@centia-io/mcp-server 1.0.4 → 1.0.6
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +18 -6
- package/centia-api.json +514 -202
- package/dist/index.js +46 -8
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -107,19 +107,31 @@ Add the server to your Claude Desktop MCP config (e.g., `claude_desktop_config.j
|
|
|
107
107
|
- `npm run build` — Compile TypeScript to CommonJS/ESM in `dist/` via `tsc`.
|
|
108
108
|
- `npm start` — Run the built server (`node dist/index.js`).
|
|
109
109
|
|
|
110
|
-
## Using
|
|
111
|
-
This repository includes an `
|
|
110
|
+
## Using AGENTS.md and Skills with AI Coding Agents
|
|
111
|
+
This repository includes an `AGENTS.md` file with global hard rules and a `skills/` folder with task-specific guidance for AI coding agents (like Claude Code, Junie, etc.) when working with Centia BaaS.
|
|
112
|
+
|
|
113
|
+
`AGENTS.md` contains the core rules (tool priority, security baselines, destructive-ops policy), while each skill in `skills/*/SKILL.md` covers a specific workflow area.
|
|
112
114
|
|
|
113
115
|
To ensure your AI agent follows these rules while developing your application:
|
|
114
116
|
|
|
115
|
-
1. Copy
|
|
116
|
-
2. When starting a session with your AI agent, it will automatically find and follow the guidelines
|
|
117
|
+
1. Copy `AGENTS.md` and the `skills/` folder from this repository to the root of **your own application's** repository.
|
|
118
|
+
2. When starting a session with your AI agent, it will automatically find and follow the guidelines.
|
|
117
119
|
|
|
118
|
-
|
|
120
|
+
**AGENTS.md** covers:
|
|
119
121
|
- **Prime Directive**: Preferring MCP tools and official SDKs.
|
|
120
122
|
- **Tool Priority**: Order of interaction (MCP tools > SDK > HTTP).
|
|
121
|
-
- **Project Structure**: Recommended layout for Centia-based apps.
|
|
122
123
|
- **Security & Auth**: How to handle tokens and OAuth flows correctly.
|
|
124
|
+
- **Destructive Operations Policy**: Requiring explicit confirmation before destructive changes.
|
|
125
|
+
|
|
126
|
+
**Skills** (`skills/*/SKILL.md`) cover task-specific workflows:
|
|
127
|
+
- `centia-runtime-sdk` — Building JS/TS runtime code with `@centia-io/sdk`
|
|
128
|
+
- `centia-provisioning` — Schema, tables, columns, constraints, indexes, migrations
|
|
129
|
+
- `centia-json-rpc` — JSON-RPC method lifecycle and TypeScript interfaces
|
|
130
|
+
- `centia-auth-model` — Auth across browser, backend, CLI, and provisioning
|
|
131
|
+
- `centia-types-formats` — PostgreSQL types, casts, type hints, output formats
|
|
132
|
+
- `centia-file-import` — File import workflow
|
|
133
|
+
- `centia-openapi-docs` — OpenAPI and docs fallback policy
|
|
134
|
+
- `centia-delivery` — Delivery checklist and quality gate
|
|
123
135
|
|
|
124
136
|
## Troubleshooting
|
|
125
137
|
- Tools missing or inputs look odd: ensure `centia-api.json` exists and is valid. The server generates tools from this file at startup.
|