​

Senso MCP Server

The Senso MCP (Model Context Protocol) server enables AI agents to interact with your Senso knowledge base using a standardized protocol designed specifically for AI-to-AI communication.

​

What is MCP?

Model Context Protocol (MCP) is an open protocol that standardizes how AI applications share context and tools. Created by Anthropic, MCP provides a consistent way for AI agents to:

• Access external tools and data sources
• Share context between different AI systems
• Execute actions in a secure, controlled manner

Think of MCP as a universal adapter that lets AI agents plug into various services without needing to understand each service’s specific API.

​

Why MCP is Better for AI Agents

While traditional APIs work well for human developers, MCP offers several advantages for AI agents:

​

1. Structured Tool Definitions

MCP provides AI agents with clear, structured descriptions of available tools, including:

• What each tool does
• Required and optional parameters
• Expected return formats

This eliminates the guesswork that often occurs when AI agents try to construct API calls from documentation.

​

2. Type Safety

Unlike traditional APIs where agents might send malformed requests, MCP enforces parameter types and validates inputs automatically, reducing errors.

​

3. Conversational Interface

MCP servers can maintain context across multiple interactions, allowing for more natural, conversational workflows rather than isolated API calls.

​

4. Built-in Error Handling

MCP provides standardized error responses that AI agents can understand and recover from, rather than cryptic HTTP status codes.

​

5. Discovery and Introspection

AI agents can query an MCP server to discover available tools and their capabilities, making integration more dynamic and adaptable.

​

Senso MCP Server

The Senso MCP server provides AI agents with powerful tools to interact with your knowledge base:

​

Available Tools

​

Key Features

• *Semantic Search: Find relevant information using natural language, not just keywords
• *Context-Aware Generation: Create new content that’s grounded in your existing knowledge
• *Structured Outputs: Use templates to ensure generated content follows specific formats (JSON or text)
• *Reusable Workflows: Save prompts and templates for consistent content generation

​

Installation

​

Prerequisites

• Python 3.8 or higher
• A Senso API key from sdk.senso.ai

​

Quick Start

1. Clone the repository:

git clone https://github.com/AI-Template-SDK/api-mcp-server.git
cd api-mcp-server

2. Install dependencies:

# Create and activate virtual environment
uv venv

# On macOS/Linux
source .venv/bin/activate

# On Windows
.venv\Scripts\activate

# Install dependencies from pyproject.toml
uv pip install -e .

3. Set your Senso API key:

• Open server.py in your text editor
• Locate the line: API_KEY = "tgr_YOUR_API_KEY"
• Replace it with your own Senso API key

4. Run the server:

python senso_mcp_server.py

​

Using with Claude Desktop

Add the following to your Claude Desktop configuration:

{
    "mcpServers": {
        "senso": {
            "command": "uv",
            "args": [
                "--directory",
                "path/to/your/directory",
                "run",
                "server.py"
            ]
        }
    }
}

​

GitHub Repository

Find the complete source code and contribute to the project: