Install Jentic One Beta

Connect the Limpi API to your agent

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

Launch an asynchronous SEO and GEO audit of a public URL with max_pages, max_depth, crawl_delay, and exclude patterns

Track audits by status, such as queued, running, completed, failed, or cancelled, with cursor pagination

Fetch a completed audit's report with overall and section scores, page-level data, checks, and recommendations

Cancel a running audit before it finishes

GET STARTED

Start building with Limpi API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Limpi API for, with concrete tasks.

★ Agent-run site audits through Jentic

An AI agent helping with a website can start a Limpi audit, poll it until the status is completed, and then summarize the report's top recommendations for the developer. Through Jentic the agent finds the create, read, and report operations by intent and loads their schemas, including the required Idempotency-Key header, so retries never launch a duplicate audit.

Create an audit for https://example.com with max_pages 50 and max_depth 3 using a unique Idempotency-Key, poll the audit by its job_id until status is completed, then fetch the report and list the three highest-priority recommendations.

Client audit reports for agencies

Agencies auditing client sites can tag each audit with client_name and analyst_name, then pull the finished report's overall score, section scores, strengths and weaknesses from the professional opinion, and recommendations with platform-specific fixes to build a client deliverable.

Create an audit for a client URL with client_name 'Acme' and analyst_name 'Sam', then fetch the report and return the score, section scores, and the professional opinion headline.

Quota-aware audit scheduling

Audits are billed by pages analyzed against a monthly page quota. Before a large crawl, an agent reads usage to see monthly_pages_remaining and available_for_next_audit, then sets max_pages so the audit fits the remaining quota.

Read usage, then create an audit with max_pages set to the smaller of available_for_next_audit and 200.

Key Endpoints

8 endpoints — the limpi api runs asynchronous seo and geo audits of public websites: you submit a url with crawl limits such as max_pages, max_depth, crawl_delay, and exclude patterns, then poll the audit as it moves from queued to running to completed.

METHOD

PATH

DESCRIPTION

POST

/audits

Create an asynchronous audit

GET

/audits

List audits

GET

/audits/{job_id}

Read an audit

GET

/audits/{job_id}/report

Read a completed audit's report

POST

/audits/{job_id}/cancel

Cancel an audit

GET

/usage

Read quota and usage

POST

/audits

Create an asynchronous audit

GET

/audits

List audits

GET

/audits/{job_id}

Read an audit

GET

/audits/{job_id}/report

Read a completed audit's report

POST

/audits/{job_id}/cancel

Cancel an audit

GET

/usage

Read quota and usage

Why Jentic?

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

Setup

Wiring Limpi by hand means sending a scoped bearer key, generating an Idempotency-Key for each audit, polling asynchronous jobs, and parsing RFC 9457 problem+json errors. Through Jentic you install once, import Limpi from the API Directory, store the key once, and your agent calls it.

Permission scoping

Limpi puts the audit id in the URL path (/audits/{job_id}), so a rule can pin your agent to one audit and its report. You choose the operations it may call, so ones like creating or cancelling audits are not included unless you add them.

Credential isolation

Your Limpi 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 'run an SEO audit' or 'get audit recommendations', and Jentic returns the matching Limpi operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Limpi API through Jentic.

What authentication does the Limpi API use?

Per its OpenAPI spec the Limpi API uses HTTP bearer authentication: you send your Limpi API key in the Authorization header as a bearer token. Operations also name a required key scope, such as audits:read, audits:write, reports:read, or usage:read. Reading the OpenAPI contract itself needs no key. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at request time.

Is there a Limpi MCP server?

You don't need an MCP server to give your agent the Limpi API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the audit, report, and usage operations on demand.

Why does creating a Limpi audit need an Idempotency-Key?

Audit creation requires an Idempotency-Key header of 8 to 128 characters. If a request is retried with the same key, Limpi replays the original response and marks it with the Idempotency-Replayed header instead of starting a second audit, which protects your page quota.

What are the rate limits for the Limpi API?

The OpenAPI spec does not state numeric limits. It declares an HTTP 429 response carrying Retry-After, X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset headers, so read those headers for your current limits, and check https://limpiaudit.com for plan details.

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

Yes. For example, write a rule that allows only the audit read and report operations for /audits/abc123, so the agent can follow one audit and summarize its report but cannot start new audits that spend your page quota or cancel running ones. Every call it makes is logged.

How do I run an SEO audit with the Limpi API through Jentic?

Search Jentic for 'run an SEO audit', load the create audit operation, and pass the url with optional max_pages and max_depth plus an Idempotency-Key header. Poll the audit by its job_id until the status is completed, then fetch the report. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Limpiaudit Limpi API

AI ReadinessAI-Aware (A-)71/100

See full scorecard

Official vendor OpenAPI document · agent-readyMarketingSeo Sembearer8 EndpointsREST

For Agents

Launch SEO and GEO audits of a website, track their status, fetch the finished report with scores, checks, and recommendations, and check the monthly page quota.

Use for: I need to run an SEO audit on example.com, Check whether my audit has finished, Get the recommendations from the latest completed audit, List all audits that failed

Not supported: Does not track keyword rankings, report backlinks, or edit your website. Use for crawling a site and reporting SEO and GEO audit findings only.

The Limpi API runs asynchronous SEO and GEO audits of public websites: you submit a URL with crawl limits such as max_pages, max_depth, crawl_delay, and exclude patterns, then poll the audit as it moves from queued to running to completed. A finished audit returns a structured report with an overall score, section scores, per-page data such as titles, canonicals, and heading counts, individual checks, and prioritized recommendations with how-to guides for platforms like WordPress, Wix, and Squarespace. Errors follow RFC 9457 problem+json, and a usage operation reports the monthly page quota.

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).

75%

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.

53%

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: BSignals: 4

15%

Description Coverage

Coverage of descriptions across API elements.

88%

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

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

56%

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: CSignals: 1

56%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Limpi API to your agent

Capabilities

Start building with Limpi API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Limpiaudit Limpi API

Jentic AI Readiness Score

Limpi 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