Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the conv2pdf 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%2Fconv2pdf.com%2Fconv2pdf" | 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%2Fconv2pdf.com%2Fconv2pdf" | 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 conv2pdf API.
List the available conversion and manipulation tools
Submit a file to a named tool to convert or manipulate a PDF
Poll a job for its status and metadata
Download the converted output file for a finished job
Delete a job and its stored files on demand
GET STARTED
Report the current quota for an API key
Patterns agents use conv2pdf API for, with concrete tasks.
★ Agent document conversion
An AI agent connected through Jentic lists the available tools, submits a source file to the chosen tool with the convert operation, polls the job until it finishes, and downloads the PDF. Because conv2pdf deletes input and output files about an hour after the job, the agent downloads the result promptly rather than relying on long-term storage.
Submit a DOCX file to the conversion tool, poll the job until it reports done, and download the resulting PDF
Batch file manipulation pipeline
A back-office pipeline routes incoming files through conv2pdf tools to standardise them as PDFs before archiving. The single convert endpoint accepts the tool name in the path, so the pipeline picks the right tool per file and tracks each job independently through its status and download steps.
For each file in a batch, call the matching conversion tool and download the output, then delete each completed job
Quota-aware conversion
Before launching a conversion run an agent reads the quota for its key so it does not start more jobs than the plan allows. conv2pdf reports the key quota on demand, letting the agent decide whether to proceed or wait.
Read the key quota and only submit a conversion job when remaining quota is sufficient
6 endpoints — the conv2pdf api converts and manipulates pdf files through a single convert operation that exposes a set of named tools, each selected by the tool path parameter.
METHOD
PATH
DESCRIPTION
/tools
List the available conversion tools
/convert/{tool}
Convert or manipulate a file with a named tool
/job/{jobId}
Get job status and metadata
/download/{jobId}
Download the converted output file
/job/{jobId}
Delete a job and its files
/quota
Report the quota for the API key
/tools
List the available conversion tools
/convert/{tool}
Convert or manipulate a file with a named tool
/job/{jobId}
Get job status and metadata
/download/{jobId}
Download the converted output file
/job/{jobId}
Delete a job and its files
/quota
Report the quota for the API key
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the conv2pdf API by hand means issuing a cpdf_live_ bearer key, learning the single convert endpoint with its tool path parameter, and managing the submit, poll, and download job lifecycle. Through Jentic you install once, import conv2pdf from the API Directory, store the key once, and your agent calls it.
Permission scoping
conv2pdf puts the tool name in the URL path (/convert/{tool}), so a rule can limit your agent to specific conversions and the job-status and download operations. You choose the operations it may call, so job deletion is not included unless you add it.
Credential isolation
Your conv2pdf 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 a file to PDF', and Jentic returns the matching conv2pdf 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 conv2pdf API through Jentic.
What authentication does the conv2pdf API use?
The conv2pdf API authenticates with a bearer API key in the Authorization header, in the cpdf_live_ format, per its OpenAPI spec. Through Jentic the key is stored once by your own self-hosted instance and injected when a call runs, so it never appears in the agent's prompt or logs.
Which conversions can I run with the conv2pdf API?
Call the tools operation to list the conversion and manipulation tools your key can use, then submit a file to a chosen tool through the convert operation, which takes the tool name in the URL path. Poll the job for status and download the output when it is done.
Can I limit what my agent is allowed to do with the conv2pdf API?
Yes. conv2pdf puts the tool name in the URL path, so write a rule that allows only the specific conversions and the job-status and download operations your agent needs, and it cannot delete jobs or run other tools, with every call logged.
How long does conv2pdf keep my files?
Per the spec, input and output files are deleted about an hour after a job runs and results are not cached, while a failed conversion's file is kept for 72 hours for diagnosis and then removed. Download a finished output promptly rather than relying on long-term storage.
Is there a conv2pdf MCP server?
You don't need an MCP server to give your agent the conv2pdf API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the convert and job operations on demand without loading another server's tool definitions into its context.
How do I convert a file to PDF with the conv2pdf API through Jentic?
Search Jentic by intent such as 'convert a document to PDF', and Jentic returns the convert operation with its input schema so your agent submits the file and tool, then polls and downloads the result. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Convert and manipulate PDF files by submitting a file to a named conversion tool, then poll the job and download the result. Lists available tools and reports key quota.
Use for: List the conversion tools this account can use, Convert this Word document to a PDF, Check the status of the conversion job I submitted, Download the finished PDF for this job
Not supported: Does not handle document storage, e-signatures, or data extraction from PDFs. Use for PDF conversion and manipulation only.
The conv2pdf API converts and manipulates PDF files through a single convert operation that exposes a set of named tools, each selected by the tool path parameter. It is hosted in France and deletes input and output files about an hour after a job runs, with no result caching. A caller lists the available tools, submits a file to a chosen tool, polls the job for status and metadata, then downloads the output or deletes the job. Each API key also carries a quota that the quota operation reports.
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>