Is MyScale agent-ready?

MyScale scores Band D on The Headless Index. Its JAIRF rating is not available because no machine-readable spec was scored. Its strongest area for agent use is headless operation; its weakest is MCP and agent posture.

Does MyScale publish an OpenAPI spec?

No published OpenAPI specification was found when MyScale was scored. That caps its JAIRF dimensions and forces agents to rely on documentation or reverse engineering to operate it.

What is MyScale's Headless Index score?

MyScale scores 34/100 on the Headless Index thesis-fit rubric and sits in Band D in the Search & Vector DBs category. The score weighs API-first design, headless operation, MCP and agent posture, schema observability, and webhooks.

03 / Scorecard / Search & Vector DBs

MyScale

Headless Index

34/100

JAIRF

N/A

Verified

AUG 20, 2026

Methodology v1 · JAIRF v1.0.0

MyScale earns Band D in the Search & Vector DBs category of The Headless Index, with a thesis-fit score of 34/100. Its strongest dimension is headless operation (10/20); its weakest scored dimension is MCP and agent posture (4/20). No public OpenAPI specification was found when MyScale was scored, which limits how far an agent can go without human integration work.

Editorial verdict

MyScale remains a dashboard-first product with a limited programmatic surface. The Headless Index thesis-fit score of 34/100 sits in the lower band of the index, and JAIRF is recorded as N/A for this vendor because no public OpenAPI specification was reachable for the open-source scorer. In practice, vendors at this tier ship enough API to be useful but not enough to be operated end to end by agents without a human in the loop, and the rest of this verdict explains where MyScale lands inside that pattern. On the API surface, the question is whether the API is the product or a layer beneath the dashboard. MyScale is ClickHouse with vector indexes, so the interface is SQL over the ClickHouse HTTP and native protocols rather than anything MyScale designed. Third-party drivers work (clickhouse-connect, clickhouse-driver), which is the saving grace. An agent cannot drive this product end to end today: the headless surface covers basic CRUD but tapers out before reaching the workflows that matter most. On headless operability: MyScaleDB is open source and self-hostable from the Docker image, so an operator can script a deployment, and every table and index operation is DDL. Beyond that the tooling is bare: no Helm chart in the org, no Terraform provider, no CLI, and cloud cluster provisioning happens in the console only. The core repository (github.com/myscale/MyScaleDB) shows no commits since February 2025.^[1] On the MCP and agent-integration axis, which is the fastest-moving criterion in the index: Nothing exists. No MCP server sits in the vendor org (github.com/myscale lists no server repository), nothing appears in the MCP registry, and the docs contain no agent-oriented section. myscalekb-agent-base and myscalekb-agent-plugin are knowledge base experiments, both with zero stars and no commits since early 2025. Agents reach MyScale only through a generic ClickHouse client.^[2] Event posture closes the loop: an agent that cannot react to state changes is reduced to polling. No event surface of any kind. MyScale registers no callbacks, defines no event types and signs no payloads. The org does publish an OpenTelemetry collector for LLM application traces (github.com/myscale/myscale-telemetry), but that pushes observability data into MyScale rather than emitting anything out of it. Agents watching for index build completion have to poll system.mutations. Net assessment: MyScale is not a strong target for agent-driven workflows today. The weakest link is MCP posture^[3], and the broader surface gives agents too little to operate against. Pick it only when the rest of your stack already mandates it. Use only when locked in.

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 intent8/20

scored

MyScale is ClickHouse with vector indexes, so the interface is SQL over the ClickHouse HTTP and native protocols rather than anything MyScale designed. Third-party drivers work (clickhouse-connect, clickhouse-driver), which is the saving grace. The vendor's own client, myscaledb-client on PyPI, has not been touched since March 2023, and no REST or GraphQL surface is published.

signals (4)

+AI review appliedReviewer: Editorial review on 2026-08-19
−OpenAPI specNot found across 34 probe paths
−GraphQL endpointNot discovered (5 probes; project-scoped endpoints require a real project ID)
·SDKs maintained1 (python); top by stars: myscale/myscaledb-client (3 stars)

cite (1)

github.sdks@2026-08-19

Headless operation10/20

scored

MyScaleDB is open source and self-hostable from the Docker image, so an operator can script a deployment, and every table and index operation is DDL. Beyond that the tooling is bare: no Helm chart in the org, no Terraform provider, no CLI, and cloud cluster provisioning happens in the console only. The core repository (github.com/myscale/MyScaleDB) shows no commits since February 2025.

signals (9)

+AI review appliedReviewer: Editorial review on 2026-08-19
−API operations exposedNo OpenAPI spec; operations count unknown
·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 (1)

github.sdks@2026-08-19

MCP & agent posture4/20

scored

Nothing exists. No MCP server sits in the vendor org (github.com/myscale lists no server repository), nothing appears in the MCP registry, and the docs contain no agent-oriented section. myscalekb-agent-base and myscalekb-agent-plugin are knowledge base experiments, both with zero stars and no commits since early 2025. Agents reach MyScale only through a generic ClickHouse client.

signals (4)

+AI review appliedReviewer: Editorial review on 2026-08-19
−Official MCP serverNone found in vendor's GitHub org or the official MCP registry
−Community MCP serversNone found
−Agent-friendly SDKsNo TypeScript/JavaScript SDK published (agents commonly run in TS/JS)

cite (1)

github.sdks@2026-08-19

Schema observability8/20

scored

No OpenAPI, no GraphQL, no published schema files. What works is inherited from ClickHouse (system.tables, system.columns, DESCRIBE TABLE), and it returns real type information including vector index parameters. That is genuine runtime introspection, but it needs credentials and a live cluster first, and it says nothing about the cloud control plane, which stays undocumented.

signals (3)

+AI review appliedReviewer: Editorial review on 2026-08-19
−OpenAPINot discovered across 34 standard probe paths
−GraphQL introspectionNo GraphQL endpoint discovered (5 probes; some vendors use project-scoped endpoints that require a real project handle)

cite (1)

github.sdks@2026-08-19

Webhooks & events4/20

scored

No event surface of any kind. MyScale registers no callbacks, defines no event types and signs no payloads. The org does publish an OpenTelemetry collector for LLM application traces (github.com/myscale/myscale-telemetry), but that pushes observability data into MyScale rather than emitting anything out of it. Agents watching for index build completion have to poll system.mutations.

signals (2)

+AI review appliedReviewer: Editorial review on 2026-08-19
·Webhook docs pageNot reached by crawler within budget (0 pages crawled). Cannot confirm whether vendor offers webhooks.

cite (1)

github.sdks@2026-08-19

JAIRF · 6 dimensions

JAIRF · N/A

This vendor does not publish a public OpenAPI specification. JAIRF cannot be computed. The Headless Index score and editorial verdict carry the readiness assessment.

No public OpenAPI specification discovered during collection

Band rationale:D band triggered: HeadlessIndex=34

04 / Embed

Show MyScale'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

Peers in Search & Vector DBs

TurbopufferD

Headless Index 36/100

MarqoD

Headless Index 32/100

TavilyF

Headless Index 25/100

See full Search & Vector DBs ranking →

FAQ

MyScale and agent readiness

Is MyScale agent-ready?: MyScale scores Band D on The Headless Index. Its JAIRF rating is not available because no machine-readable spec was scored. Its strongest area for agent use is headless operation; its weakest is MCP and agent posture.
Does MyScale publish an OpenAPI spec?: No published OpenAPI specification was found when MyScale was scored. That caps its JAIRF dimensions and forces agents to rely on documentation or reverse engineering to operate it.
What is MyScale's Headless Index score?: MyScale scores 34/100 on the Headless Index thesis-fit rubric and sits in Band D in the Search & Vector DBs category. The score weighs API-first design, headless operation, MCP and agent posture, schema observability, and webhooks.