github.com b6bda023
gChain projects and find good first issues. Code of Conduct – Our community guidelines and standards for participation.
Source Taxonomy
Listings discovered from PYPI. Use this view to compare quality and reliability within one ecosystem.
Profiles enriched with trust, contract, and editorial guidance.
gChain projects and find good first issues. Code of Conduct – Our community guidelines and standards for participation.
-level agent orchestration framework Integrations — Chat & embedding models, tools & toolkits, and more LangSmith — Agent evals, observability, and debugging for LLM apps LangSmith...
ditorconfig .gitattributes .gitattributes .gitignore .gitignore .markdownlint.json .markdownlint.json .mcp.json .mcp.json .pre-commit-config.yaml .pre-commit-config.yaml AGENTS.md...
ate with the latest AI developments through an active open-source community Flexible abstraction layers — Work at the level of abstraction that suits your needs — from high-level c...
and medium teams Startups Nonprofits BY USE CASE App Modernization DevSecOps DevOps CI/CD View all use cases BY INDUSTRY Healthcare Financial services Manufacturing Government View...
GitHub - langchain-ai/langchain: The agent engineering platform · GitHub Skip to content Navigation Menu Toggle navigation Sign in Appearance settings Platform AI CODE CREATION Git...
VAILABLE ADD-ONS GitHub Advanced Security Enterprise-grade security features Copilot for Business Enterprise-grade AI features Premium Support Enterprise-grade 24/7 support Pricing...
b or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.
d langchain from langchain . chat models import init chat model model = init chat model ( "openai:gpt-5.4" ) result = model .
your application's needs. As the industry frontier evolves, adapt quickly — LangChain's abstractions keep you moving without losing momentum Rapid prototyping — Quickly build and i...
it process with context ( x , ctx ) Context Properties and Methods The Context object provides the following capabilities: ctx.request id - Unique ID for the current request ctx.cl...
custom level await ctx.report progress(progress, total=None, message=None) - Report operation progress await ctx.read resource(uri) - Read a resource by URI await ctx.elicit(messag...
tuple, Union, Optional, etc.) - wrapped in {"result": value} Classes without type hints cannot be serialized for structured output.
0 )) return Image ( data = img . tobytes (), format = "png" ) Full example: examples/snippets/servers/images.py Context The Context object is automatically injected into tool and r...
nt ] @ mcp . tool () def advanced tool () - CallToolResult : """Return CallToolResult directly for full control including meta field.""" return CallToolResult ( content = [ TextCon...
th empty content.""" return CallToolResult ( content = []) Full example: examples/snippets/servers/direct call tool result.py Important: CallToolResult must always be returned (no...
" , ) await ctx . debug ( f"Completed step { i + 1 } " ) return f"Task ' { task name } ' completed" Full example: examples/snippets/servers/tool progress.py Completions MCP support...
he server args = [ "run" , "server" , "completion" , "stdio" ], Server with completion support env = { "UV INDEX" : os . environ .
name } " ) Complete resource template arguments if templates . resourceTemplates : template = templates .
ner" : "modelcontextprotocol" }, ) print ( f"Completions for 'repo' with owner='modelcontextprotocol': { result . completion . values } " ) Complete prompt arguments if prompts .
n" : 40.0 , "std dev" : 5.2 } Ordinary classes with type hints work for structured output class UserProfile : name : str age : int email : str | None = None def init ( self , name...
" ) condition : str wind speed : float @ mcp . tool () def get weather ( city : str ) - WeatherData : """Get weather for a city - returns structured data.""" Simulated weather data...
ns unstructured output - no schema generated""" return UntypedConfig ( "value1" , "value2" ) Lists and other types are wrapped automatically @ mcp .
ew" ) def review code ( code : str ) - str : return f"Please review this code: \n \n { code } " @ mcp .
website url = "https://example.com" , icons = [ icon ] ) Add icons to tools, resources, and prompts @ mcp .
annotation causes the tool to be classified as structured and this is undesirable , the classification can be suppressed by passing structured output=False to the @tool decorator.
ments/{name}" ) def read document ( name : str ) - str : """Read a document by name.""" This would normally read from disk return f"Content of { name } " @ mcp .
str : """Get weather for a city.""" This would normally call a weather API return f"Weather in { city } : 22degrees { unit [ 0 ].
or i in range ( steps ): progress = ( i + 1 ) / steps await ctx . report progress ( progress = progress , total = 1.0 , message = f"Step { i + 1 } / { steps } " , ) await ctx .
: yield AppContext ( db = db ) finally : Cleanup on shutdown await db .
, and Streamable HTTP Handle all MCP protocol messages and lifecycle events Installation Adding MCP to your python project We recommend using uv to manage your Python projects.
CP server mcp = FastMCP ( "Demo" , json response = True ) Add an addition tool @ mcp .
P transport if name == " main " : mcp . run ( transport = "streamable-http" ) Full example: examples/snippets/servers/fastmcp quickstart.py You can install this server in Claude Co...
it like a web API, but specifically designed for LLM interactions.
aclasses import dataclass from mcp . server . fastmcp import Context , FastMCP from mcp . server .
tures Solutions BY COMPANY SIZE Enterprises Small and medium teams Startups Nonprofits BY USE CASE App Modernization DevSecOps DevOps CI/CD View all use cases BY INDUSTRY Healthcar...