Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Epublys 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%2Fepublys.com%2Fepublys" | shStep 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%2Fepublys.com%2Fepublys" | sh
jentic register # connects your agent to your Jentic One instanceJentic 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.
What an agent can do with Epublys API.
Merge multiple EPUB files into a single ebook
Split an EPUB into individual chapters or pull a chapter range out as one EPUB
Convert between EPUB, PDF, DOCX, and Markdown formats
Read and edit EPUB metadata such as the title and author
Validate an EPUB and compress it to reduce file size
GET STARTED
Generate an AI book cover on the Pro plan and read the remaining account allowance
Patterns agents use Epublys API for, with concrete tasks.
★ Ebook Format Conversion
A publishing workflow needs a manuscript available in several formats. The Epublys API converts a Word document or Markdown source into EPUB, turns an EPUB into PDF for print proofs, and converts an EPUB back to Markdown for editing, sending the file content as base64 JSON in each direction.
Convert a DOCX manuscript to EPUB, then convert that EPUB to PDF, passing the file as base64-encoded JSON each time
EPUB Validation and Metadata Cleanup
Before distributing an ebook, a team validates the EPUB, edits its metadata so the title and author are correct, and compresses the file to keep the download small. The Epublys API returns validation results an agent can branch on and merges metadata edits without rebuilding the book.
Validate an EPUB, edit its metadata to set the title and author, then compress the file
AI Agent Ebook Pipeline via Jentic
An AI agent assembles and ships an ebook through Jentic without holding the Epublys API key itself. It searches by intent, receives the matching operation and its input schema, and runs conversion, validation, and metadata edits with the credential injected at run time, so a build-and-publish sequence runs on its own.
Search Jentic for 'convert a document to EPUB', load the conversion operation schema, and run it with Jentic-managed credentials
14 endpoints — the epublys api manipulates epub and pdf ebooks: it merges several files into one, splits an epub into chapters, compresses files, and validates them.
METHOD
PATH
DESCRIPTION
/merge
Merge multiple EPUBs into one
/split
Split an EPUB into chapters or a chapter range
/epub-to-pdf
Convert an EPUB to PDF
/pdf-to-epub
Convert a PDF to EPUB
/metadata
Read EPUB metadata
/validate
Validate an EPUB
/usage
Read the account's remaining allowance
/merge
Merge multiple EPUBs into one
/split
Split an EPUB into chapters or a chapter range
/epub-to-pdf
Convert an EPUB to PDF
/pdf-to-epub
Convert a PDF to EPUB
/metadata
Read EPUB metadata
/validate
Validate an EPUB
/usage
Read the account's remaining allowance
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Epublys by hand means managing its bearer key, base64-encoding every file into JSON, and decoding the result on each conversion. Through Jentic you install once, import Epublys from the API Directory, store the key once, and your agent calls it.
Permission scoping
Epublys carries the file inside the request body, so rules bound which operations your agent may call, not which file. Limit the agent to the operations it needs, such as merge, convert, and validate, so cover generation and the Pro upgrade operation are not included unless you add them.
Credential isolation
Your Epublys 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 'convert an EPUB to PDF' or 'validate an ebook', and Jentic returns the matching Epublys operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Epublys API through Jentic.
What authentication does the Epublys API use?
The Epublys API authenticates with a bearer API key in the Authorization header per its OpenAPI spec. A free key is available from the Epublys account page, with a Pro tier for higher limits. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never reaches the agent.
Can I convert between EPUB, PDF, DOCX, and Markdown with the Epublys API?
Yes. The Epublys API has dedicated conversion operations for EPUB to PDF, PDF to EPUB, DOCX to EPUB, Markdown to EPUB, and EPUB to Markdown. Each sends and receives the file as base64-encoded JSON, so an agent can chain conversions without handling binary uploads directly.
What are the rate limits for the Epublys API?
The OpenAPI spec does not state specific numeric rate limits for the Epublys API. A free tier and a paid Pro tier with higher limits are offered per the API's own description, and the usage operation reports the remaining allowance on your account so an agent can pace itself.
How do I convert a document to EPUB with the Epublys API through Jentic?
Search Jentic for 'convert a document to EPUB' and it returns the matching Epublys conversion operation with its input schema. Load the schema, send the file as base64 JSON, and the credential is injected at run time. 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 Epublys API?
Yes. Epublys carries the file in the request body, so a rule bounds which operations your agent may call rather than which file. Limit it to the operations it needs, such as conversion and validation, and leave cover generation or the Pro upgrade operation out unless you add them.
Is there an Epublys API MCP server?
You don't need an MCP server to give your agent the Epublys API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the conversion and validation operations it needs without a separate server to install.
For Agents
Merge, split, compress, and validate EPUB files, convert between EPUB, PDF, DOCX, and Markdown, and read or edit ebook metadata. Authenticated with a bearer API key.
Use for: Merge several EPUB files into one ebook, Split an EPUB into its chapters, Convert an EPUB to PDF, Convert a PDF into an EPUB
Not supported: Does not handle ebook storage, DRM, or online reading. Use for EPUB and PDF conversion, merging, and validation only.
The Epublys API manipulates EPUB and PDF ebooks: it merges several files into one, splits an EPUB into chapters, compresses files, and validates them. It converts between EPUB, PDF, DOCX, and Markdown, and reads or edits EPUB metadata such as the title and author. All file data is passed as base64-encoded JSON, and a usage endpoint reports the remaining allowance on the account.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>