Hunter MCP server
Commit Nov 14, 2026Create, manage, and judge coding and academic competitions with automated evaluation and built-in code execution.
Also known as msc24x/hunter
- Stars
- 24
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.1.0
- Last commit
- Nov 14, 2026
- License
- —
What is Hunter MCP?
Hunter is an MCP server. Create, manage, and judge coding and academic competitions with automated evaluation and built-in code execution.
Summary generated from the project's README
About Hunter MCP server
Hunter provides a platform for hosting coding and academic competitions through an automated system. It allows hosts to create contests by adding metadata, scheduling information, and various question types. Hosts can configure specific rules such as positive or negative marking, case sensitivity for input questions, and minimum word counts for essays. Participants can sign up using GitHub to join public competitions, submit code, and track their performance on a live scoreboard.
The system includes a homegrown execution engine called Showdown that handles code compilation and testing. This engine detects the programming language and runs the submitted code against sample and final test cases. While coding tasks are evaluated automatically across seven supported languages, the platform also supports multiple choice, fill in the blank, and long answer questions. For essay-style responses, the dashboard provides tools for manual grading and ranking of participant answers.
What you can do with it
- 1Automate coding task gradingUse the built-in execution engine to compile and test code submissions against provided test cases.
- 2Manage academic essay examsReview and manually grade long-form written responses through a centralized dashboard.
Written from the project's README. Every use case is checked against a quote from it.
How to install Hunter MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Hunter MCP in Claude Code
$ claude mcp add --transport http hunter https://hunter.cambo.in/api/mcpInstall Hunter MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"hunter": {
"url": "https://hunter.cambo.in/api/mcp"
}
}
}Install Hunter MCP in VS Code
.vscode/mcp.json
{
"servers": {
"hunter": {
"type": "http",
"url": "https://hunter.cambo.in/api/mcp"
}
}
}Install Hunter MCP in VS Code CLI
$ code --add-mcp '{"name":"hunter","type":"http","url":"https://hunter.cambo.in/api/mcp"}'Install Hunter MCP in Codex
$ codex mcp add hunter --url https://hunter.cambo.in/api/mcpInstall Hunter MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.hunter] url = "https://hunter.cambo.in/api/mcp"
Install Hunter MCP in Gemini CLI
$ gemini mcp add -s user --transport http hunter https://hunter.cambo.in/api/mcpInstall Hunter MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"hunter": {
"url": "https://hunter.cambo.in/api/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablemsc24x/hunter is public and reachablegithub.com/msc24x/hunter ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-11-11github.com/msc24x/hunter ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 403 (sign-in required)Pass
README
View on GitHubHunter: Contest Hosting Platform

Built to simplify the daily coding and normal academic competitions hosting in general. Hunter gives you the ability to create your own competitions and necessary features to maintain and judge your participants.
Visit at hunter.cambo.in
Overview
Users can sign up with Github for the free account and start creating competitions. Along with the competition meta data and scheduling information, you can add questions to your contest. Host can add as many questions they like. A question will consists of statement, sample test cases and final test cases. Each question can have positive and negative marking according to your requirement.
On the side of the participants, users who wish to just participate can get ready in the compete page, where all the competitions, which were made public by the hosts, would appear. Any one can get started with them when they are live. Users can submit the code, test them again samples and final submit and track their performance.
Users submit their solution code to the online judge built for Hunter, that detects the language, compiles it and test it against the test cases provided by the host user. All this is done by a homegrown execution engine called 'Showdown', which is in testing phase and will be open source soon. All the results would be public on a live scoreboard during the competition.
Question Types Supported
- Coding questions (Hunter started from this)
- Supported 7 programming languages
- In built code execution and evaluation
- Multiple choice questions
- Fill in blank questions (Or basic input question)
- Long answer type questions (Useful for essay writing)
Automatic Evaluation
- Positive marking
- Negative marking
- Case sensitivity configuration for input based questions
- Configure minimum number of words for long answer type questions
Manual evaluations for long answer type questions
- Full dashboard with participants responses, grading & ranking
- View pending evaluations, read answers and option to grade them manually
Key Features
| Feature | Description | Image |
|---|---|---|
| Seamless Automatic Evaluation | Build your contest and let Hunter do all the hard work. Configure your questions' rules and grading with effortless settings; so sit back and relax! | |
| Built-in Coding Task Support | Create custom programming questions effortlessly. Set up problems, test cases, and scoring systems with our intuitive interface. | |
| Secure & Always On Time | Custom scheduler features according to your needs and rules. Get rid of manual distribution and increase efficiency, with automated visibilities and grading features. | |
| Secure Code Compilation & Execution | Powerful backend infrastructure handles code compilation and execution. Multiple language support with secure sandboxing. | |
| Essay Evaluation Control | View and evaluate your participants' responses that require manual grading. See all the data and details, understand the trends of responses and grade them. | |
| Global Participation | Share your contests globally. Engage with participants worldwide and foster a community of programmers. |
Contributing
Contributions are welcome. See CONTRIBUTING.md for setup
steps, dev commands, and the PR workflow, and read our
Code of Conduct. Issues labeled good first issue
and help wanted are good starting points.
Hunter MCP questions
How do I add Hunter MCP to Claude Code?
Run claude mcp add --transport http hunter https://hunter.cambo.in/api/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Hunter MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How is code evaluated in Hunter?
Code is submitted to an online judge that detects the language, compiles it, and tests it against provided test cases using the Showdown execution engine.
Can I manually grade essay-style responses?
Yes, the platform provides a dashboard to view pending evaluations, read answers, and grade long answer responses manually.