kailash-mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited kailash-mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Production-ready MCP server implementation built into Kailash Core SDK for seamless AI agent integration.
Kailash's MCP module provides:
from kailash_mcp import MCPServer
# Create MCP server
server = MCPServer(name="my-server")
# Register workflow as MCP tool
@server.tool()
def summarize(text: str) -> str:
"""Summarize the given text."""
workflow = create_summary_workflow()
results, run_id = runtime.execute(workflow.build())
return results["summary"]
# Run server (stdio transport by default)
server.run()The Model Context Protocol enables AI agents to:
MCP supports multiple transport mechanisms:
Tools are type-safe functions exposed to AI agents:
Resources expose data to AI agents:
Use MCP when you need to:
from kailash_mcp import MCPServer
from kailash.workflow.builder import WorkflowBuilder
server = MCPServer(name="workflow-server")
@server.tool()
def process_data(input: str) -> dict:
"""Process data through a workflow."""
workflow = WorkflowBuilder()
# Build workflow
results, run_id = runtime.execute(workflow.build())
return results["output"]from nexus import Nexus
# Nexus automatically creates MCP channel
app = Nexus()
app.register("my_workflow", workflow.build())
app.start() # Includes MCP serverfrom kailash_mcp import MCPServer
from dataflow import DataFlow
server = MCPServer(name="db-server")
db = DataFlow(...)
@server.resource("users://list")
def get_users():
"""Expose database via MCP resource."""
return db.query_users()from kailash_mcp import MCPServer
from kaizen.core.base_agent import BaseAgent
server = MCPServer(name="agent-server")
@server.tool()
def analyze(text: str) -> str:
"""Analyze text using an AI agent."""
agent = AnalysisAgent()
return agent(text=text).result| Transport | Use Case | Pros | Cons |
|---|---|---|---|
| stdio | Local tools, CLI | Simple, reliable | Local only |
| SSE | Web apps | Real-time updates | Complex setup |
| HTTP | APIs, services | Standard protocol | No streaming |
For MCP-specific questions, invoke:
mcp-specialist - MCP server implementationtesting-specialist - MCP testing strategiesdecide-framework skill - MCP integration architecture~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.