Install Jentic One Beta

Connect the LinkIntel API to your agent

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

Read X's published ranking weights and the changelog of how they shift

Return a cited content brief that grounds a post suggestion in ranking signals

Pull the customer's own recent X posts once they connect their account

Run operations through a JSON-RPC endpoint that agent tooling discovers on demand

GET STARTED

Start building with LinkIntel API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use LinkIntel API for, with concrete tasks.

★ Agent-written content brief

An AI writing assistant can call the LinkIntel API through Jentic to read X's current ranking weights and the customer's recent posts, then return a cited content brief for the next post. Jentic returns the right operation from a natural-language query, so the assistant grounds its suggestion in live ranking signals without parsing the LinkIntel reference first.

Read X's published ranking weights, pull the customer's recent posts, and return a cited content brief recommending what to post next.

Post performance measurement

Register newly published posts through the ingest endpoint so their performance can be measured against the ranking weights over time. Automation tools use this to close the loop between what was posted and how the algorithm scored it.

Register the posts published in the last day through the ingest endpoint and confirm how many were accepted for measurement.

Ranking-weight monitoring

Read X's published ranking weights and their changelog to track how the algorithm's priorities move, which is a public endpoint so a dashboard can poll it without a connected account. Teams use this to adjust content strategy as the weights change.

Read the current ranking weights and their changelog, then report which signals gained the most weight since the last check.

Key Endpoints

4 endpoints — the linkintel api gives an ai assistant evidence for its next x post: the customer's own recent x posts once they connect their x account, x's published ranking weights and their changelog, and optional public posts they choose, returned as a cited content brief.

METHOD

PATH

DESCRIPTION

POST

/api/mcp

Send a JSON-RPC message to the server

GET

/x-algorithm.json

Retrieve X's published ranking weights and changelog

POST

/api/ingest/posts

GET

/api/ingest/posts

Describe the ingest endpoint

POST

/api/mcp

Send a JSON-RPC message to the server

GET

/x-algorithm.json

Retrieve X's published ranking weights and changelog

POST

/api/ingest/posts

GET

/api/ingest/posts

Describe the ingest endpoint

Why Jentic?

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

Setup

Wiring the LinkIntel API by hand means running the OAuth2 flow to connect an X account, handling bearer tokens for the JSON-RPC and ingest endpoints, and coding each call yourself. Through Jentic you install once, import the API from the API Directory, store the token once, and your agent calls it.

Permission scoping

The LinkIntel endpoints carry no resource id in the URL path, so bound your agent to the operations it needs, such as reading ranking weights and recent posts. You choose which operations it may call, so the ingest operation is not included unless you add it.

Credential isolation

Your LinkIntel token 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 'get a content brief' or 'read X ranking weights', and Jentic returns the matching LinkIntel operation with its input schema so the agent calls the right endpoint without reading the reference docs.

FAQs

Specific to using LinkIntel API through Jentic.

Is there a LinkIntel API MCP server?

Yes. LinkIntel exposes a JSON-RPC endpoint that MCP clients can call directly. You can also connect it through Jentic from the API Directory: your agent gets the full four-endpoint surface without loading another server's tool definitions into its context, your credential is injected at call time by your self-hosted instance, and your rules decide which operations the agent may call.

What authentication does the LinkIntel API use?

The API uses OAuth2 authorization code to connect a customer's X account and bearer tokens for the JSON-RPC and ingest endpoints, per its OpenAPI spec. Through Jentic the token is stored encrypted in your own Jentic One instance and supplied only when an allowed call runs, so it never reaches the agent's context.

Can I read X's ranking weights with the LinkIntel API?

Yes. The ranking-weights endpoint returns X's published weights and their changelog, and it is a public endpoint, so a dashboard can poll it without a connected X account. The weights are what a content brief grounds its suggestions on.

What are the rate limits for the LinkIntel API?

The OpenAPI spec does not specify rate limits. The service is priced per month rather than per request, so confirm the limits for your plan in the LinkIntel documentation at https://www.getlinkintel.com/pricing.md.

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

Yes. Write a rule that permits only the read operations, pulling ranking weights and recent posts, when the agent should only draft briefs, and add the ingest operation only for workflows that register published posts, with every call logged.

How do I get a content brief with the LinkIntel API through Jentic?

Search Jentic for 'get a content brief for my next X post' to surface the brief operation, load its input schema, pass the connected account context, and execute. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Getlinkintel LinkIntel API

AI ReadinessAI-Aware (B+)68/100

See full scorecard

Official vendor OpenAPI document · agent-readySocial MediaSocial Listeningoauth2, bearer4 EndpointsREST

For Agents

Gather evidence for the next X post: register published posts for measurement, read X's published ranking weights and changelog, and return a cited content brief grounded in real ranking signals.

Use for: Get a content brief for my next X post, Read X's current ranking weights and recent changes, Register the posts I just published for measurement, Pull my recent X posts after connecting my account

Not supported: Does not publish posts, schedule content, or manage ad spend. Use for gathering X ranking signals and post-performance evidence for content briefs only.

The LinkIntel API gives an AI assistant evidence for its next X post: the customer's own recent X posts once they connect their X account, X's published ranking weights and their changelog, and optional public posts they choose, returned as a cited content brief. It exposes a JSON-RPC endpoint that agent tooling calls to discover and run those operations, plus an ingest endpoint that registers newly published posts for measurement. The ranking-weights endpoint surfaces how X currently scores content so a brief can be grounded in the live algorithm. It is aimed at creators and growth tools that want post suggestions backed by real ranking signals rather than guesswork.

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: BSignals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

56%

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

42%

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.

50%

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: A-Signals: 1

70%

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: A-Signals: 1

72%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the LinkIntel API to your agent

Capabilities

Start building with LinkIntel API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Getlinkintel LinkIntel API

Jentic AI Readiness Score

LinkIntel 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