# AfterQuery

**Canonical:** https://apis.io/providers/afterquery/  
**Website:** https://www.afterquery.com/  
**APIs profiled:** 1

AfterQuery is a San Francisco applied research lab that curates expert reasoning data for frontier foundation models - supervised fine-tuning sets, rubric- and verifier-based reinforcement-learning environments, tool-calling and computer-use environments, RLHF, deep research tasks, multimodal data, and custom evaluation suites - produced with a network of verified professionals in finance, healthcare, law and software engineering through its AfterQuery Experts contributor platform. It publishes the IDE-Bench, App-Bench, Market-Bench, FinanceArena and FinanceQA benchmarks and sells data and evaluation engagements directly to AI labs and enterprises. AfterQuery ships no public product API: its only machine-callable surface is an anonymous documentation MCP server on its help-centre host, alongside an A2A agent card, a published agent skill and two llms.txt files.

## Kin Score — 23.7 / 100 (emerging)

Scored 2026-10-03 under rubric 0.23.0. Trend: flat (+0.0 from 23.7).

| Facet | Score |
|---|---|
| Discoverability | 75.0 |
| Contract Quality | 0.0 |
| Contract Governance | 18.2 |
| Operational Transparency | 2.6 |
| Developer Ergonomics | 35.7 |
| Access Clarity | 27.6 |

Regulatory layer — **Horizontal (data, software, accessibility, platform)**: 22.7 (matched via fallback).

## Agent readiness — 17.8 (agent-aware)

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

## APIs (1)

- **AfterQuery Experts Help Center MCP** — A read-only Model Context Protocol server over the AfterQuery Experts Help Center, served anonymously from AfterQuery's documentation host. Three tools - full-text documentation...

## MCP servers (1)

- **AfterQuery Experts Help Center MCP** — A read-only documentation MCP server over the AfterQuery Experts Help Center - full-text search across the help centre, a sandboxed read-only filesystem view of the documentatio...

## Security (2)

- **Afterquery Authentication** — 1 scheme
- **Afterquery Domain Security** — TLSv1.3 · HSTS · DMARC

## Plans (1)

- **Afterquery Plans Pricing**

## Tags

Company, Artificial Intelligence, Machine Learning, Training Data, Data, Evaluation, Reinforcement Learning, Benchmarks, Research, Agents, MCP, A2A

---

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