Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the DocuWriter.ai REST 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%2Fdocuwriter.ai%2Fdocuwriter" | 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%2Fdocuwriter.ai%2Fdocuwriter" | 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 DocuWriter.ai REST API.
Generate documentation for a single code file or a multi-file codebase
Generate Swagger/OpenAPI documentation from code
Generate UML diagrams from code
Organize generated documentation into Spaces as documents
Search the documents within a Space
GET STARTED
List past generations and connected repositories
Patterns agents use DocuWriter.ai REST API for, with concrete tasks.
★ Agent-Generated Code Docs
An AI agent connected through Jentic sends a source file to DocuWriter.ai, receives generated documentation, and stores it as a document in the right Space. The API exposes the generation and Space operations the agent needs, and Jentic injects the bearer token at call time so the agent never holds it.
Generate documentation for a source file and save it as a document in a named Space
OpenAPI and UML from Code
Teams that keep specs and diagrams in sync with the code generate them on demand. The DocuWriter.ai API produces Swagger/OpenAPI documentation and UML diagrams from source, so an agent can refresh a spec or diagram when the code changes.
Generate a Swagger/OpenAPI document and a UML diagram from a module's source files
Searchable Documentation Spaces
Generated documentation is only useful if the team can find it. The DocuWriter.ai API creates Spaces, stores documents in them, and searches those documents, so an agent can answer a question by searching the team's documentation.
Search a Space for documentation mentioning a function and return the matching documents
11 endpoints — the docuwriter.
METHOD
PATH
DESCRIPTION
/generate-code-documentation
Generate code documentation
/generate-multi-file-documentation
Generate documentation from multiple files
/generate-swagger-api
Generate Swagger/OpenAPI documentation
/generate-uml-diagram
Generate UML diagrams
/spaces
List Spaces
/spaces
Create a Space
/spaces/{space}/documents
Create a Space document
/spaces/{space}/search
Search documents in a Space
/generate-code-documentation
Generate code documentation
/generate-multi-file-documentation
Generate documentation from multiple files
/generate-swagger-api
Generate Swagger/OpenAPI documentation
/generate-uml-diagram
Generate UML diagrams
/spaces
List Spaces
/spaces
Create a Space
/spaces/{space}/documents
Create a Space document
/spaces/{space}/search
Search documents in a Space
What agents get from Jentic-routed access to this vendor.
Setup
Wiring DocuWriter.ai by hand means managing its bearer token and sending source files to the right generation endpoint for docs, specs, or diagrams yourself. Through Jentic you install once, import DocuWriter.ai from the API Directory, store the token once, and your agent calls it.
Permission scoping
DocuWriter.ai puts the Space id in the URL path (/spaces/{space}/...), so a rule can pin your agent to one Space: it can create and search documents there and nothing else. You choose which operations it may call, so the code-generation operations are included only if you add them.
Credential isolation
Your DocuWriter.ai 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 'generate code documentation' or 'search a Space', and Jentic returns the matching DocuWriter.ai operation with its input schema so the agent calls the right endpoint directly.
Alternatives and complements available in the Jentic catalogue.
Specific to using DocuWriter.ai REST API through Jentic.
What authentication does the DocuWriter.ai API use?
The DocuWriter.ai API authenticates with a bearer token sent in the Authorization header, per its OpenAPI spec. Create the token in your DocuWriter.ai account and send it on every call. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at execution time, so it never enters the agent's prompt or logs.
Can I generate code documentation with the DocuWriter.ai API?
Yes. The API generates documentation for a single file or a multi-file codebase, and produces Swagger/OpenAPI documentation and UML diagrams from source. The output can be stored as documents in Spaces that you can later search.
Is there a DocuWriter.ai MCP server?
You don't need an MCP server to give your agent the DocuWriter.ai API. Jentic connects it directly from the API Directory: import it, store your token once, and your agent calls the generation and Space operations. Operations load on demand, so your agent's context stays lean instead of holding another server's tool definitions.
Can I limit what my agent is allowed to do with the DocuWriter.ai API?
Yes. Write a rule that allows only the document-creation and search operations within one Space, so the agent can add and find documentation there but cannot trigger new code-documentation generations or reach other Spaces. Every call the agent makes is logged.
What are the rate limits for the DocuWriter.ai API?
The OpenAPI spec does not specify rate limits. Check the DocuWriter.ai documentation at https://docuwriter.ai for current limits before running a large multi-file documentation job.
How do I generate documentation with the DocuWriter.ai API through Jentic?
Search Jentic for an intent like 'generate code documentation', add the DocuWriter.ai API from the directory, and store your token once. Your agent then sends the source and saves the result as a document in a Space. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Generate code documentation, OpenAPI specs, and UML diagrams from source with DocuWriter.ai, then store and search the results in Spaces.
Use for: Generate documentation for a source file, I need to document my entire codebase, Generate an OpenAPI spec from my code, Create a UML diagram for a module
Not supported: Does not handle version control, CI pipelines, or documentation hosting. Use for generating and organizing software documentation, OpenAPI specs, and UML diagrams only.
The DocuWriter.ai API generates software documentation from source code and organizes it in Spaces. It documents a single file or a multi-file codebase, generates Swagger/OpenAPI documentation and UML diagrams, and stores the output as documents inside Spaces you can search. It also lists past generations and the repositories connected to your 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>