Install Jentic One Beta

Connect the Mercury Web Parser API to your agent

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

Extract article body content from any URL in HTML, Markdown, or plain text format

Identify and return article metadata including author, publication date, and title

Parse pre-fetched HTML content without requiring an additional network request

Detect lead images and excerpts suitable for content previews

GET STARTED

Start building with Mercury Web Parser API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Mercury Web Parser API for, with concrete tasks.

★ Content Aggregation Pipeline

Build automated content aggregation feeds by extracting article text and metadata from multiple source URLs. Mercury Parser returns structured data including title, author, publication date, and clean article body, enabling agents to compile curated content digests without manual copy-pasting. Each parsed result includes word count and excerpt for filtering and prioritization.

Parse https://example.com/article-url and return the article title, author, word count, and content in Markdown format

Reader Mode for Applications

Provide a distraction-free reading experience by stripping ads, navigation, and sidebars from web pages. Mercury returns only the core article content in the requested format, along with text direction detection for proper rendering of RTL languages. Integration adds reader-mode functionality to any application in minutes rather than building custom extraction logic.

Extract the article content from a given URL in plain text format and verify the word count exceeds 200 words

Research and Knowledge Base Ingestion

Ingest web articles into knowledge bases or research systems by extracting structured content programmatically. Mercury returns publication dates, authors, and full article text that can be indexed, chunked for embeddings, or stored as reference material. Supports custom headers for accessing authenticated or paywalled content when credentials are available.

Parse a research article URL with custom headers and store the returned title, author, date_published, and content fields in a knowledge base record

AI Agent Web Content Access

Enable AI agents to read and understand web page content through Jentic by searching for the parse operation, loading the schema, and executing against target URLs. Agents discover the parsing capability via intent search and receive structured article data without needing to handle HTML scraping logic directly. Integration through Jentic takes under an hour compared to building custom parsers.

Search Jentic for 'extract article content from URL', load the Mercury Parser schema, and execute a parse request against a target news article URL

Key Endpoints

2 endpoints — jentic publishes the only available openapi specification for mercury web parser api, keeping it validated and agent-ready.

METHOD

PATH

DESCRIPTION

GET

/parser

Parse a web page by URL and extract content

POST

/parser

Parse pre-fetched HTML content

GET

/parser

Parse a web page by URL and extract content

POST

/parser

Parse pre-fetched HTML content

Why Jentic?

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

Setup

Wiring the Mercury Web Parser API by hand means handling its x-api-key header and passing the target URL to the parser on every request yourself. Through Jentic you install once, import the Mercury Web Parser API from the API Directory, store the key once, and your agent calls it.

Permission scoping

Mercury exposes its parser endpoint with the target URL in the query or request body, so you limit the agent to the parse operations it needs. Only the operations you add are available to it.

Credential isolation

Your Mercury 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 'extract article content from a URL', and Jentic returns the matching Mercury Parser operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Mercury Web Parser API through Jentic.

Why is there no official OpenAPI spec for Mercury Web Parser API?

Postlight does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Mercury Web Parser API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.

What authentication does the Mercury Web Parser API use?

The Mercury Web Parser API uses an API key passed in the x-api-key HTTP header. Through Jentic, this key is stored encrypted in the credential vault and agents receive scoped access without handling raw keys directly.

Can I extract content in Markdown format with the Mercury Web Parser API?

Yes. The parser endpoint accepts a contentType query parameter with values html, markdown, or text. Setting contentType to markdown returns the extracted article body formatted as Markdown, which is useful for knowledge base ingestion and LLM context preparation.

What are the rate limits for the Mercury Web Parser API?

The API returns a 429 status code when rate limits are exceeded. Specific rate limit thresholds depend on your API key tier. Monitor response headers for rate limit state and implement exponential backoff when a 429 response is received.

How do I parse a web page through the Mercury Web Parser API using Jentic?

Install the SDK with pip install jentic, then search for the intent 'extract article content from URL'. Jentic returns the Mercury Parser parseUrl operation with its input schema. Execute with a target URL and optional contentType parameter to receive structured article data including title, author, content, and word_count fields.

Can I parse pre-fetched HTML without making Mercury fetch the URL again?

Yes. The POST /parser endpoint accepts a JSON body with url and html fields. Provide your already-fetched HTML in the html field and the original URL in the url field for link resolution. This avoids duplicate network requests when you have already retrieved the page content.

Can I limit what my agent is allowed to do with the Mercury Web Parser API?

Yes. Because Jentic One is self-hosted, you decide which Mercury Web Parser operations your agent can reach, and only the operations you add are available to it. Mercury exposes a single parser endpoint that takes a target URL in the query string (GET /parser) or pre-fetched HTML in the request body (POST /parser), so you can grant just the parse operation your agent needs and withhold the rest. Your Mercury API key stays with your own instance and is injected at execution time, never entering the agent's prompt or context.

Postlight Mercury Web Parser API

Name: Mercury Web Parser API
Brand: Mercury Web Parser API
Availability: InStock

AI ReadinessAI-Aware (A-)73/100

See full scorecard

Agent-ready OpenAPI document · curated by JenticData EnrichmentData TransformationapiKey2 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Extract article content, metadata, and structured information from any web page URL. Returns clean text with author, date, title, and lead image.

Use for: I need to extract the main article content from a web page, I want to get clean readable text from a cluttered news page, Retrieve the author and publication date from a blog post URL, Get the lead image URL for a given article

Not supported: Does not handle JavaScript rendering, screenshot capture, or full-page crawling - use for static article content extraction only.

Jentic publishes the only available OpenAPI specification for Mercury Web Parser API, keeping it validated and agent-ready. Mercury Parser extracts meaningful content from any web page URL, returning clean article text, titles, authors, publication dates, lead images, and excerpts. It supports output in HTML, Markdown, or plain text formats and can also parse pre-fetched HTML content directly without re-fetching the URL.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

100

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 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).

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: B+Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

75%

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: B-Signals: 4

85%

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.

67%

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: ASignals: 1

88%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Mercury Web Parser API to your agent

Capabilities

Start building with Mercury Web Parser API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Postlight Mercury Web Parser API

Jentic AI Readiness Score

Mercury Web Parser 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