Kinetica is a GPU-accelerated, real-time analytical database that unifies relational (SQL), vector, graph, geospatial, time-series and OLAP workloads in a single query engine, aimed at applications needing millisecond-latency analytics over continuously streaming data. Grown out of a GPU-accelerated geospatial and temporal engine built for U.S. Army Intelligence (INSCOM) in 2009, it is deployed today as the retrieval and reasoning layer behind AI agents and LLM-powered systems. The database is consumed through a POST-only JSON REST API (/execute/sql, /show/table, /insert/records/json, /filter/*, /aggregate/*, /match/graph and friends) served from each deployment on port 9191, plus first-party client libraries for Python, Java, C++, C#, JavaScript/Node.js and Go, JDBC/ODBC drivers, and the KiSQL command-line client. For agents, Kinetica publishes an A2A agent card and an installable Agent Skills package on its documentation host, and ships Toolbelt — an OAuth-protected hosted MCP server exposing toolbelt_* tools for SQL, vector search, graph traversal, schema introspection and ingest-job inspection.
Kinetica is listed with 3 APIs on the APIs.io network. Tagged areas include Database, Analytics, gpu-acceleration, Real-Time Analytics, and Vector Search.
Kinetica’s developer surface includes documentation, API reference, getting-started guide, support, engineering blog, pricing, signup flow, and 28 more developer resources.
49.1/100developing▬ flatAgent27/100agent awareFront door AI5/6
prominent
Heartbeat94/100
alive
saas
Full breakdown ↓
scored 2026-11-06 · rubric v0.27.0 · Show this score on your site →
Regulatory Posture applies to this provider. Its tags matched the
Horizontal (data, software, accessibility, platform) regime, so
Regulatory Posture carries 15 points of the composite.
If this regime is wrong for your business, say so on your
provider repo — the
applicability map is public and we will correct it.
Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for
this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero:
never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and
several others — scorable at all.
The six quality facets above are damped to 85 points between them,
because the conditional facet above carries the other
15. That is why each facet's contribution is shown against a damped
maximum: raising a quality facet moves the composite by 85% of its nominal
weight, not 100%. The full arithmetic is at apis.io/rating/.
Show this score on your site.
It updates itself when the score changes. Paste this where you link to your API docs:
<a href="https://apis.io/providers/kinetica/"><img src="https://apis.io/badge/kinetica/card.svg" alt="Kinetica on APIs.io — Kin Score by API Evangelist"></a>
Other styles, a README pill and a shields.io endpoint are on the badge page.
Raise your score.
Agent readiness — checks not met, largest first (exact, from this profile):
Idempotency+9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented)
A2A Agent Card+8 pts — a2a/-a2a.yml manifest, graded on conformance.grade against A2A 1.0.0
Rate-Limit Signaling+7 pts — OpenAPI responses document X-RateLimit-* / RateLimit headers (verified), else a rate_limits artifact or RateLimits link (documented)
Request/Response Examples+7 pts — share of operations carrying request/response examples; else an Examples / Code Samples link
6 more unmet checks in the Agent Readiness table above.
Kin Score — facets with the most composite points still available (weight × headroom):
The Kin Score Market layer reads a provider inside its market:
its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted:
not part of the Kin Score or agent readiness.
Registered MCP server and declares compatibility are report only — not weighted.
Undeclared means we found nothing we can read, so there is no number: we never infer integrations.
Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.
POST-only JSON REST API exposed by every Kinetica deployment on port 9191. Endpoints cover SQL execution (/execute/sql), record ingest and egress (/insert/records/json, /get/rec...
Hosted Model Context Protocol server that gives any MCP-speaking agent a single endpoint onto a Kinetica database. Exposes toolbelt_* tools for SQL execution, vector search, kno...
Read-only Model Context Protocol server over the published Kinetica documentation site, advertised from https://docs.kinetica.com/.well-known/mcp.json with authentication none. ...
aid: kinetica
name: Kinetica
description: Kinetica is a GPU-accelerated, real-time analytical database that unifies relational (SQL), vector, graph, geospatial,
time-series and OLAP workloads in a single query engine, aimed at applications needing millisecond-latency analytics over
continuously streaming data. Grown out of a GPU-accelerated geospatial and temporal engine built for U.S. Army Intelligence
(INSCOM) in 2009, it is deployed today as the retrieval and reasoning layer behind AI agents and LLM-powered systems. The
database is consumed through a POST-only JSON REST API (/execute/sql, /show/table, /insert/records/json, /filter/*, /aggregate/*,
/match/graph and friends) served from each deployment on port 9191, plus first-party client libraries for Python, Java,
C++, C#, JavaScript/Node.js and Go, JDBC/ODBC drivers, and the KiSQL command-line client. For agents, Kinetica publishes
an A2A agent card and an installable Agent Skills package on its documentation host, and ships Toolbelt — an OAuth-protected
hosted MCP server exposing toolbelt_* tools for SQL, vector search, graph traversal, schema introspection and ingest-job
inspection.
deliveryModel:
model: saas
open_source: false
commercial: true
callable_host: false
label: Hosted service · you call their endpoint
confidence: medium
source:
- pricing
generated: '2026-08-28'
method: derived
accessModel:
pricing: freemium
onboarding: self-serve
trial: false
try_now: true
public: false
gated: none
gated_source:
- onboarding
label: Freemium · Self-serve signup
confidence: high
source:
- plans
- authentication
- scopes
- security
- sandbox
generated: '2026-11-06'
method: derived
image: https://kinetica-web-assets.s3.us-east-1.amazonaws.com/assets/og-image.png
url: https://raw.githubusercontent.com/api-evangelist/kinetica/refs/heads/main/apis.yml
x-type: company
x-source: harvest:secondary-market
x-tier: profiled
x-tier-reason: enrichment-pipeline
specificationVersion: '0.23'
created: '2026-08-04'
modified: '2026-08-04'
x-docs-platform: mintlify
x-docs-platform-confidence: medium
x-docs-platform-checked: 2026-10-03
tags:
- Database
- Analytics
- gpu-acceleration
- Real-Time Analytics
- Vector Search
- Graph Analytics
- Geospatial
- Time Series
- SQL
- Streaming
- Data Infrastructure
- MCP
- Agent-Native
- RAG
- A2A
tags_raw:
- database
- analytics
- gpu-acceleration
- real-time-analytics
- vector-search
- graph-analytics
- geospatial
- time-series
- sql
- streaming
- data-infrastructure
- mcp
- agent-native
- rag
- A2A
maintainers:
- FN: Kin Lane
email: kin@apievangelist.com
- FN: APIs.json
email: info@apis.io
apis:
- name: Kinetica Database REST API
description: POST-only JSON REST API exposed by every Kinetica deployment on port 9191. Endpoints cover SQL execution (/execute/sql),
record ingest and egress (/insert/records/json, /get/records/json), schema and metadata introspection (/show/table, /show/graph,
/show/system/properties), filtering (/filter/byarea, /filter/byradius), aggregation (/aggregate/groupby, /aggregate/statistics,
/aggregate/histogram, /aggregate/kmeans), graph creation and solving (/create/graph, /match/graph) and cluster administration
(/admin/rebalance, /admin/show/cluster/operations). Authentication is HTTP Basic or an OAuth 2.0 bearer token. The base
URL is deployment-specific — clusters are self-hosted or provisioned through Kinetica Cloud — so there is no single public
production host.
humanURL: https://docs.kinetica.com/7.2/api/rest/
baseURL: https://cloud.kinetica.com/
x-base-url-note: Deployment-specific. The documented form is http://<db.host>:9191 for a self-managed cluster; cloud.kinetica.com
is the Kinetica Cloud provisioning console that issues a per-cluster host.
tags:
- Database
- SQL
- Analytics
- Vector Search
- Graph Analytics
- Geospatial
- Time Series
tags_raw:
- database
- sql
- analytics
- vector-search
- graph-analytics
- geospatial
- time-series
properties:
- type: Documentation
url: https://docs.kinetica.com/7.2/
- type: APIReference
url: https://docs.kinetica.com/7.2/api/rest/
- type: GettingStarted
url: https://docs.kinetica.com/7.2/guides/quickstart-guide/
- type: Authentication
url: authentication/kinetica-authentication.yml
- type: Conventions
url: conventions/kinetica-conventions.yml
- type: ErrorCatalog
url: errors/kinetica-error-codes.yml
- name: Kinetica Toolbelt MCP Server
description: Hosted Model Context Protocol server that gives any MCP-speaking agent a single endpoint onto a Kinetica database.
Exposes toolbelt_* tools for SQL execution, vector search, knowledge-graph traversal, schema introspection and ingest-job
inspection, with namespace isolation between datasets. Protected by OAuth 2.0 (RFC 9728 protected-resource metadata, authorization
server at app.toolbelt.ai, scope mcp:tools, PKCE S256, dynamic client registration). Installable in one command with npx
@toolbeltai/cli, or self-hosted via the Helm chart.
humanURL: https://www.kinetica.com/agents
baseURL: https://mcp.toolbelt.ai/mcp
tags:
- MCP
- Agent-Native
- Database
- Vector Search
- Graph Analytics
tags_raw:
- mcp
- agent-native
- database
- vector-search
- graph-analytics
properties:
- type: MCPServer
url: mcp/kinetica-mcp.yml
- type: Documentation
url: https://www.toolbelt.ai
- type: OAuthScopes
url: scopes/kinetica-scopes.yml
- name: Kinetica Docs MCP Server
description: Read-only Model Context Protocol server over the published Kinetica documentation site, advertised from https://docs.kinetica.com/.well-known/mcp.json
with authentication none. Exposes search_kinetica_docs (full-text search across the docs knowledge base), query_docs_filesystem_kinetica_docs
(read-only shell-like queries against a virtualized in-memory filesystem of the docs tree) and submit_feedback (report
a documentation defect). Scoped to public site content; the server performs no database actions.
humanURL: https://docs.kinetica.com/
baseURL: https://kinetica.main-kill-isr.mintlify.me/mcp
tags:
- MCP
- Documentation
- Agent-Native
tags_raw:
- mcp
- documentation
- agent-native
properties:
- type: MCPServer
url: mcp/kinetica-docs-mcp.yml
- type: Documentation
url: https://docs.kinetica.com/
common:
- type: Plans
url: plans/kinetica-plans-pricing.yml
- type: VulnerabilityDisclosure
url: security/kinetica-vulnerability-disclosure.yml
- type: DomainSecurity
url: security/kinetica-domain-security.yml
- type: Website
url: https://www.kinetica.com/
- type: DeveloperPortal
url: https://docs.kinetica.com/
- type: Documentation
url: https://docs.kinetica.com/7.2/
- type: APIReference
url: https://docs.kinetica.com/7.2/api/
- type: GettingStarted
url: https://docs.kinetica.com/7.2/guides/quickstart-guide/
- type: Support
url: https://www.kinetica.com/support
- type: Blog
url: https://www.kinetica.com/blog
- type: GitHubOrganization
url: https://github.com/kineticadb
- type: Pricing
url: https://www.kinetica.com/pricing
- type: SignUp
url: https://cloud.kinetica.com/
- type: TermsOfService
url: https://www.kinetica.com/terms-of-service
- type: PrivacyPolicy
url: https://www.kinetica.com/privacy-policy
- type: ChangeLog
url: https://docs.kinetica.com/7.2/release/
- type: ChangeLog
url: changelog/kinetica-changelog.yml
- type: Security
url: https://www.kinetica.com/.well-known/security.txt
- type: SecurityTxt
url: well-known/kinetica-security.txt
- type: WellKnown
url: well-known/kinetica-well-known.yml
- type: AgentCard
url: a2a/kinetica-a2a.yml
- type: AgentSkill
url: skills/_index.yml
- type: MCPServer
url: mcp/kinetica-mcp.yml
- type: Packages
url: packages/kinetica-packages.yml
- type: SDKs
url: packages/kinetica-packages.yml
- type: LLMsTxt
url: llms/kinetica-llms.txt
- type: Authentication
url: authentication/kinetica-authentication.yml
- type: OAuthScopes
url: scopes/kinetica-scopes.yml
- type: Conventions
url: conventions/kinetica-conventions.yml
- type: ErrorCatalog
url: errors/kinetica-error-codes.yml
- type: Lifecycle
url: lifecycle/kinetica-lifecycle.yml
- type: Conformance
url: conformance/kinetica-conformance.yml
- type: CLI
url: cli/kinetica-cli.yml
- type: Components
url: components/kinetica-components.yml
- type: Sandbox
url: sandbox/kinetica-sandbox.yml
x-enrichment:
date: '2026-08-04'
status: enriched
artifacts_added: 27
pass: local-v1
x-a2a:
verified: true
probed: '2026-09-26'
url: https://docs.kinetica.com/.well-known/agent-card.json
grade: conformant
protocol_version: '0.3'
control: 404
Kinetica API — frequently asked questions
Does Kinetica have an API?
Yes. APIs.io lists 3 APIs from Kinetica, including Kinetica Database REST API, Kinetica Toolbelt MCP Server and Kinetica Docs MCP Server.
How do I authenticate with the Kinetica API?
Kinetica documents its authentication (http/oauth2 · 4 schemes). The details are profiled on APIs.io as Kinetica Authentication.
How much does the Kinetica API cost?
Kinetica publishes its prices; its Developer Edition (Shared Cloud) plan is Free forever as of 2026-10-28. APIs.io lists 3 pricing plans for Kinetica, with each plan's price, limits and inclusions under Pricing on this page.
Does Kinetica have an MCP server?
Yes. APIs.io lists 2 MCP servers for Kinetica: Remote MCP server at mcp.toolbelt.ai over HTTP; 5 tools listed.
Is the Kinetica API ready for AI agents?
Kinetica has a Kin Score of 49.1 out of 100 (developing) and an Agent Readiness score of 27.3 (agent-aware), scored by API Evangelist on 2026-11-06.
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we
store it to create your key and to recognise you if you sign in with another
provider. See our Privacy Policy and
Terms.
Kin Score
How this is scored →
It updates itself when the score changes. Paste this where you link to your API docs: