Install Jentic One Beta

Connect the RANDOM.ORG API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the RANDOM.ORG 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.

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%2Frandom.org%2Frandom" | sh

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%2Frandom.org%2Frandom" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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 RANDOM.ORG API.

Draw random integers in a min to max range with or without replacement through generateIntegers

Produce shuffled integer sequences with generateIntegerSequences for fair ordering and draws

Generate decimal fractions, Gaussian-distributed values, random strings from a chosen character set, UUIDs, and binary blobs

Verify the signature on a signed RANDOM.ORG response with verifySignature

GET STARTED

Start building with RANDOM.ORG API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use RANDOM.ORG API for, with concrete tasks.

★ Fair draws by an agent through Jentic

An agent running a giveaway or raffle needs a draw nobody can accuse of being rigged. Through Jentic the agent searches for 'generate true random numbers', receives the RANDOM.ORG invoke operation with its input schema, and sends a generateIntegers request with n, min, max, and replacement set to false, with the API key supplied at execution time. The draw comes from atmospheric noise rather than a pseudo-random generator in the agent's runtime.

Call POST /invoke with method 'generateIntegers' and params n 3, min 1, max 500, replacement false, and return the three winning entry numbers

Auditable randomness with signatures

Lotteries, games, and research studies sometimes need to prove a random result was not altered after the fact. RANDOM.ORG's POST /verify route takes a random object and its signature and runs verifySignature, so a third party can confirm that a signed draw came from RANDOM.ORG unchanged.

Send POST /verify with method 'verifySignature' and params random and signature from a stored draw, and report whether the signature is valid

Test data and identifiers

Developers seeding test fixtures or simulations want values that are not tied to a seeded generator. RANDOM.ORG returns Gaussian values for simulations, random strings drawn from a specified characters set and length, UUIDs, and binary blobs through methods on the same invoke route.

Call POST /invoke with method 'generateStrings' and params n 5, length 10, characters 'abcdefghijklmnopqrstuvwxyz', replacement true

Key Endpoints

3 endpoints — jentic publishes the only available openapi specification for random.

METHOD

PATH

DESCRIPTION

POST

/invoke

Invoke a JSON-RPC generate method

POST

/verify

Verify a signed random response

POST

/usage

Get API key usage

POST

/invoke

Invoke a JSON-RPC generate method

POST

/verify

Verify a signed random response

POST

/usage

Get API key usage

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring RANDOM.ORG by hand means building JSON-RPC 2.0 envelopes with jsonrpc, method, params, and id, placing your API key inside params, and parsing the JSON-RPC result or error. Through Jentic you install once, import RANDOM.ORG from the API Directory, store the key once, and your agent calls it.

Permission scoping

RANDOM.ORG carries the method name inside the JSON-RPC request body, so rules bound which of the three routes your agent may call, not which generate method it runs on the invoke route. Limit it to the routes it needs, such as invoke and verify, so the usage route is not included unless you add it.

Credential isolation

Your RANDOM.ORG API key is stored once, encrypted, by your own Jentic One instance and supplied at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'generate true random numbers' or 'verify a signed random draw', and Jentic returns the matching RANDOM.ORG operation with its input schema, including the JSON-RPC method and params shape, so the agent calls it correctly.

FAQs

Specific to using RANDOM.ORG API through Jentic.

Why is there no official OpenAPI spec for RANDOM.ORG API?

RANDOM.ORG does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call RANDOM.ORG API via structured tooling. It is validated against the live API and kept up to date. To run it on your own infrastructure, install Jentic One from its GitHub repo.

What authentication does the RANDOM.ORG API use?

The OpenAPI spec declares an API key scheme on the X-Api-Key header, and its description and request examples pass the key as apiKey inside the JSON-RPC params object. Keys are issued from the API keys page on api.random.org. Through Jentic the key is stored by your own instance and supplied at call time, so it never enters the agent's context.

Can I pick random winners without repeats using the RANDOM.ORG API?

Yes. Send POST /invoke with the generateIntegers method, set n to the number of winners, min and max to your entry range, and replacement to false so no number is drawn twice. For a full random ordering, use generateIntegerSequences instead.

What are the rate limits for the RANDOM.ORG API?

The OpenAPI spec does not state numeric limits. Allowances are tracked per API key, and POST /usage with the getUsage method reports what remains; check https://api.random.org for current quotas.

Is there a RANDOM.ORG MCP server?

You don't need an MCP server to give your agent RANDOM.ORG. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls the generate, verify, and usage operations on demand.

Can I limit what my agent is allowed to do with the RANDOM.ORG API?

Yes. For example, write a rule that allows only POST /invoke and POST /verify, so the agent can draw numbers and check signatures but cannot read your key's usage. RANDOM.ORG picks the JSON-RPC method inside the body, so the rule works per route, and the agent's calls are logged.

RANDOM.ORG API

AI ReadinessAI-Aware (B-)62/100

See full scorecard

Agent-ready OpenAPI document · curated by JenticData EnrichmentData TransformationapiKey3 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Generate true random integers, sequences, decimals, Gaussians, strings, UUIDs, and blobs from RANDOM.ORG's atmospheric-noise source, verify signed results, and check API key usage.

Use for: Pick 3 random winners from 500 entries without repeats, Generate 10 random integers between 1 and 100, Shuffle a list of 20 names into a random order, I need five random 12-character passwords from a set of letters

Not supported: Does not handle cryptographic key management, lottery ticket sales, or pseudo-random seeding. Use for drawing true random values from RANDOM.ORG and verifying signed results only.

Jentic publishes the only available OpenAPI specification for RANDOM.ORG API, keeping it validated and agent-ready. The RANDOM.ORG API generates true random numbers from atmospheric noise through a JSON-RPC 4 interface. A single invoke route runs methods such as generateIntegers, generateIntegerSequences, generateDecimalFractions, generateGaussians, generateStrings, generateUUIDs, and generateBlobs, with parameters like n, min, max, and replacement. A verify route checks the signature on a signed random response, and a usage route reports the remaining allowance for an API key.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

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).

60%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: CSignals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

25%

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.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: DSignals: 4

17%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

70%

Summary Coverage

Coverage of summaries across operations/tags/info.

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.

Security

Trust, risk posture, and security compliance.

Grade: C-Signals: 1

50%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: B-Signals: 1

62%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the RANDOM.ORG API to your agent

Capabilities

Start building with RANDOM.ORG API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

RANDOM.ORG API

Jentic AI Readiness Score

RANDOM.ORG API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness