### Python MCP Server Project Setup

Source: https://docs.enconvo.ai/advanced/mcp-advanced

Installs the MCP library for Python.

```bash
mkdir my-mcp-server
cd my-mcp-server
pip install mcp
```

--------------------------------

### TypeScript MCP Server Project Setup

Source: https://docs.enconvo.ai/advanced/mcp-advanced

Installs necessary dependencies for creating an MCP server in TypeScript.

```bash
mkdir my-mcp-server
cd my-mcp-server
npm init -y
npm install @modelcontextprotocol/sdk
npm install -D typescript @types/node
```

--------------------------------

### Execute Python Virtual Environment and Install Package

Source: https://docs.enconvo.ai/ai/code-runner

This example demonstrates how an AI agent can instruct the Code Runner to create a Python virtual environment and install a package using pip. Ensure the Python interpreter and pip are available in the environment.

```shell
python3 -m venv myenv
source myenv/bin/activate && pip install pandas
```

--------------------------------

### Install Skill from GitHub Repository

Source: https://docs.enconvo.ai/configuration/skills

Command to install a skill directly from a GitHub repository URL, supporting subdirectory paths.

```bash
/skill-installer https://github.com/anthropics/skills/tree/main/skills/pptx
```

--------------------------------

### Install Extension from GitHub

Source: https://docs.enconvo.ai/extensions/overview

Clone an extension repository from GitHub and install it into EnConvo by pointing to the local folder.

```bash
# Clone extension repository
git clone https://github.com/enconvo/extension-name

# Install in EnConvo
# Settings → Extensions → Install from folder
```

--------------------------------

### Install Skill from EnConvo Skills Store

Source: https://docs.enconvo.ai/configuration/skills

Command to install a skill by its name from the EnConvo Skills Store.

```bash
/skill-installer pdf
```

--------------------------------

### Loop Example: Process URLs

Source: https://docs.enconvo.ai/workflows/advanced-workflows

An example demonstrating how to loop through a list of URLs, fetch content from each, and summarize the fetched content.

```text
URL List → Loop Items (for each url)
             → Web Fetch ({{current_item}})
             → Summarize ({{fetch_result}})
           → Collect Summaries → Format Report
```

--------------------------------

### Initialize New EnConvo Extension

Source: https://docs.enconvo.ai/extensions/developing

Use this command to create a new EnConvo extension project. Navigate into the created directory and install dependencies.

```bash
npx create-enconvo-extension my-extension
cd my-extension
npm install
```

--------------------------------

### Access Extensions via SmartBar

Source: https://docs.enconvo.ai/extensions/overview

Use a forward slash '/' prefix in the SmartBar to quickly invoke installed extensions with their commands.

```bash
/translate Hello world to Spanish
/code explain this function
/image a sunset over mountains
/summarize this article
```

--------------------------------

### Example Image Generation Prompts

Source: https://docs.enconvo.ai/ai/image-generation

Use these prompts in SmartBar to generate various types of images. Simply type /image followed by your description.

```text
/image A serene mountain lake at sunset with snow-capped peaks
/image Minimalist logo for a tech startup, blue and white colors
/image Cute cartoon cat sitting on a stack of books
/image Professional headshot of a friendly robot in a business suit
```

--------------------------------

### Install Ollama using Homebrew

Source: https://docs.enconvo.ai/providers/ollama

Use this command to install Ollama on macOS via Homebrew.

```bash
brew install ollama
```

--------------------------------

### Skill Directory Structure Example

Source: https://docs.enconvo.ai/configuration/skills

A typical skill directory includes a SKILL.md file for instructions and metadata, along with optional scripts, references, and assets.

```tree
my-skill/
├── SKILL.md          # Required: instructions + metadata
├── scripts/          # Optional: executable code
├── references/       # Optional: documentation
└── assets/           # Optional: templates, resources
```

--------------------------------

### Provider Selection Example

Source: https://docs.enconvo.ai/extensions/built-in-extensions

Demonstrates how consumer extensions target specific provider extensions using a command key format. Configure default providers in extension settings or let AI agents choose automatically.

```plaintext
chat_with_ai (consumer) → llm|open_ai (provider)
tts (consumer) → tts_providers|openai_tts_provider (provider)
translate (consumer) → translate_providers|deepl_translate_provider (provider)
```

--------------------------------

### SmartBar Built-in Calculator Examples

Source: https://docs.enconvo.ai/features/smartbar

Type mathematical expressions directly into the SmartBar input to get instant results. Supports standard arithmetic, trigonometric functions, and more. Press Enter to copy the result.

```text
2+3*4       → 14
```

```text
sqrt(144)   → 12
```

```text
sin(45)     → 0.7071...
```

```text
100/3       → 33.333...
```

--------------------------------

### MCP Store Manifest Example

Source: https://docs.enconvo.ai/advanced/mcp-advanced

Define a manifest for publishing an MCP server to the store, including name, version, description, transport, command, and configuration options.

```json
{
  "name": "my-awesome-server",
  "version": "1.0.0",
  "description": "Does awesome things with AI",
  "transport": "stdio",
  "command": "npx",
  "args": ["-y", "my-awesome-server"],
  "config": {
    "api_key": {
      "type": "password",
      "description": "Your API key for the awesome service",
      "required": true
    }
  }
}
```

--------------------------------

### Apple Mail Usage Examples

Source: https://docs.enconvo.ai/integrations/apple-ecosystem

These examples demonstrate how to interact with the Apple Mail integration using natural language commands. They cover actions like viewing emails, composing new messages, and archiving messages.

```text
"Show me my unread emails"
```

```text
"Send an email to alice@example.com about the project deadline"
```

```text
"Archive all emails from notifications@github.com"
```

```text
"What did Bob say in his last email?"
```

--------------------------------

### Manual Extension Installation Path

Source: https://docs.enconvo.ai/features/browser-control

Specifies the directory path for manually loading the Enconvo Companion extension. Ensure Enconvo is restarted if the folder does not exist.

```bash
~/.enconvo/chrome_extension/
```

--------------------------------

### Example Text-to-Video Prompt

Source: https://docs.enconvo.ai/ai/video-generation

Use this structure for creating effective text-to-video prompts. Ensure prompts are in English and include subject, action, setting, style, and camera movement.

```text
A golden retriever running through a field of wildflowers at sunset,
slow motion, cinematic lighting, warm tones
```

```text
A futuristic city skyline at night with flying cars and neon lights,
drone shot sweeping across the buildings, cyberpunk aesthetic
```

```text
A cup of coffee being poured in slow motion, close-up shot,
steam rising, soft morning light through a window
```

--------------------------------

### Load and Get Command Configuration

Source: https://docs.enconvo.ai/extensions/extension-api-reference

Use CommandManageUtils to load a command's full configuration or get raw command info synchronously.

```typescript
import { CommandManageUtils, ExtensionManageUtils, PreferenceManageUtils } from "@enconvo/api";

// Load a command's full configuration
const config = await CommandManageUtils.loadCommandConfig({
  commandKey: "gmail|send_email",
  useAsRunParams: true
});

// Get raw command info (synchronous)
const rawCmd = CommandManageUtils.getRawCommandInfo("llm|open_ai");
```

--------------------------------

### SKILL.md Frontmatter Example

Source: https://docs.enconvo.ai/configuration/skills

The SKILL.md file requires a frontmatter block with 'name' and 'description' fields to define the skill's identity and trigger conditions.

```markdown
---
name: my-skill
description: Explain exactly when this skill should and should not trigger.
---

Step-by-step instructions for EnConvo to follow.
```

--------------------------------

### Write a Simple Command Handler

Source: https://docs.enconvo.ai/extensions/developing

Implement the `Command` interface in `src/index.ts` to handle extension commands. This example shows a command that displays a toast notification and returns a greeting.

```typescript
import { Command, showToast } from '@enconvo/api';

export default class HelloCommand implements Command {
  async run(input: string): Promise<string> {
    showToast({ title: 'Hello!', message: input });
    return `Hello, ${input || 'World'}!`;
  }
}
```

--------------------------------

### Run Extension in Development Mode

Source: https://docs.enconvo.ai/extensions/developing

Use 'npm run dev' to start your extension with hot reload enabled for a faster development cycle.

```bash
npm run dev
```

--------------------------------

### Agent Output Format Example

Source: https://docs.enconvo.ai/ai/agents

Specifies the desired output structure for an agent. This ensures consistent and usable results, especially for structured data.

```markdown
# Output Format
**Subject:** [suggested subject line]

[email body]

---
**Tone:** [formal/casual/neutral]
**Word count:** [count]
```

--------------------------------

### Agent Role Definition Example

Source: https://docs.enconvo.ai/ai/agents

Defines a specific role for an agent to ensure focused and expert responses. Use this to guide the agent's persona and expertise.

```markdown
# Role
Professional email writer for business communication.
```

--------------------------------

### Example Questions for Recording Analysis

Source: https://docs.enconvo.ai/features/meeting-recording

Ask specific questions about meeting content to get precise answers. This feature leverages semantic search against transcriptions to retrieve relevant information.

```text
What did we decide about the pricing strategy?
Who is responsible for the design mockups?
What was the timeline discussed for the product launch?
Did anyone mention concerns about the budget?
Summarize what Speaker 2 said about customer feedback
What were the main disagreements in the meeting?
```

--------------------------------

### Agent Invocation from SmartBar

Source: https://docs.enconvo.ai/ai/agents

Demonstrates how to invoke agents directly from the SmartBar using the '@' prefix followed by the agent's name and query.

```bash
@deep-research What are the current trends in AI regulation?
@code-reviewer Review this pull request for security issues
@my-custom-bot Analyze the Q4 sales report
```

--------------------------------

### Transcription Output Example

Source: https://docs.enconvo.ai/features/meeting-recording

This is an example of the structured transcription output, showing timestamps, speaker labels, and dialogue segments.

```plaintext
[00:00:12] Speaker 1: Let's start with the Q3 review. Revenue
is up 15% compared to last quarter.

[00:00:28] Speaker 2: That's great. Can you break down the
growth by product line?

[00:00:35] Speaker 1: Sure. The cloud platform grew 22%,
while consulting services grew 8%.

[00:01:02] Speaker 3: What about customer retention rates?
```

--------------------------------

### Pull a Local LLM Model with Ollama

Source: https://docs.enconvo.ai/configuration/privacy-security

Use this command to download and install a local language model for offline use with EnConvo. Ensure Ollama is installed first.

```bash
ollama pull llama3.2
```

--------------------------------

### Create Custom MCP Server with Python

Source: https://docs.enconvo.ai/features/mcp

This Python snippet demonstrates how to create a custom MCP server, define a tool using a decorator, and run the server using stdio transport.

```python
from mcp.server import Server
from mcp.server.stdio import stdio_server

server = Server("my-custom-server")

@server.tool()
async def get_weather(city: str) -> str:
    """Get current weather for a city."""
    weather = await fetch_weather(city)
    return json.dumps(weather)

async def main():
    async with stdio_server() as (read, write):
        await server.run(read, write)
```

--------------------------------

### Changelog Generator Skill Example

Source: https://docs.enconvo.ai/configuration/skills

This skill generates a changelog from git commits, categorizing them into features, fixes, and breaking changes. It includes a detailed output format example.

```markdown
---
name: changelog-generator
description: Generate a changelog from git commits. Use when the user asks to create a changelog, release notes, or commit summary. Do not use for general git operations.
---

## Instructions

1. Read the git log for the specified date range or number of commits.
2. Group commits by category:
   - **Features**: New functionality (commits starting with "feat:")
   - **Fixes**: Bug fixes (commits starting with "fix:")
   - **Breaking Changes**: Changes that break backward compatibility
   - **Other**: Everything else
3. For each commit, write a user-facing description (not the raw commit message).
4. Format as markdown with version header, date, and categorized bullet points.
5. Highlight breaking changes with a warning callout.

## Output Format

```markdown
## v1.2.0 (2024-01-15)

### Features

* Added dark mode support for all pages
* New export to PDF option in reports

### Fixes

* Fixed login timeout on slow connections
* Resolved duplicate notification issue

### Breaking Changes

⚠️ API endpoint `/v1/users` now requires authentication

```
```

--------------------------------

### NativeAPI.callCommand

Source: https://docs.enconvo.ai/extensions/extension-api-reference

Invoke any other extension command programmatically. This allows extensions to interact with and trigger functionalities of other installed extensions.

```APIDOC
## NativeAPI.callCommand

### Description
Invoke any other extension command programmatically.

### Method Signature
`NativeAPI.callCommand(commandId: string, payload?: any): Promise<any>`

### Parameters
#### Path Parameters
- **commandId** (string) - Required - The unique identifier of the command to invoke.
- **payload** (any) - Optional - The data to pass to the command.

### Request Example
```typescript
import { NativeAPI } from "@enconvo/api";

// Call Gmail to send an email
const result = await NativeAPI.callCommand("gmail|send_email", {
  to: "user@example.com",
  subject: "Hello",
  body: "Message content"
});
```
```

--------------------------------

### Full-Text Search Example

Source: https://docs.enconvo.ai/advanced/knowledge-base-advanced

Demonstrates how full-text search with fuzzy matching can be used for keyword-based retrieval in LanceDB.

```text
Query "OAuth2 PKCE flow"
  → Full-text index lookup with fuzziness
  → Return matching chunks
```

--------------------------------

### Basic Python MCP Server Implementation

Source: https://docs.enconvo.ai/advanced/mcp-advanced

Defines a simple MCP server with 'hello' and 'search_records' tools using the `mcp` library.

```python
import json
from mcp.server import Server
from mcp.server.stdio import stdio_server

server = Server("my-custom-server")


@server.tool()
async def hello(name: str) -> str:
    """Say hello to someone.

    Args:
        name: Person's name
    """
    return f"Hello, {name}!"


@server.tool()
async def search_records(
    query: str,
    limit: int = 10,
    category: str = "all"
) -> str:
    """Search records in the database.

    Args:
        query: Search query
        limit: Max results to return
        category: Filter by category (all, active, archived)
    """
    results = await perform_search(query, limit, category)
    return json.dumps(results, indent=2)


async def main():
    async with stdio_server() as (read, write):
        await server.run(read, write)


if __name__ == "__main__":
    import asyncio
    asyncio.run(main())
```

--------------------------------

### Check Node.js Version

Source: https://docs.enconvo.ai/getting-started/troubleshooting

Verify your installed Node.js version. EnConvo requires Node.js 18 or higher. Update if necessary.

```bash
node --version
```

```bash
brew install node
```

--------------------------------

### Run React Project Build

Source: https://docs.enconvo.ai/ai/code-runner

Use this command to build a React project and check for errors. The agent will execute the build and report the status.

```shell
npm run build
```

--------------------------------

### Single File API Route

Source: https://docs.enconvo.ai/extensions/extension-api-reference

Files in `src/api/` are auto-discovered as API routes. This example shows a simple status endpoint.

```typescript
// src/api/status.ts
export default async function main(request: Request) {
  return Response.json({ status: "ok", uptime: process.uptime() });
}
```

--------------------------------

### Referencing Documentation in Instructions

Source: https://docs.enconvo.ai/configuration/skills

Shows how to reference external documentation files within skill instructions using markdown.

```markdown
Consult `references/api-docs.md` for the API schema before making requests.
```

--------------------------------

### SKILL.md Frontmatter and Instructions

Source: https://docs.enconvo.ai/configuration/skills

Defines the skill's name, description, and provides step-by-step instructions for the AI. Use instruction-only skills unless deterministic behavior or external tooling is required.

```markdown
---
name: my-skill
description: Summarize selected text into bullet points. Use when the user asks for a summary or key takeaways. Do not use for translation or rewriting tasks.
---

## Instructions

1. Read the selected text from the user's input.
2. Identify the 3-5 most important points.
3. Return a bullet-point summary.
4. Keep each bullet under 20 words.
```

--------------------------------

### Vector Similarity Search Example

Source: https://docs.enconvo.ai/advanced/knowledge-base-advanced

Illustrates the process of embedding a query and comparing it against stored vectors to find semantically similar chunks.

```text
Query "How does authentication work?"
  → Embed query → [0.12, -0.45, 0.78, ...]
  → Compare against all chunk vectors
  → Return top-K most similar chunks
```

--------------------------------

### environment

Source: https://docs.enconvo.ai/extensions/extension-api-reference

Access runtime context about the current command execution, including extension details, development status, and user interface settings.

```APIDOC
## environment

### Description
The `environment` object exposes runtime context about the current command execution.

### Properties
- **extensionName** (string): Current extension name.
- **commandName** (string): Current command name.
- **commandTitle** (string): Display title of the command.
- **assetsPath** (string): Path to extension's assets/ directory.
- **supportPath** (string): Per-extension support directory.
- **rootSupportPath** (string): Root support directory.
- **cachePath** (string): Cache directory.
- **isDevelopment** (boolean): true if running in dev mode.
- **appearance** (string): "light" | "dark".
- **textSize** (string): "medium" | "large".
- **chatConversationId** (string): Current conversation ID.
- **chatSessionId** (string): Current session ID.
- **enconvoVersion** (string): EnConvo app version.
- **runType** (string): "command" | "api" | "flow".
- **flowId** (string): Workflow ID (if running in a workflow).

### Usage Example
```typescript
import { environment } from "@enconvo/api";

console.log(environment.extensionName);
console.log(environment.isDevelopment);
```
```

--------------------------------

### Build and Test Extension

Source: https://docs.enconvo.ai/extensions/developing

Use `npm run build` to compile your extension and `npm run dev` for hot reloading during development.

```bash
npm run build
npm run dev  # Hot reload during development
```

--------------------------------

### Run Go Program

Source: https://docs.enconvo.ai/ai/code-runner

Compile and run a Go program using the 'go run' command. Ensure the Go source file is present in the working directory.

```shell
go run main.go
```

--------------------------------

### Custom Server Configuration

Source: https://docs.enconvo.ai/advanced/mcp-advanced

Define a custom server with a name, transport type, command, and arguments.

```json
{
  "name": "my-custom-server",
  "transport": "stdio",
  "command": "python",
  "args": ["/path/to/my-mcp-server/server.py"]
}
```

--------------------------------

### Add a stdio MCP Server

Source: https://docs.enconvo.ai/features/mcp

Configure a local MCP server that runs as a Node.js process. Specify the command, arguments, and any necessary paths.

```json
{
  "name": "filesystem",
  "transport": "stdio",
  "command": "npx",
  "args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/you/Documents"]
}
```

--------------------------------

### Read OpenClaw Gateway Token

Source: https://docs.enconvo.ai/providers/openclaw

Use this command to extract the Gateway token from the default OpenClaw configuration file. Ensure the `jq` utility is installed.

```bash
jq -r '.gateway.auth.token' ~/.openclaw/openclaw.json
```

--------------------------------

### Dynamic Configuration with Template Strings

Source: https://docs.enconvo.ai/advanced/mcp-advanced

Use template strings for dynamic values in command, arguments, and environment variables, referencing built-in variables like `__dirname` and `HOME`, and user-provided configurations.

```json
{
  "command": "node",
  "args": ["${__dirname}/server.js"],
  "env": {
    "HOME": "${HOME}",
    "CUSTOM_SETTING": "${user_config.custom_setting}"
  }
}
```

--------------------------------

### Apple Shortcuts Integration

Source: https://docs.enconvo.ai/integrations/apple-ecosystem

Run any installed Apple Shortcut directly from EnConvo by using natural language commands. Supports text input and output.

```text
"Run my 'Morning Routine' shortcut"
```

```text
"List all my shortcuts"
```

```text
"Execute the 'Resize Image' shortcut with the file on my desktop"
```