docbot-mcp 1.0.2 → 1.0.4

package/.github/copilot-instructions.md

@@ -0,0 +1,57 @@
+# GitHub Copilot Instructions for docbot-mcp
+
+## Purpose
+Provide workspace-specific guidance for Copilot Chat agents to work effectively in this small Node.js MCP server project.
+
+## Project brief
+- Node.js (ES modules, `type: module`) MCP server for CSV/JSON/Markdown conversion.
+- Two transports: HTTP (`index.js`) and stdio (`index-stdio.js`).
+- Minimal scripts (`npm start` for HTTP), no automated tests currently.
+- Dependencies: `@modelcontextprotocol/sdk`, `@rflukerii/docbot`, `express`, `zod`.
+
+## Key files
+- `index.js` : main server (HTTP + Express on port 3000, MCP tool registration)
+- `index-stdio.js` : stdio transport alternative
+- `README.md` : most up-to-date usage, architecture and examples
+- `package.json` : scripts + dependencies
+
+## Build / test commands
+- `npm install`
+- `npm start` (starts production-like server on localhost:3000)
+- `node index-stdio.js` (stdio transport)
+
+> Note: no test suite exists, implement new tests in a modern style (Jest/Mocha/Node test runner) if requested.
+
+## Architecture notes
+- Each POST to `/docbot-mcp` creates a new MCP server via `createServer` and `StreamableHTTPServerTransport`.
+- Tools are registered via `server.registerTool()` with Zod schema validation.
+- Conversion logic primarily lives in the `@rflukerii/docbot` package and is wrapped by MCP tool handlers.
+
+## Conventions / style
+- ES modules (`import` / `export`) throughout.
+- Keep payloads as text (`type: 'text'`, `content` array) in MCP responses.
+- Avoid mutating shared state; each request new server context.
+- For new tool additions, follow the registration pattern in `index.js`.
+
+## Common changes
+- Add tool: update `index.js` tool registry + README docs
+- Transport behavior: follow patterns for `StreamableHTTPServerTransport` and stdio setup
+
+## Gotchas
+- Do not use `require()` (Esm only).
+- Express v5 middleware and response flow must match existing behavior.
+- Keep `content` as string arrays; avoid mixing objects in response type unless MCP spec supports.
+
+## Example prompts
+1. "Add tool `yamlToJson` in `index.js` with schema `yaml: z.string()`, converting YAML text to JSON string output."
+2. "Refactor server lifecycle in `index.js` so MCP server instance is reused across requests but still isolates tool execution per request."
+3. "Add basic Jest tests for `csvToJson` and `jsonToCsv` using `node index-stdio.js` or direct function exports."
+
+## Next agent customizations
+- **agent**: `create-agent docbot-mcp/dev` (focus on tool authoring and transport patches).
+- **prompt**: `create-prompt docbot-mcp/add-tool` (guides on how to add tools with converters and Zod schemas).
+- **hook**: `create-hook docbot-mcp/on-run-tests` (automate test command from unobtrusive mode).
+
+---
+
+> This file is intended as workspace bootstrap for Copilot Chat. Keep it minimal, precise, and updated when major architecture or dependency changes occur.

package/.github/instructions/chat.instructions.md

@@ -0,0 +1,45 @@
+---
+name: chat-instructions
+description: Chatbot response rules and guidelines
+---
+
+# Chat Instructions
+
+These instructions govern how chatbots respond to user prompts. Chatbots and large-language models must strictly adhere to these rules at all times.
+
+**Rule 1: Always limit responses to a maximum of 30 words**
+
+**Rule 2: Chat in a conversational manner**
+
+A conversational manner means:
+
+- Use natural language that mimics human conversation
+- Write direct and concise statements or questions
+- Exchange back-and-forth dialogue addressing one idea or topic at a time
+- Avoid providing multiple suggestions, explanations, or solutions in a single response
+- When the user writes a declarative prompt:
+  - Do NOT immediately provide answers, suggestions or explanations
+  - Respond with a simple acknowledgement
+  - Ask a question to clarify intent--a declarative prompt may be a prelude to an imperative or interrogative prompt
+
+**Rule 3: Tutoring the User**
+
+When the user asks how to complete a complex procedure such as coding and developing a user-interface, adhere to the following rules:
+
+- **Do not immediately provide a full solution:**\
+Begin by framing the problem to help the user reason about the solution themselves.
+
+- **Surface initial thought starters:**\
+Share guiding principles or foundational concepts relevant to the task (e.g., componentization, data flow, layout hierarchy, state boundaries).
+
+- **Ask probing, clarifying questions:**\
+Use questions to uncover intent, constraints, and assumptions. The goal is to lead the user's thinking, not to guess on their behalf.
+
+- **Facilitate decomposition:**\
+Use chain-of-thought (CoT) reasoning to break down complex procedures into smaller, manageable steps and present each step sequentially. (e.g., pages → sections → components → behaviors).
+
+- **Use conversational scaffolding:**\
+Phrase guidance in a way that nudges the user toward the correct approach without asserting the solution. Avoid prescriptive language unless explicitly prompted.
+
+- **Casually confirm understanding:**\
+Periodically check the user's comprehension with a short quiz e.g. "Does this distinction make sense?" or "Can you explain why we'd lift this state?".

package/.github/instructions/version-control.instructions.md

@@ -0,0 +1,97 @@
+# Version Control Instructions
+
+Git is the version-control system used for this project.
+
+Follow the rules below when a user prompts you to complete a task related to version control.
+
+## Copilot Capabilities
+
+You are allowed to carry out ONLY the following two actions:
+
+1. Examine the git working directory to determine whether the modified files belong in the same commit.
+2. Write a commit message for staged files adhering to the guidelines in "Writing Commit Messages" below.
+
+### Allowed Commands
+
+Copilot may always run the following commands without asking for permission:
+
+- **git status --short**\
+List files that are in the working directory as well as files that are staged for commit.
+
+- **git diff --name-only**\
+List files in the working diretory that have unstaged changes.
+
+- **git diff --staged --name-only**\
+List files that are staged for commit.
+
+### Prohibited Commands
+
+Copilot is NEVER allowed to modify the index nor run the following commands regardless of user permission:
+
+- **git add [file]**\
+NEVER stage a file for commit.
+
+- **git commit -m "[message]"**\
+NEVER create a commit.
+
+- **git restore [file]**\
+NEVER discard changes in the working directory.
+
+- **git reset [file]**\
+NEVER unstage a file.
+
+- **git push**\
+NEVER push commits to a remote repository.
+
+- **git pull**\
+NEVER pull changes from a remote repository.
+
+
+- Always examine the diffs of staged files to get context for commit messages
+  - List staged files by executing `git diff --cached --name-only`
+  - View file diffs, run `git diff --cached`
+- If there are no staged files:
+  - Do not write a commit message
+  - Inform the user, "There are not staged files"
+
+## Writing Commit Messages
+
+Commit messages must follow the [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/) structure including:
+
+1. Use the imperative mood -- the message should complete the sentence: "If applied, this commit will __"
+2. Insert a blank line between the subject and the body
+3. Limit the subject to a maximum of 50 characters
+4. Wrap the body lines at approximately 72 characters
+5. Use Conventional Commit prefixes (e.g., `feat:`, `fix:`, `docs:`, `refactor`, `revert`)
+
+Carry out the following steps when prompted to write a commit message:
+
+1. Check for staged files: run `git diff --staged --name-only`
+2. If there are no staged files:
+   - Do not write a commit message
+   - Inform the user, "There are not staged files"
+
+If there are staged files:
+
+1. Run `git diff --staged` to examine the diffs and get context for commit messages
+2. Based on the file diffs, infer the message's structural elements including:
+   - Prefix
+   - Optional scope
+   - Body
+   - Footer
+3. Output the commit message inside the chat panel for the user to preview prior to commit
+
+### Example Message Structure
+
+```
+feat(auth): add OAuth2 provider for Google logins
+
+Implement the Google-specific strategy within the passport middleware.
+This allows users to authenticate using their corporate accounts.
+
+Fixes: #102
+```
+
+## References
+
+[Git documentation](https://git-scm.com/docs "Official Git docs")

package/CHANGELOG.md

@@ -1,20 +1,33 @@
-# Changelog
-
-All notable changes to this project will be documented in this file.
-
-## [1.0.2] - 2026-03-09
-### Added
-- Add `mcpName` to package.json for MCP registry registration
-- Add `server.json` for MCP registry metadata
-
-## [1.0.1] - 2026-03-07
-### Changed
-- Migrate from stdio to HTTP transport
-
-## [1.0.0] - 2026-03-05
-### Added
-- Initial release
-- `csvToJson` — converts CSV string to JSON array
-- `jsonToCsv` — converts JSON array to CSV string
-- `jsonToMarkdown` — converts JSON array to Markdown table
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+## [1.0.4] - 2026-03-15
+### Changed
+- Move sample data into `data/` subfolder for better organization
+- Remove exposed App Runner URL from server settings
+- Update `.gitignore` with MCP registry ignore rules
+- Add `sample_data.csv` fixture under `data/`
+- Add script to sync version between package files
+
+## [1.0.3] - 2026-03-14
+### Changed
+- Update HTTP MCP endpoint from `/mcp` to `/docbot-mcp` for all incoming requests
+- Bump `server.json` package/service version to 1.0.3
+
+## [1.0.2] - 2026-03-09
+### Added
+- Add `mcpName` to package.json for MCP registry registration
+- Add `server.json` for MCP registry metadata
+
+## [1.0.1] - 2026-03-07
+### Changed
+- Migrate from stdio to HTTP transport
+
+## [1.0.0] - 2026-03-05
+### Added
+- Initial release
+- `csvToJson` — converts CSV string to JSON array
+- `jsonToCsv` — converts JSON array to CSV string
+- `jsonToMarkdown` — converts JSON array to Markdown table
 - `csvToMarkdown` — converts CSV string to Markdown table

package/README.md

@@ -1,177 +1,177 @@
-# docbot-mcp
-
-Bidirectional CSV ↔️ JSON ↔️ Markdown transformer exposed as an MCP (Model Context Protocol) server with HTTP transport.
-
-## Overview
-
-**docbot-mcp** is a Model Context Protocol server that provides tools for converting between CSV, JSON, and Markdown formats. It's built on the [Model Context Protocol](https://modelcontextprotocol.io/) and designed for deployment on serverless platforms like AWS App Runner.
-
-## Features
-
-- ✅ **CSV to JSON** — Parse CSV strings into JSON arrays
-- ✅ **JSON to CSV** — Serialize JSON arrays to CSV format
-- ✅ **CSV to Markdown** — Convert CSV to formatted Markdown tables
-- ✅ **JSON to Markdown** — Convert JSON arrays to Markdown tables
-- ✅ **HTTP-based** — REST API endpoint for easy integration
-- ✅ **Containerized** — Ready for deployment on AWS App Runner, Docker, etc.
-
-## Installation
-
-```bash
-npm install
-```
-
-### Requirements
-
-- Node.js 16+ (ES modules support)
-- Dependencies:
-  - `@modelcontextprotocol/sdk` — MCP protocol implementation
-  - `@rflukerii/docbot` — Document conversion utilities
-  - `express` — HTTP server framework
-  - `zod` — Input validation
-
-## Usage
-
-### Starting the Server
-
-```bash
-npm start
-```
-
-The server starts on `http://localhost:3000` with the MCP endpoint at `/docbot-mcp`.
-
-### Available Tools
-
-All tools accept input as text parameters and return formatted text responses.
-
-#### csvToJson
-Converts a CSV string to JSON format.
-
-**Input:** `csv` (string)  
-**Output:** JSON array as string
-
-```bash
-curl -X POST http://localhost:3000/docbot-mcp \
-  -H "Content-Type: application/json" \
-  -d '{"tool": "csvToJson", "input": {"csv": "name,age\nAlice,30"}}'
-```
-
-#### jsonToCsv
-Converts a JSON array to CSV format.
-
-**Input:** `json` (string)  
-**Output:** CSV string
-
-```bash
-curl -X POST http://localhost:3000/docbot-mcp \
-  -H "Content-Type: application/json" \
-  -d '{"tool": "jsonToCsv", "input": {"json": "[{\"name\":\"Alice\",\"age\":30}]"}}'
-```
-
-#### csvToMarkdown
-Converts a CSV string to a Markdown table.
-
-**Input:** `csv` (string)  
-**Output:** Markdown table string
-
-#### jsonToMarkdown
-Converts a JSON array to a Markdown table.
-
-**Input:** `json` (string)  
-**Output:** Markdown table string
-
-## Architecture
-
-### HTTP Transport
-
-The server uses `StreamableHTTPServerTransport` instead of stdio for better compatibility with containerized environments. Each request to `/docbot-mcp` creates a new server instance, processes the MCP request, and returns the result.
-
-```
-Express Server (port 3000)
-    ↓
-POST /docbot-mcp endpoint
-    ↓
-MCP Server instance (createServer)
-    ↓
-StreamableHTTPServerTransport
-    ↓
-Tool execution (csvToJson, jsonToCsv, etc.)
-    ↓
-Response back to client
-```
-
-### File Structure
-
-- `index.js` — Main HTTP server entry point (AWS App Runner compatible)
-- `index-stdio.js` — Stdio transport version (for local/stdio-based clients)
-- `package.json` — Dependencies and scripts
-
-## Deployment
-
-### AWS App Runner
-
-The server includes a `start` script configured for AWS App Runner:
-
-```json
-{
-  "scripts": {
-    "start": "node index.js"
-  }
-}
-```
-
-**Steps to deploy:**
-
-1. Push code to AWS CodeCommit, GitHub, or BitBucket
-2. Create AWS App Runner service
-3. Configure source as your repository
-4. Set build command: `npm install`
-5. Set start command: `npm start`
-6. App Runner will automatically run the server on port 3000
-
-### Docker
-
-Example Dockerfile:
-
-```dockerfile
-FROM node:18-alpine
-WORKDIR /app
-COPY package*.json ./
-RUN npm install --production
-COPY . .
-EXPOSE 3000
-CMD ["npm", "start"]
-```
-
-## Development
-
-### Switching Between Transports
-
-- **HTTP (default)**: `node index.js` — For containerized environments
-- **Stdio**: `node index-stdio.js` — For direct CLI/stdio clients
-
-### Adding New Tools
-
-Edit `index.js` and use the `server.registerTool()` pattern:
-
-```javascript
-server.registerTool(
-  'toolName',
-  {
-    title: 'Display Title',
-    description: 'What it does',
-    inputSchema: { paramName: z.type() }
-  },
-  async ({ paramName }) => ({
-    content: [{ type: 'text', text: 'result' }]
-  })
-);
-```
-
-## License
-
-MIT
-
-## Changelog
-
+# docbot-mcp
+
+Bidirectional CSV ↔️ JSON ↔️ Markdown transformer exposed as an MCP (Model Context Protocol) server with HTTP transport.
+
+## Overview
+
+**docbot-mcp** is a Model Context Protocol server that provides tools for converting between CSV, JSON, and Markdown formats. It's built on the [Model Context Protocol](https://modelcontextprotocol.io/) and designed for deployment on serverless platforms like AWS App Runner.
+
+## Features
+
+- ✅ **CSV to JSON** — Parse CSV strings into JSON arrays
+- ✅ **JSON to CSV** — Serialize JSON arrays to CSV format
+- ✅ **CSV to Markdown** — Convert CSV to formatted Markdown tables
+- ✅ **JSON to Markdown** — Convert JSON arrays to Markdown tables
+- ✅ **HTTP-based** — REST API endpoint for easy integration
+- ✅ **Containerized** — Ready for deployment on AWS App Runner, Docker, etc.
+
+## Installation
+
+```bash
+npm install
+```
+
+### Requirements
+
+- Node.js 16+ (ES modules support)
+- Dependencies:
+  - `@modelcontextprotocol/sdk` — MCP protocol implementation
+  - `@rflukerii/docbot` — Document conversion utilities
+  - `express` — HTTP server framework
+  - `zod` — Input validation
+
+## Usage
+
+### Starting the Server
+
+```bash
+npm start
+```
+
+The server starts on `http://localhost:3000` with the MCP endpoint at `/docbot-mcp`.
+
+### Available Tools
+
+All tools accept input as text parameters and return formatted text responses.
+
+#### csvToJson
+Converts a CSV string to JSON format.
+
+**Input:** `csv` (string)  
+**Output:** JSON array as string
+
+```bash
+curl -X POST http://localhost:3000/docbot-mcp \
+  -H "Content-Type: application/json" \
+  -d '{"tool": "csvToJson", "input": {"csv": "name,age\nAlice,30"}}'
+```
+
+#### jsonToCsv
+Converts a JSON array to CSV format.
+
+**Input:** `json` (string)  
+**Output:** CSV string
+
+```bash
+curl -X POST http://localhost:3000/docbot-mcp \
+  -H "Content-Type: application/json" \
+  -d '{"tool": "jsonToCsv", "input": {"json": "[{\"name\":\"Alice\",\"age\":30}]"}}'
+```
+
+#### csvToMarkdown
+Converts a CSV string to a Markdown table.
+
+**Input:** `csv` (string)  
+**Output:** Markdown table string
+
+#### jsonToMarkdown
+Converts a JSON array to a Markdown table.
+
+**Input:** `json` (string)  
+**Output:** Markdown table string
+
+## Architecture
+
+### HTTP Transport
+
+The server uses `StreamableHTTPServerTransport` instead of stdio for better compatibility with containerized environments. Each request to `/docbot-mcp` creates a new server instance, processes the MCP request, and returns the result.
+
+```
+Express Server (port 3000)
+    ↓
+POST /docbot-mcp endpoint
+    ↓
+MCP Server instance (createServer)
+    ↓
+StreamableHTTPServerTransport
+    ↓
+Tool execution (csvToJson, jsonToCsv, etc.)
+    ↓
+Response back to client
+```
+
+### File Structure
+
+- `index.js` — Main HTTP server entry point (AWS App Runner compatible)
+- `index-stdio.js` — Stdio transport version (for local/stdio-based clients)
+- `package.json` — Dependencies and scripts
+
+## Deployment
+
+### AWS App Runner
+
+The server includes a `start` script configured for AWS App Runner:
+
+```json
+{
+  "scripts": {
+    "start": "node index.js"
+  }
+}
+```
+
+**Steps to deploy:**
+
+1. Push code to AWS CodeCommit, GitHub, or BitBucket
+2. Create AWS App Runner service
+3. Configure source as your repository
+4. Set build command: `npm install`
+5. Set start command: `npm start`
+6. App Runner will automatically run the server on port 3000
+
+### Docker
+
+Example Dockerfile:
+
+```dockerfile
+FROM node:18-alpine
+WORKDIR /app
+COPY package*.json ./
+RUN npm install --production
+COPY . .
+EXPOSE 3000
+CMD ["npm", "start"]
+```
+
+## Development
+
+### Switching Between Transports
+
+- **HTTP (default)**: `node index.js` — For containerized environments
+- **Stdio**: `node index-stdio.js` — For direct CLI/stdio clients
+
+### Adding New Tools
+
+Edit `index.js` and use the `server.registerTool()` pattern:
+
+```javascript
+server.registerTool(
+  'toolName',
+  {
+    title: 'Display Title',
+    description: 'What it does',
+    inputSchema: { paramName: z.type() }
+  },
+  async ({ paramName }) => ({
+    content: [{ type: 'text', text: 'result' }]
+  })
+);
+```
+
+## License
+
+MIT
+
+## Changelog
+
 See [CHANGELOG.md](CHANGELOG.md) for version history and updates.

package/data/sample-data.csv

@@ -0,0 +1,26 @@
+ticker,shares,price,gain-loss,sector,market-cap,volume
+AAPL,219,422.4,+9.93%,Technology,2353B,40302865
+MSFT,409,90.41,+1.82%,Energy,769B,20254714
+GOOGL,72,77.64,-0.99%,Consumer Staples,1991B,36897201
+AMZN,328,167.85,-8.21%,Consumer Staples,1531B,8895044
+TSLA,349,103.06,+1.42%,Financials,2498B,36219457
+BRK-B,160,512.64,-1.85%,Technology,2111B,14232770
+UNH,477,235.41,-8.35%,Technology,352B,12674771
+JNJ,313,284.86,+1.27%,Energy,1405B,17165971
+XOM,482,339.26,+10.15%,Energy,52B,10598777
+JPM,19,568.33,+11.13%,Healthcare,2046B,29312899
+META,100,324.34,+13.14%,Technology,631B,22888266
+V,94,589.52,+8.33%,Consumer Discretionary,1643B,28852195
+PG,268,105.61,+3.67%,Financials,1909B,44038561
+MA,79,182.44,-9.38%,Financials,173B,37474546
+HD,175,71.8,+3.33%,Financials,2863B,7625833
+CVX,32,266.04,-1.28%,Consumer Discretionary,1531B,28573010
+ABBV,417,146.22,-6.24%,Energy,2672B,32220110
+LLY,314,113.88,-10.53%,Financials,2143B,1232034
+PEP,35,137.1,+6.95%,Energy,2720B,30765339
+KO,128,558.33,+12.15%,Consumer Staples,1788B,37818059
+BAC,412,277.88,+1.46%,Financials,2908B,12488920
+PFE,338,508.69,+1.46%,Consumer Staples,554B,44892846
+COST,70,422.18,-5.12%,Energy,779B,4379465
+TMO,74,264.56,-14.95%,Financials,579B,19665238
+AVGO,230,293.56,+6.99%,Financials,1575B,20542990

package/index-stdio.js

@@ -1,63 +1,63 @@
-#!/usr/bin/env node
-
-// External imports
-import { csvToJson, jsonToCsv, jsonToMarkdown, csvToMarkdown } from '@rflukerii/docbot'
-import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
-import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
-import { z } from 'zod';
-
-const server = new McpServer({
-  name: 'docbot-mcp',
-  version: '1.0.0'
-});
-
-server.registerTool(
-  'csvToJson',
-  {
-    title: 'Convert CSV to JSON',
-    description: 'Converts a CSV string to JSON',
-    inputSchema: { csv: z.string() }
-  },
-  async ({ csv }) => ({
-    content: [{ type: 'text', text: JSON.stringify(csvToJson(csv)) }]
-  })
-);
-
-server.registerTool(
-  'jsonToCsv',
-  {
-    title: 'Convert JSON to CSV',
-    description: 'Converts a JSON string to CSV',
-    inputSchema: { json: z.string() }
-  },
-  async ({ json }) => ({
-    content: [{ type: 'text', text: jsonToCsv(JSON.parse(json)) }]
-  })
-);
-
-server.registerTool(
-  'csvToMarkdown',
-  {
-    title: 'Convert CSV to Markdown',
-    description: 'Converts a CSV string to Markdown',
-    inputSchema: { csv: z.string() }
-  },
-  async ({ csv }) => ({
-    content: [{ type: 'text', text: csvToMarkdown(csv) }]
-  })
-);
-
-server.registerTool(
-  'jsonToMarkdown',
-  {
-    title: 'Convert JSON to Markdown',
-    description: 'Converts a JSON string to Markdown',
-    inputSchema: { json: z.string() }
-  },
-  async ({ json }) => ({
-    content: [{ type: 'text', text: jsonToMarkdown(JSON.parse(json)) }]
-  })
-);
-
-const transport = new StdioServerTransport();
-await server.connect(transport);
+#!/usr/bin/env node
+
+// External imports
+import { csvToJson, jsonToCsv, jsonToMarkdown, csvToMarkdown } from '@rflukerii/docbot'
+import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
+import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
+import { z } from 'zod';
+
+const server = new McpServer({
+  name: 'docbot-mcp',
+  version: '1.0.0'
+});
+
+server.registerTool(
+  'csvToJson',
+  {
+    title: 'Convert CSV to JSON',
+    description: 'Converts a CSV string to JSON',
+    inputSchema: { csv: z.string() }
+  },
+  async ({ csv }) => ({
+    content: [{ type: 'text', text: JSON.stringify(csvToJson(csv)) }]
+  })
+);
+
+server.registerTool(
+  'jsonToCsv',
+  {
+    title: 'Convert JSON to CSV',
+    description: 'Converts a JSON string to CSV',
+    inputSchema: { json: z.string() }
+  },
+  async ({ json }) => ({
+    content: [{ type: 'text', text: jsonToCsv(JSON.parse(json)) }]
+  })
+);
+
+server.registerTool(
+  'csvToMarkdown',
+  {
+    title: 'Convert CSV to Markdown',
+    description: 'Converts a CSV string to Markdown',
+    inputSchema: { csv: z.string() }
+  },
+  async ({ csv }) => ({
+    content: [{ type: 'text', text: csvToMarkdown(csv) }]
+  })
+);
+
+server.registerTool(
+  'jsonToMarkdown',
+  {
+    title: 'Convert JSON to Markdown',
+    description: 'Converts a JSON string to Markdown',
+    inputSchema: { json: z.string() }
+  },
+  async ({ json }) => ({
+    content: [{ type: 'text', text: jsonToMarkdown(JSON.parse(json)) }]
+  })
+);
+
+const transport = new StdioServerTransport();
+await server.connect(transport);

package/index.js

@@ -1,121 +1,121 @@
-#!/usr/bin/env node
-
-// External imports
-import { csvToJson, jsonToCsv, jsonToMarkdown, csvToMarkdown } from '@rflukerii/docbot'
-import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
-import { StreamableHTTPServerTransport } from '@modelcontextprotocol/sdk/server/streamableHttp.js';
-import { z } from 'zod';
-import express from 'express';
-
-const app = express();
-app.use(express.json());
-
-function createServer() {
-  const server = new McpServer({
-    name: 'docbot-mcp',
-    version: '1.0.2'
-  });
-
-  server.registerTool(
-    'csvToJson',
-    {
-      title: 'Convert CSV to JSON',
-      description: 'Converts a CSV string to JSON',
-      inputSchema: { csv: z.string() }
-    },
-    async ({ csv }) => ({
-      content: [
-        {
-          type: 'text',
-          text: JSON.stringify(csvToJson(csv)) + '\n\n@rflukerii/docubot'
-        },
-        {
-          type: 'text',
-          text: '@rflukerii/docubot'
-        }
-      ]
-    })
-  );
-
-  server.registerTool(
-    'jsonToCsv',
-    {
-      title: 'Convert JSON to CSV',
-      description: 'Converts a JSON string to CSV',
-      inputSchema: { json: z.string() }
-    },
-    async ({ json }) => ({
-      content: [
-        {
-          type: 'text',
-          text: jsonToCsv(JSON.parse(json)) + '\n\n@rflukerii/docubot'
-        },
-        {
-          type: 'text',
-          text: '@rflukerii/docubot' 
-        }
-      ]
-    })
-  );
-
-  server.registerTool(
-    'csvToMarkdown',
-    {
-      title: 'Convert CSV to Markdown',
-      description: 'Converts a CSV string to Markdown',
-      inputSchema: { csv: z.string() }
-    },
-    async ({ csv }) => ({
-      content: [
-        {
-          type: 'text',
-          text: csvToMarkdown(csv) + '\n\n@rflukerii/docubot'
-        },
-        {
-          type: 'text',
-          text: '@rflukerii/docubot' 
-        }
-      ]
-    })
-  );
-
-  server.registerTool(
-    'jsonToMarkdown',
-    {
-      title: 'Convert JSON to Markdown',
-      description: 'Converts a JSON string to Markdown',
-      inputSchema: { json: z.string() }
-    },
-    async ({ json }) => ({
-      content: [
-        {
-          type: 'text',
-          text: jsonToMarkdown(JSON.parse(json)) + '\n\n@rflukerii/docubot'
-        },
-        {
-          type: 'text',
-          text: '@rflukerii/docubot' 
-        }
-      ]
-    })
-  );
-
-  return server;
-}
-
-app.get('/health', (req, res) => {
-  res.status(200).send('OK');
-});
-
-app.post('/mcp', async (req, res) => {
-  const server = createServer();
-  const transport = new StreamableHTTPServerTransport({
-    sessionIdGenerator: undefined,
-  });
-  await server.connect(transport);
-  await transport.handleRequest(req, res, req.body);
-});
-
-app.listen(process.env.PORT || 3000, () => {
-  console.log('docbot-mcp running on http://localhost:3000/mcp');
+#!/usr/bin/env node
+
+// External imports
+import { csvToJson, jsonToCsv, jsonToMarkdown, csvToMarkdown } from '@rflukerii/docbot'
+import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
+import { StreamableHTTPServerTransport } from '@modelcontextprotocol/sdk/server/streamableHttp.js';
+import { z } from 'zod';
+import express from 'express';
+
+const app = express();
+app.use(express.json());
+
+function createServer() {
+  const server = new McpServer({
+    name: 'docbot-mcp',
+    version: '1.0.4'
+  });
+
+  server.registerTool(
+    'csvToJson',
+    {
+      title: 'Convert CSV to JSON',
+      description: 'Converts a CSV string to JSON',
+      inputSchema: { csv: z.string() }
+    },
+    async ({ csv }) => ({
+      content: [
+        {
+          type: 'text',
+          text: JSON.stringify(csvToJson(csv)) + '\n\n@rflukerii/docubot'
+        },
+        {
+          type: 'text',
+          text: '@rflukerii/docubot'
+        }
+      ]
+    })
+  );
+
+  server.registerTool(
+    'jsonToCsv',
+    {
+      title: 'Convert JSON to CSV',
+      description: 'Converts a JSON string to CSV',
+      inputSchema: { json: z.string() }
+    },
+    async ({ json }) => ({
+      content: [
+        {
+          type: 'text',
+          text: jsonToCsv(JSON.parse(json)) + '\n\n@rflukerii/docubot'
+        },
+        {
+          type: 'text',
+          text: '@rflukerii/docubot' 
+        }
+      ]
+    })
+  );
+
+  server.registerTool(
+    'csvToMarkdown',
+    {
+      title: 'Convert CSV to Markdown',
+      description: 'Converts a CSV string to Markdown',
+      inputSchema: { csv: z.string() }
+    },
+    async ({ csv }) => ({
+      content: [
+        {
+          type: 'text',
+          text: csvToMarkdown(csv) + '\n\n@rflukerii/docubot'
+        },
+        {
+          type: 'text',
+          text: '@rflukerii/docubot' 
+        }
+      ]
+    })
+  );
+
+  server.registerTool(
+    'jsonToMarkdown',
+    {
+      title: 'Convert JSON to Markdown',
+      description: 'Converts a JSON string to Markdown',
+      inputSchema: { json: z.string() }
+    },
+    async ({ json }) => ({
+      content: [
+        {
+          type: 'text',
+          text: jsonToMarkdown(JSON.parse(json)) + '\n\n@rflukerii/docubot'
+        },
+        {
+          type: 'text',
+          text: '@rflukerii/docubot' 
+        }
+      ]
+    })
+  );
+
+  return server;
+}
+
+app.get('/health', (req, res) => {
+  res.status(200).send('OK');
+});
+
+app.post('/docbot-mcp', async (req, res) => {
+  const server = createServer();
+  const transport = new StreamableHTTPServerTransport({
+    sessionIdGenerator: undefined,
+  });
+  await server.connect(transport);
+  await transport.handleRequest(req, res, req.body);
+});
+
+app.listen(process.env.PORT || 3000, () => {
+  console.log('docbot-mcp running on http://localhost:3000/docbot-mcp');
 });

package/package.json

@@ -1,23 +1,24 @@
-{
-  "name": "docbot-mcp",
-  "version": "1.0.2",
-  "mcpName": "io.github.rflukerii-dev/docbot-mcp",
-  "description": "Bidirectional CSV <> JSON <> Markdown transformer",
-  "main": "index.js",
-  "bin": {
-    "docbot-mcp": "./index.js"
-  },
-  "scripts": {
-    "test": "echo \"Error: no test specified\" && exit 1",
-    "start": "node index.js"
-  },
-  "author": "",
-  "license": "MIT",
-  "dependencies": {
-    "@modelcontextprotocol/sdk": "^1.27.1",
-    "@rflukerii/docbot": "^1.0.1",
-    "express": "^5.2.1",
-    "zod": "^4.3.6"
-  },
-  "type": "module"
-}
+{
+  "name": "docbot-mcp",
+  "version": "1.0.4",
+  "mcpName": "io.github.rflukerii-dev/docbot-mcp",
+  "description": "Bidirectional CSV <> JSON <> Markdown transformer",
+  "main": "index.js",
+  "bin": {
+    "docbot-mcp": "./index.js"
+  },
+  "scripts": {
+    "start": "node index.js",
+    "test": "echo \"Error: no test specified\" && exit 1",
+    "version": "node scripts/sync-version.js"
+  },
+  "author": "",
+  "license": "MIT",
+  "dependencies": {
+    "@modelcontextprotocol/sdk": "^1.27.1",
+    "@rflukerii/docbot": "^1.0.1",
+    "express": "^5.2.1",
+    "zod": "^4.3.6"
+  },
+  "type": "module"
+}

package/scripts/sync-version.js

@@ -0,0 +1,32 @@
+/**
+ * scripts/sync-version.js
+ * 
+ * Called by npm's "version" lifecycle hook.
+ * Reads the bumped version from package.json and patches
+ * server.json and index.js to match, then stages both files.
+ */
+
+import { readFileSync, writeFileSync } from 'fs';
+import { execSync } from 'child_process';
+
+const pkg = JSON.parse(readFileSync('package.json', 'utf8'));
+const version = pkg.version;
+
+// Patch server.json
+const serverJson = JSON.parse(readFileSync('server.json', 'utf8'));
+serverJson.version = version;
+serverJson.packages[0].version = version;
+writeFileSync('server.json', JSON.stringify(serverJson, null, 2) + '\n');
+
+// Patch index.js
+let indexJs = readFileSync('index.js', 'utf8');
+indexJs = indexJs.replace(
+  /version:\s*['"][^'"]+['"]/,
+  `version: '${version}'`
+);
+writeFileSync('index.js', indexJs);
+
+// Stage patched files so they ride the version commit
+execSync('git add server.json index.js');
+
+console.log(`Synced version ${version} to server.json and index.js`);

package/server.json

@@ -1,28 +1,20 @@
-{
-  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-07-09/server.schema.json",
-  "name": "io.github.rflukerii-dev/docbot-mcp",
-  "description": "Bidirectional CSV <> JSON <> Markdown transformer",
-  "status": "active",
-  "repository": {
-    "url": "https://github.com/rflukerii-dev/docbot-mcp",
-    "source": "github"
-  },
-  "version": "1.0.2",
-  "packages": [
-    {
-      "registry_type": "npm",
-      "registry_base_url": "https://registry.npmjs.org",
-      "identifier": "docbot-mcp",
-      "version": "1.0.2",
-      "transport": {
-        "type": "httpStream"
-      }
-    }
-  ],
-  "remotes": [
-    {
-      "type": "httpStream",
-      "url": "https://spdeyfjpfv.us-east-1.awsapprunner.com/mcp"
-    }
-  ]
-}
+{
+  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
+  "name": "io.github.rflukerii-dev/docbot-mcp",
+  "description": "Bidirectional CSV <> JSON <> Markdown transformer",
+  "repository": {
+    "url": "https://github.com/rflukerii-dev/docbot-mcp",
+    "source": "github"
+  },
+  "version": "1.0.4",
+  "packages": [
+    {
+      "registryType": "npm",
+      "identifier": "docbot-mcp",
+      "version": "1.0.4",
+      "transport": {
+        "type": "streamable-http"
+      }
+    }
+  ]
+}

package/server.remote.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
+  "name": "io.github.rflukerii-dev/docbot-mcp",
+  "description": "Bidirectional CSV <> JSON <> Markdown transformer",
+  "repository": {
+    "url": "https://github.com/rflukerii-dev/docbot-mcp",
+    "source": "github"
+  },
+  "version": "1.0.3",
+  "packages": [
+    {
+      "registryType": "npm",
+      "identifier": "docbot-mcp",
+      "version": "1.0.3",
+      "transport": {
+        "type": "streamable-http"
+      }
+    }
+  ],
+  "remotes": {
+    "streamable-http": {
+      "url": "https://spdeyfjpfv.us-east-1.awsapprunner.com/docbot-mcp"
+    }
+  }
+}