Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Codequiry 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%2Fcodequiry.com%2Fcodequiry" | 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%2Fcodequiry.com%2Fcodequiry" | 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 Codequiry API.
Create a similarity check and upload one or more ZIP code submissions
Start a check and poll its status until it completes
Read overview and detailed similarity results, including matched web files
Detect AI-generated code through the AI detection results
Run an all-in-one quick check in a single call
GET STARTED
Export results as CSV or a full export and open the results viewer
List your checks, supported languages, and detection engines
Patterns agents use Codequiry API for, with concrete tasks.
★ Agent-Run Plagiarism Checks Through Jentic
An AI agent reviewing code submissions can run Codequiry through Jentic instead of wiring the multi-step flow by hand. The agent creates a check, uploads the ZIP submissions, starts the check, polls until it finishes, and reads the overview and detailed results. Because checks are addressed by id, the agent's reach is easy to bound to the checks it created.
Create a check, upload a ZIP submission, start the check, poll until it completes, and read the results overview
Batch Student Submission Checking
For academic integrity, a workflow uploads many student code submissions in a batch and checks them for similarity against each other and web sources. The overview highlights the highest-similarity pairs, and the detailed results and viewer show the matching sections side by side.
Batch-upload a set of student submissions to a check, start it, and read the overview to find the highest-similarity pairs
AI-Generated Code Detection
To screen for machine-written code, a check includes an AI detection step that reports whether a submission looks AI-generated. A reviewer can run this alongside the similarity pass to flag submissions that warrant a closer look.
Fetch the AI detection results for a completed check and flag any submission scored as likely AI-generated
Originality Gate for Code Contributions
A contribution pipeline can run a quick check on an incoming code submission and gate the next step on the similarity outcome. The single quick-check call uploads, runs, and returns a result so the pipeline does not have to orchestrate each step itself.
Run a quick check on an incoming submission and branch the pipeline on whether the similarity exceeds a threshold
38 endpoints — the codequiry api checks source code for similarity and plagiarism and flags ai-generated submissions.
METHOD
PATH
DESCRIPTION
/check/create
Create a check
/check/upload
Upload a submission ZIP
/check/start
Start a check
/checks/{checkId}/status
Get check status
/check/overview
Get results overview
/check/results
Get detailed results
/ai-results
Get AI detection results
/check/quick
Run an all-in-one quick check
/check/create
Create a check
/check/upload
Upload a submission ZIP
/check/start
Start a check
/checks/{checkId}/status
Get check status
/check/overview
Get results overview
/check/results
Get detailed results
/ai-results
Get AI detection results
/check/quick
Run an all-in-one quick check
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Codequiry API by hand means passing your key in the apikey request header and following its multi-step flow: create a check, upload ZIP submissions, start it, then poll status before reading results. Through Jentic you install once, import Codequiry from the API Directory, store the key once, and your agent calls it.
Permission scoping
Codequiry puts the check id in the URL path for its REST operations (the /checks/ prefix), so a rule can pin your agent to the checks it needs and the operations you choose. You choose the operations it may call, so destructive ones like deleting a check or a submission are not included unless you add them.
Credential isolation
Your Codequiry 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 check code for plagiarism, and Jentic returns the matching Codequiry operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Codequiry API through Jentic.
What authentication does the Codequiry API use?
The Codequiry API authenticates with an API key sent in the apikey request header, per its OpenAPI spec; a validate operation lets you confirm the key works. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never reaches the agent's context.
Can I check code for plagiarism with the Codequiry API?
Yes. The typical flow is to create a check, upload one or more ZIP submissions, start the check, poll its status, and then read the overview and detailed results, including the matched web files behind a flagged section. A quick check runs that whole flow in a single call.
Can the Codequiry API detect AI-generated code?
Yes. Alongside similarity detection, an AI detection results operation reports whether a submission looks AI-generated. You run it against a completed check to get the AI results for the submissions in it.
How do I run a plagiarism check with the Codequiry API through Jentic?
Install Jentic One, then import Codequiry from the API Directory and store your key once. Your agent searches by intent such as check code for plagiarism, and Jentic returns the create-check and upload operations with their input schemas so the agent uploads the submissions, starts the check, and reads the results. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a Codequiry API MCP server?
You don't need an MCP server to give your agent the Codequiry API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the check, upload, and results operations on demand. Operations are discovered when the agent needs them, so they do not fill its context ahead of time.
Can I limit what my agent is allowed to do with the Codequiry API?
Yes. Write a rule that allows only the operations your agent needs, such as creating checks, uploading submissions, and reading results, so it can run plagiarism checks and nothing else. Deleting a check or a submission stays out of that set unless you add them, and every call the agent makes is logged.
For Agents
Create a code similarity check, upload ZIP submissions, start it, and read overview and detailed plagiarism results plus AI-generation detection. A quick check runs the whole flow in one call.
Use for: I want to check a code submission for plagiarism, Upload a ZIP of submissions for a similarity check, Get the detailed similarity results for a check, Detect whether code was AI-generated
Not supported: Does not grade assignments, run unit tests, or scan for security vulnerabilities. Use for source code similarity and AI-generation detection only.
The Codequiry API checks source code for similarity and plagiarism and flags AI-generated submissions. The typical flow creates a check, uploads one or more ZIP submissions, starts the check, polls its status, and then reads an overview and detailed results, including the matched web files behind a flagged section. A quick check runs that whole sequence in a single call. Results can be read through the viewer, exported as CSV or a full export, and an AI detection operation reports whether a submission looks machine-written.
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>