KinToolkit Public Catalog and MCP HTTP API
64
AI ReadinessAI-Aware (B)64/100
Official vendor OpenAPI document · agent-readyHealthcarePharmacynone2 EndpointsREST
For Agents
Look up public US liquid medicine label references, list calculator-supported bottles, and read published label directions for an exact bottle and concentration, without sending patient details.
Use for: Find the label reference for a children's liquid acetaminophen bottle, List the bottles the KinToolkit calculators support, Get the published label directions for an exact bottle and concentration, Check which manufacturer source a label reference comes from
Not supported: Does not provide personalised dosing, prescriptions, drug interaction checks, or patient records. Use for educational lookup of published US liquid medicine label references only.
The KinToolkit API looks up published US liquid medicine label references for educational use, not personalised prescriptions. A public discovery document lists the calculators, label references, manufacturer sources, and Markdown alternatives, and a JSON-RPC tool endpoint answers three tool calls: find_label_references, list_calculator_bottles, and get_label_directions. It needs no API key and accepts no patient details; results keep the age restrictions, directions, maximum, and source together so the full package label can be checked.
Install Jentic One Beta
Connect the KinToolkit Public Catalog and MCP HTTP API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the KinToolkit Public Catalog and MCP HTTP API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fkintoolkit.com%2Fkintoolkit" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fkintoolkit.com%2Fkintoolkit" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with KinToolkit Public Catalog and MCP HTTP API.
Read the public discovery document of calculators, label references, and manufacturer sources from /api/catalog.json
Find label references for a public brand, ingredient, and bottle audience with the find_label_references tool
List the exact bottles and concentrations the calculators support with list_calculator_bottles
Return the published label directions, age restrictions, and maximum for an exact listed bottle with get_label_directions
Link each answer back to its manufacturer source so the full package label can be verified
Use Cases
Patterns agents use KinToolkit Public Catalog and MCP HTTP API for, with concrete tasks.
★ AI agent label reference lookup through Jentic
A family health assistant needs to point a parent to the published label for a liquid medicine without giving personalised dosing. Through Jentic the agent finds the KinToolkit tool operation, sends only the public brand, ingredient, and bottle audience to find_label_references, and returns the matching reference with its manufacturer source. The agent never forwards names, measurements, or medical history, and it asks which bottle is meant when matches are ambiguous.
Call POST /api/mcp with a tools/call request for find_label_references using only the brand name and bottle audience, then return the reference title, url, and manufacturer source
Published directions for an exact bottle
Once the exact bottle is known, list_calculator_bottles confirms it is calculator-supported and get_label_directions returns the published label band with its age restrictions, maximum, and source kept together. Store-brand entries are reference-only and are not treated as substitutes, and the API does not interpolate or convert concentrations.
Call list_calculator_bottles through POST /api/mcp, confirm the user's exact bottle and concentration are listed, then call get_label_directions for that bottle and show the directions with the source
Discovery for health content sites
A health content site can read the public discovery document to list every KinToolkit calculator and label reference, with links to the calculator page, its Markdown alternative, and the manufacturer source. The document accepts no patient data or dosing inputs.
Call GET /api/catalog.json and return the title, url, and manufacturerSource for every entry in calculators
Key Endpoints
2 endpoints — the kintoolkit api looks up published us liquid medicine label references for educational use, not personalised prescriptions.
METHOD
PATH
DESCRIPTION
GET
/api/catalog.json
Read the public calculator and label-reference catalog
POST
/api/mcp
Send one JSON-RPC tool call or protocol message
GET
/api/catalog.json
Read the public calculator and label-reference catalog
POST
/api/mcp
Send one JSON-RPC tool call or protocol message
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
K
KinToolkit Public Catalog and MCP HTTP API
- AI-Aware (B)64/100
84
Foundational Compliance63
Developer Experience & Jentic Compatibility43
AI-Readiness & Agent Experience94
Agent Usability100
Security50
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
84
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: ASignals: 4
99%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
35%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
63
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B-Signals: 4
1%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
50%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
43
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: DSignals: 4
11%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
62%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
100
Security
Trust, risk posture, and security compliance.
Grade: A+Signals: 1
100%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
50
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: C-Signals: 1
50%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring KinToolkit by hand means building JSON-RPC envelopes, negotiating the protocol version headers, and respecting its per-IP firewall window. Through Jentic you install once, import KinToolkit from the API Directory, and your agent calls it with no credential to manage.
Permission scoping
KinToolkit has one read-only discovery operation and one JSON-RPC operation, and the tool name travels in the request body. Limit the agent to the operations it needs, such as reading the discovery document: rules bound which operations your agent may call, not which tool inside the JSON-RPC call.
Credential isolation
KinToolkit needs no credential, so there is nothing to store, and calls run through your own Jentic One instance rather than from inside the agent's context.
Intent-based discovery
Agents search Jentic by intent such as 'find a medicine label reference' or 'list calculator bottles', and Jentic returns the matching KinToolkit operation with its input schema so the agent sends a well-formed request without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using KinToolkit Public Catalog and MCP HTTP API through Jentic.
What authentication does the KinToolkit API use?
None. Per its OpenAPI spec, both operations are public and need no API key or token, and no persistent protocol session is required. Never send patient names, exact measurements, or medical history in a request.
Does the KinToolkit API give personalised dosing advice?
No. It returns educational references to published US liquid medicine labels. get_label_directions works only for an exact listed calculator bottle, concentration, and published label band, and the answer keeps the age restrictions, directions, maximum, and source together. Verify the full package label and ask a clinician when unsure.
What are the rate limits for the KinToolkit API?
Per the OpenAPI spec, the hosting firewall limits /api/mcp to 120 HTTP requests per IP per 60-second fixed window in each region, counting every protocol message. Over the cap the firewall rejects requests; honor a valid Retry-After value when present, otherwise wait at least 60 seconds and back off with jitter.
Is there a KinToolkit MCP server?
KinToolkit publishes its tools on a JSON-RPC endpoint at /api/mcp, and you don't need to install a separate server to give your agent access. Jentic connects the API directly from the API Directory: import it and your agent calls the label tools on demand without loading another server's tool definitions into its context.
Can I limit what my agent is allowed to do with the KinToolkit API?
Yes. For example, write a rule that allows only GET /api/catalog.json, so the agent can read the discovery document of calculators and label references but cannot send tool calls. Because the tool name travels in the request body, allowing POST /api/mcp allows every tool on that endpoint. Every call the agent makes through your instance is logged.
How do I look up a label reference through Jentic?
Search Jentic for 'find a medicine label reference', load the KinToolkit tool-call operation, and send a tools/call request naming find_label_references with only the public brand, ingredient, and bottle audience. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED