Agent tools
Your agent builds apps on manh.run through MCP tools; this page lists each group of tools, the two tool sets by connection URL and the order an agent calls them in a build session.
manh.run writes no code itself. Your agent (Claude Code, ChatGPT, Gemini, Cursor…) connects to https://mcp.manh.run, reads the docs, writes files into app/, runs check and deploys. Each of those steps is a tool, much like the CLI commands of other frameworks.
Tool groups
| Group | Tools | What for |
|---|---|---|
| Projects | list_projects · create_project · get_project | List, create and inspect projects |
| Files | list_files · read_files · write_files · delete_files | Read and write the app/ tree |
| check | check | Find errors before deploying |
| deploy | deploy | Put the UI and the API live together, then run the tests |
| Testing | run_acceptance · create_test_accounts · remove_test_accounts | Business tests, test accounts per role |
| Checkpoints | checkpoint · restore_checkpoint | Save and restore the file tree |
| Database | db_query · db_exec | Read and write the app’s database |
| Logs | logs | Requests, console output, traffic, metrics |
| Secrets | env_set · env_list | API keys and tokens of outside services |
| Feature blocks | blocks · block_plan · block_add | Add tested features to the app |
| Cron | cron_jobs · cron_runs · cron_control | Inspect and control scheduled jobs |
| Outside data | integrations · integration_sql | The owner’s Supabase |
| Images | list_images · upload_image | The owner’s own photos for the website |
| Docs | framework_docs | Framework docs for the agent |
Every tool that works on a project takes a project argument: the project id from list_projects. The agent sees only the projects of the account it signed in with.
Two tool sets
manh.run has two MCP URLs. They differ in the tools that write real data or take secrets.
https://mcp.manh.run: the full set, for Claude Code, Cursor, Codex and custom connectors.https://mcp.manh.run/directory: the set used by the ChatGPT app directory. It has noenv_set,db_exec,integrationsorintegration_sql.write_filesdoes not delete; deleting is its own tool,delete_files.deployhas noforce.
With the smaller set you set secrets in the dashboard (the project’s Secrets page) and change data through the app’s API or the Database tab.
A build session
An agent usually calls the tools in this order. The results of write_files, check, deploy, get_project and create_project end with a Progress section and a next: line naming the next step, so weaker models reach a working app too.
1. framework_docs("process"), ("framework"), ("pro") read the conventions before writing
2. list_projects / create_project pick or create a project
3. write_files, one phase at a time tables + repository → handlers → layout + pages
4. check({ typecheck: true }) fix every error
5. deploy the API answers 503 until the first deploy; returns test results
6. run_acceptance fix until every test in spec/acceptance.json passes
7. remove_test_accounts, checkpoint clean up test accounts, save a labelled pointGood to know
- Writing files never deploys. The live app changes only when the agent calls
deployor you click Deploy. - You see each file write right away in the dashboard preview.
- Errors come back as
ERROR_CODE: what to do, so the agent can fix them without guessing.
Next steps
- Deploy your app: what a deploy does and what goes live.
- check rules: the check layers and the main rules.
- Your first app: from an idea to a running app.