MCP

The framework speaks the Model Context Protocol  natively. Plug stdio or HTTP MCP servers in directly; the agent loop treats them like any other ToolHost.

from loomflow import Agent
from loomflow.mcp import MCPRegistry, MCPServerSpec
 
registry = MCPRegistry([
    MCPServerSpec.stdio(
        name="git",
        command="uvx",
        args=["mcp-server-git", "--repo", "/Users/me/code/myrepo"],
    ),
    MCPServerSpec.http(
        name="hosted",
        url="https://example.com/mcp/",
        headers={"Authorization": "Bearer ..."},
    ),
])
 
agent = Agent(
    "You are a coding assistant.",
    model="claude-opus-4-7",
    tools=registry,
)

Tool name conflicts across servers are auto-disambiguated: git.commit and github.commit if both servers expose commit; just commit if only one does. Either form is accepted at call time.

Read more

What MCP gets you

• Language-agnostic tools. MCP servers can be Python, Node, Rust. Anything. The framework launches them as subprocesses (stdio) or talks to them over HTTP.
• Reusable tool servers. The MCP ecosystem already ships servers for git, filesystem, GitHub, Slack, browser, Figma. You don’t re-implement what already exists.
• The full protocol surface. Beyond tools, the registry aggregates resources and prompts across servers, refreshes tool lists automatically when a server announces listChanged, and can answer server-initiated sampling requests with a model you choose.
• Fault isolation. One dead server never takes down the others — its tools are skipped, its name lands in registry.unavailable, and it heals on the next refresh. See Server specs + registry.
• Auth and rate limiting on the server. Hosted MCP servers authenticate the framework via headers; the agent never sees the underlying credentials.

Install

pip install 'loomflow[mcp]'

Pulls in the official mcp SDK + httpx.

Compose with built-in tools

MCPRegistry is just a ToolHost. Mix MCP servers with regular @tool functions by wrapping the registry with ExtendedToolHost, which combines a base host with extra in-process tools:

from loomflow import Agent, tool
from loomflow.mcp import MCPRegistry, MCPServerSpec
from loomflow.architecture.tool_host_wrappers import ExtendedToolHost
 
@tool
async def custom_search(q: str) -> str:
    """My custom search tool."""
    ...
 
mcp_registry = MCPRegistry([
    MCPServerSpec.stdio("git", "uvx", ["mcp-server-git"]),
    MCPServerSpec.stdio("fs",  "uvx", ["mcp-server-filesystem", "--root", "."]),
])
 
# Combine the MCP registry with the custom tool into one host
agent = Agent(
    "...",
    model="claude-opus-4-7",
    tools=ExtendedToolHost(mcp_registry, [custom_search]),
)