Expose your service to Agents
Concierge is a declarative framework that allows LLMs to interact with your applications and navigate through complex service hierarchies. Build applications for AI/LLM use exposed over the web to guide agents towards domain specific goals.
Concierge token efficiency across increasing difficulty levels of tasks.
# Install MCP SDK
pip install openmcp-sdk
# Initialize with ChatGPT Apps support
openmcp init --chatgpt
# Deploy your service
openmcp deployExample: Interactive Applications rendering in ChatGPT
from openmcp import OpenMCP
mcp = OpenMCP("my-app", stateless_http=True)
@mcp.widget(uri="widget://chart", html="<div>Chart Widget</div>")
def show_chart(data: str):
"""Display a chart widget."""
return {"data": data}Concierge OpenMCP provides it's own abstractions like widgets and OpenAI emulator that emulates the window.openai in the inspector enabling app creation in seconds.
Use https://getconcierge.app/docs to get started.
# Install MCP Core
pip install openmcp-sdk
# Initialize your MCP project
openmcp init
# Deploy your service
openmcp deployExample: Convert your existing MCPs to OpenMCP
from mcp.server.fastmcp import FastMCP
from openmcp import OpenMCP
# Enable OpenMCP on FastMCP
mcp = OpenMCP(FastMCP("my-server")) # 1 line replacement
@mcp.tool()
def get_user(user_id: int):
"""Get user by ID."""
return {"id": user_id, "name": "John"}
if __name__ == "__main__":
mcp.run()Your existing MCP tools work unchanged. OpenMCP adds widget support, inspector debugging, and ChatGPT Apps compatibility. Use https://getconcierge.app/docs to get started.
# Install MCP Core with all features
pip install openmcp-sdk[all]
# Initialize concierge project
openmcp init
# Deploy with enhanced capabilities
openmcp deployExample: Enable OpenMCP Search Backend
from openmcp import OpenMCP, Config, ProviderType
mcp = OpenMCP("my-app", config=Config(provider_type=ProviderType.SEARCH))
@mcp.tool()
def add(a: int, b: int):
"""Add two numbers together."""
return a + b
@mcp.tool()
def subtract(a: int, b: int):
"""Subtract b from a."""
return a - b
# Automatically adds search_tools and call_tool!| Protocol | Status | Description |
|---|---|---|
| AIP (Agentic Interactive Protocol) | ✅ Supported | Concierge natively implements the Agentic Interactive Protocol (AIP) for connecting agents to web-exposed services. Tools are served dynamically, preventing model context bloat, saving cost and latency. |
| MCP (Model Context Protocol) | ✅ Supported | Now express Concierge workflows through MCP |
Developers define workflows with explicit rules and prerequisites. You control agent autonomy by specifying legal tasks at each stage and valid transitions between stages. For example: agents cannot checkout before adding items to cart. Concierge enforces these rules, validates prerequisites before task execution, and ensures agents follow your defined path through the application.
Tasks are the smallest granularity of callable business logic. Several tasks can be defined within 1 stage. Ensuring these tasks are avialable or callable at the stage.
@task(description="Add product to shopping cart")
def add_to_cart(self, state: State, product_id: str, quantity: int) -> dict:
"""Adds item to cart and updates state"""
cart_items = state.get("cart.items", [])
cart_items.append({"product_id": product_id, "quantity": quantity})
state.set("cart.items", cart_items)
return {"success": True, "cart_size": len(cart_items)}A stage is a logical sub-step towards a goal, Stage can have several tasks grouped together, that an agent can call at a given point.
@stage(name="product")
class ProductStage:
@task(description="Add product to shopping cart")
def add_to_cart(self, state: State, product_id: str, quantity: int) -> dict:
"""Adds item to cart"""
@task(description="Save product to wishlist")
def add_to_wishlist(self, state: State, product_id: str) -> dict:
"""Saves item for later"""
A state is a global context that is maintained by Concierge, parts of which can get propagated to other stages as the agent transitions and navigates through stages.
# State persists across stages and tasks
state.set("cart.items", [{"product_id": "123", "quantity": 2}])
state.set("user.email", "user@example.com")
state.set("cart.total", 99.99)
# Retrieve state values
items = state.get("cart.items", [])
user_email = state.get("user.email")A workflow is a logic grouping of several stages, you can define graphs of stages which represent legal moves to other stages within workflow.
@workflow(name="shopping")
class ShoppingWorkflow:
discovery = DiscoveryStage # Search and filter products
product = ProductStage # View product details
selection = SelectionStage # Add to cart/wishlist
cart = CartStage # Manage cart items
checkout = CheckoutStage # Complete purchase
transitions = {
discovery: [product, selection],
product: [selection, discovery],
selection: [cart, discovery, product],
cart: [checkout, selection, discovery],
checkout: []
}Dashboard
@workflow(name="amazon_shopping")
class AmazonShoppingWorkflow:
browse = BrowseStage # Search and filter products
select = SelectStage # Add items to cart
checkout = CheckoutStage # Complete transaction
transitions = {
browse: [select],
select: [browse, checkout],
checkout: []
}@stage(name="browse")
class BrowseStage:
@task(description="Search for products by keyword")
def search_products(self, state: State, query: str) -> dict:
"""Returns matching products"""
@task(description="Filter products by price range")
def filter_by_price(self, state: State, min_price: float, max_price: float) -> dict:
"""Filters current results by price"""
@task(description="Sort products by rating or price")
def sort_products(self, state: State, sort_by: str) -> dict:
"""Sorts: 'rating', 'price_low', 'price_high'"""
@stage(name="select")
class SelectStage:
@task(description="Add product to shopping cart")
def add_to_cart(self, state: State, product_id: str, quantity: int) -> dict:
"""Adds item to cart"""
@task(description="Save product to wishlist")
def add_to_wishlist(self, state: State, product_id: str) -> dict:
"""Saves item for later"""
@task(description="Star product for quick access")
def star_product(self, state: State, product_id: str) -> dict:
"""Stars item as favorite"""
@task(description="View product details")
def view_details(self, state: State, product_id: str) -> dict:
"""Shows full product information"""@stage(name="checkout", prerequisites=["cart.items", "user.payment_method"])
class CheckoutStage:
@task(description="Apply discount code")
def apply_discount(self, state: State, code: str) -> dict:
"""Validates and applies discount"""
@task(description="Complete purchase")
def complete_purchase(self, state: State) -> dict:
"""Processes payment and creates order"""We are building the agentic web. Come join us.
Interested in contributing or building with Concierge? Reach out.
Contributions are welcome. Please open an issue or submit a pull request.
