Identity | served |
| Protected Resource Metadata | no |
| Dynamic Client Registration | no |
| Agentic Commerce | no |

## Access

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

## APIs (1)

- **Chalk API** — REST + gRPC API for querying features from the Chalk Context Engine — online single-row queries, bulk (feather/Arrow) queries, and asynchronous offline dataset generation — plus...

## MCP servers (1)

- **Chalk MCP Server**

## Security (3)

- **Chalk Authentication** — oauth2/http · 3 schemes
- **Chalk Domain Security** — TLSv1.3 · HSTS · DMARC
- **Chalk Vulnerability Disclosure** — contact published

## Tags

Company, Machine-Learning, Feature Store, Artificial Intelligence, Data Platform, MLOps, Real-Time Data, LLM, Agents, Feature Engineering

---

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