# AI use cases for On Co (judegomila/OnCo) Repo: [judegomila/OnCo](https://github.com/judegomila/OnCo) | Use cases: 4 | Page: https://dedupedai.com/use-cases/judegomila-onco/ OnCo is an open, cited knowledge graph of oncology, with a website, static JSON API, MCP server, CLI and a validated TypeScript corpus of cancers, treatments, trials and related records. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Let an AI agent search and compare On Co cancer records: https://dedupedai.com/use-cases/judegomila-onco/search-oncology-records-with-mcp/ - Pull On Co cancer records into a script via CLI or API: https://dedupedai.com/use-cases/judegomila-onco/pull-oncology-records-into-scripts/ - Correct an oncology record and open a pull request: https://dedupedai.com/use-cases/judegomila-onco/correct-a-cancer-record-by-pull-request/ - Cross-check corpus facts against openFDA and ClinicalTrials.gov: https://dedupedai.com/use-cases/judegomila-onco/audit-corpus-facts-against-regulators-and-trials/ ## How to let an AI agent search and compare On Co cancer records with On Co Repo: [judegomila/OnCo](https://github.com/judegomila/OnCo) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Connect an agent to the On Co MCP server to search, fetch and compare cancer records with sources. **Who it is for:** An AI agent builder or a researcher whose agent needs cited oncology facts about a specific cancer, treatment or trial. **The problem:** General language models often state oncology facts without checkable sources or country-specific approval status. **The outcome:** The agent answers from On Co records, with a TL;DR, approval status for a chosen country and primary source links for each claim. ### Steps 1. Install Node.js so that npx is available. (inferred, check the README) 2. Add an MCP server entry to your client that runs `npx -y onco-mcp`. 3. Ask the agent to search On Co for a cancer type, then fetch one treatment record. 4. Ask the agent to compare two treatments and list the primary source link for each fact. 5. Open each source link and confirm it matches the claim before using the answer. ### Prompt to paste into your agent ```text Using the OnCo MCP server started with `npx -y onco-mcp` from the judegomila/OnCo repository, search for , fetch the treatment record for , and return its TL;DR, its approval status for , and every primary source link. Verify that each link resolves before reporting, and state any field the record marks as no data. ``` ### Caveat The README says facts may be incomplete, out of date or wrong, so every answer needs checking against the primary source linked on each page. Risk, reverse engineering: The MCP server returns general oncology information that the README says is work in progress and not medical advice, so outputs must not guide treatment decisions. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/judegomila-onco/search-oncology-records-with-mcp/ ## How to pull On Co cancer records into a script via CLI or API with On Co Repo: [judegomila/OnCo](https://github.com/judegomila/OnCo) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Use the onco command or the static JSON API to load cancer records into your own analysis. **Who it is for:** A data analyst or developer who needs structured oncology records, such as cancers, drugs or trials, for a dashboard, report or dataset. **The problem:** Oncology facts are scattered across journals, regulators and registries, which makes repeatable structured pulls hard. **The outcome:** A script that reads On Co records as JSON, with the required attribution line carried through to the output. ### Steps 1. Install Node.js so that npx is available. (inferred, check the README) 2. Run `npx onco` to see the command-line tool and its options. 3. Open https://onco.cc/api/ for the endpoint list and https://onco.cc/api/v1/openapi.json for the OpenAPI 3.1 schema. 4. Fetch the JSON records your script needs from the static JSON API under https://onco.cc/api/v1/. 5. Keep the attribution line "Data from On Co (onco.cc)" in every export or report you publish. ### Prompt to paste into your agent ```text Using the OnCo JSON API at https://onco.cc/api/v1/ and the OpenAPI schema at https://onco.cc/api/v1/openapi.json, fetch all records of the kind and write them to a CSV file with the attribution line "Data from OnCo (onco.cc)" in the header. Verify that the row count matches the endpoint's reported count and report any record missing a primary link. ``` ### Caveat The corpus is licensed CC BY-NC 4.0, so commercial use requires contacting On Co for a data licence, as the README states. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/judegomila-onco/pull-oncology-records-into-scripts/ ## How to correct an oncology record and open a pull request with On Co Repo: [judegomila/OnCo](https://github.com/judegomila/OnCo) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README Edit a record in the corpus, run the checks and submit a change that passes the same safety gate. **Who it is for:** A clinician, scientist or patient advocate who has found an error or a missing fact in a record on the site. **The problem:** Outdated or wrong oncology facts stay online unless someone with the source in hand fixes the record in the open. **The outcome:** A pull request that corrects the record, cites its source, and passes validation, type checks, lint, tests and build. ### Steps 1. Clone the repository with `git clone https://github.com/judegomila/OnCo` and enter the folder. (inferred, check the README) 2. Open an issue first, since the site's forms prefill it, and note the triaged issue number. 3. Edit the record in the matching file under `src/data/` and set its `asOf` date and a primary `links` entry. 4. Run `npm run validate` and fix any duplicate ids, dangling references or malformed records it reports. 5. Run `npm run typecheck && npm run lint && npm test && npm run build`, then open the pull request referencing the issue. ### Prompt to paste into your agent ```text In a local clone of judegomila/OnCo, update the record with id in src/data/ so that it matches the primary source , set asOf to today's date, and run `npm run validate`. Expected output is a clean validation report and a diff limited to that record. Verify that the new link resolves and that no other record changed. ``` ### Caveat The README says no personal or patient data belongs in the repository, so corrections must cite public sources about science, products and organisations only. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/judegomila-onco/correct-a-cancer-record-by-pull-request/ ## How to cross-check corpus facts against openFDA and ClinicalTrials.gov with On Co Repo: [judegomila/OnCo](https://github.com/judegomila/OnCo) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Run the fact-check and audit scripts to flag stale or contradictory oncology records. **Who it is for:** A maintainer or researcher who wants to find outdated approvals or trial statuses in the corpus before relying on them. **The problem:** Approval and trial facts change over time, and a static record can quietly fall behind the registries it cites. **The outcome:** A list of records that disagree with openFDA or ClinicalTrials.gov, or that the audit marks as stale or contradictory. ### Steps 1. Clone the repository and run `npm install` in its folder. (inferred, check the README) 2. Run `npm run validate` to confirm the corpus parses before checking it. 3. Run `npm run factcheck` to cross-check against openFDA and ClinicalTrials.gov. 4. Run `npm run audit` to find stale or contradictory facts. 5. Open each flagged record, check the primary source and open an issue or pull request if the record is wrong. ### Prompt to paste into your agent ```text In a local clone of judegomila/OnCo, run `npm run validate`, then `npm run factcheck` and `npm run audit`. Expected output is a list of flagged record ids with the field, the stored value and the source value. Verify each flag against the linked primary source before reporting it as an error. ``` ### Caveat The README warns that facts may be wrong, so a flag from the checks is a prompt to verify at source, not proof that a record is incorrect. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/judegomila-onco/audit-corpus-facts-against-regulators-and-trials/