Install Jentic One Beta

Connect the NamingSignal API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the NamingSignal 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%2Fnamingsignal.com%2Fnamingsignal" | 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%2Fnamingsignal.com%2Fnamingsignal" | 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 NamingSignal API.

Compile a naming brief from pasted text, a public HTTPS URL, or a public GitHub repository

Generate 4-50 name candidates per batch with optional primary-domain checks and an excludedNames list from earlier rounds

Check 1-100 names across up to 5 TLDs and namespaces, capped at 150 name and TLD combinations per call

Rank 2-30 domain survivors with an independent model, falling back to the deterministic score order

GET STARTED

Start building with NamingSignal API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use NamingSignal API for, with concrete tasks.

★ Agent-run naming sprint through Jentic

A developer asks their coding agent, connected through Jentic, to name a new open-source project. The agent compiles a brief from the repository URL, generates 24 candidates with checkPrimaryDomain on, ranks the survivors, and researches the top three. Passing the same X-Name-Ledger-Sprint value on the generation, ranking, and research calls keeps them under one shared provider-cost budget.

Call POST /api/v1/brief with url='https://github.com/example/project', pass the returned brief to POST /api/v1/generate with count=24 and tlds=['com','dev'], then send the survivors to POST /api/v1/rank

Bulk domain and namespace checks

When a team already has a list of name ideas, the check operation scores them for domain and namespace availability in one call. It accepts 1-100 names and up to 5 TLDs, with names times TLDs capped at 150. Oversized namespace work degrades explicitly to unknown through boundedDegradation instead of failing the request.

Call POST /api/v1/check with names=['ledgerly','tallyfox','quillpath'], tlds=['com','io','dev'], and includeNamespaces=true, then list the names with a likely-unregistered .com

Finalist research before committing

Before adopting a name, a founder wants to know what else shares it. The research operation takes one to three finalists and returns namespaces, source-backed namesake evidence when the search provider is configured, risk signals, and links for manual checks. Trademark output is preliminary research, so the agent flags the manual verification steps instead of treating the result as clearance.

Call POST /api/v1/research with names=['tallyfox'] and tlds=['com','io'], then summarise the risk signals and list the manual verification links

Key Endpoints

8 endpoints — the namingsignal api turns a project description into a naming brief, generates batches of name candidates with a model ensemble, checks each name across domain tlds and namespaces, ranks the survivors, and researches up to three finalists.

METHOD

PATH

DESCRIPTION

POST

/api/v1/brief

Compile a naming brief

POST

/api/v1/generate

Generate name candidates

POST

/api/v1/check

Check and score names across TLDs

POST

/api/v1/rank

Rank domain survivors

POST

/api/v1/research

Research finalists

GET

/api/v1/account/usage

Read credit balance and activity

POST

/api/v1/brief

Compile a naming brief

POST

/api/v1/generate

Generate name candidates

POST

/api/v1/check

Check and score names across TLDs

POST

/api/v1/rank

Rank domain survivors

POST

/api/v1/research

Research finalists

GET

/api/v1/account/usage

Read credit balance and activity

Why Jentic?

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

Setup

Wiring NamingSignal by hand means creating a user API key, sending Idempotency-Key and X-Name-Ledger-Sprint headers so retries do not re-charge credits, and reading fallback labels and Retry-After on rate-limited responses. Through Jentic you install once, import NamingSignal from the API Directory, store the key once, and your agent calls it.

Permission scoping

NamingSignal carries names and briefs in the request body, so rules bound which operations your agent may call, not which names it sends. Limit the agent to the operations it needs, such as checking names, and leave the credit-heavy generation and research operations out unless you add them.

Credential isolation

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

Intent-based discovery

Agents search Jentic by intent such as 'generate product name ideas' or 'check domain availability for names', and Jentic returns the matching NamingSignal operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using NamingSignal API through Jentic.

What authentication does the NamingSignal API use?

Per its OpenAPI spec, the NamingSignal API uses a bearer token: a user-owned API key created after sign-in at the NamingSignal developers page, sent as Authorization: Bearer. GET /api/v1/health is public and needs no credential. Revoked or expired keys return 401. Through Jentic, the key is stored once by your own Jentic One instance and injected at call time.

How are NamingSignal API calls metered?

Calls draw on Naming Credits. Generation costs one generation unit plus one domain_check unit per candidate when checkPrimaryDomain is true, check costs one domain_check unit per name and TLD combination, rank costs one ranking unit, and research costs one research unit per finalist. Send an Idempotency-Key so a retried request replays the stored response instead of charging again.

What are the rate limits for the NamingSignal API?

The spec says rate-limited responses carry Retry-After, retryAfterSeconds, and resetAt, and that GET /api/v1/health reports the applied limits, including the Naming Credit schedule. It does not list fixed numbers in the spec itself, so read the health endpoint for the current values.

Is there a NamingSignal MCP server?

Yes. NamingSignal exposes a remote MCP endpoint at POST /mcp that uses the same API key. You can also connect the NamingSignal API directly through Jentic: your agent gets the full 8-endpoint surface without loading another server's tool definitions into its context, your key is injected at call time by your self-hosted instance instead of living in an MCP config, and your rules decide which operations the agent may call.

How do I run a naming sprint through Jentic?

Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, import the NamingSignal API from the API Directory, and store your API key once. Your agent searches for 'generate product name ideas', gets compileBrief and generateCandidates with their input schemas, and chains them with checkNames and rankDomainSurvivors. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Can I limit what my agent is allowed to do with the NamingSignal API?

Yes. To cap credit spend, write a rule that allows only checkNames and getAccountUsage, so the agent can score names you already have and watch the balance but cannot start model generation, ranking, or research runs. Add generateCandidates when you want it to propose names too.

NamingSignal API

AI ReadinessAI-Aware (B+)68/100

See full scorecard

Official vendor OpenAPI document · agent-readyAI/MLLanguage Modelsbearer8 EndpointsREST

For Agents

Compile a naming brief, generate 4-50 product name candidates, check them across up to 5 TLDs and namespaces, rank 2-30 survivors, and research up to 3 finalists.

Use for: Generate name ideas for my developer tool from its README, Check whether these five names are free as .com and .io domains, Rank the shortlisted names that have an available domain, Research the top three finalists for namesake conflicts

Not supported: Does not register domains, file trademarks, or give legal clearance. Use for generating, checking, ranking, and researching product names only.

The NamingSignal API turns a project description into a naming brief, generates batches of name candidates with a model ensemble, checks each name across domain TLDs and namespaces, ranks the survivors, and researches up to three finalists. Every model-backed step labels its deterministic fallback with fallback and fallbackReason, so callers can tell a model result from a fallback one. Registry not-found is reported as a likely-unregistered signal, not a purchase guarantee, and trademark output is preliminary research only. Calls are metered against Naming Credits, and the account usage endpoint reports the remaining balance.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

98%

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).

100%

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: BSignals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

66%

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: D+Signals: 4

49%

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.

47%

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: B-Signals: 1

60%

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

69%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the NamingSignal API to your agent

Capabilities

Start building with NamingSignal API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

NamingSignal API

Jentic AI Readiness Score

NamingSignal 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