aiskillstore/marketplace / skills/0xdarkmatter/mcp-patterns
mcp-patterns
VerifiedModel Context Protocol (MCP) server patterns for building integrations with Claude Code. Triggers on: mcp server, model context protocol, tool handler, mcp resource, mcp tool.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.5 KB |
| references/auth-patterns.md | markdown | 1.3 KB |
| references/resource-patterns.md | markdown | 1.1 KB |
| references/state-patterns.md | markdown | 1.5 KB |
| references/testing-patterns.md | markdown | 911 B |
| references/tool-patterns.md | markdown | 2.3 KB |
| skill-report.json | config | 42.3 KB |
references/tool-patterns.md
View on GitHub# MCP Tool Patterns
Extended patterns for MCP tool implementation.
## Tool with Validation
```python
from pydantic import BaseModel, Field
class SearchInput(BaseModel):
query: str = Field(..., min_length=1, max_length=500)
limit: int = Field(default=10, ge=1, le=100)
@app.call_tool()
async def call_tool(name: str, arguments: dict):
if name == "search":
# Pydantic validates and parses
params = SearchInput(**arguments)
results = await search(params.query, params.limit)
return {"content": [{"type": "text", "text": json.dumps(results)}]}
```
## Tool with Error Handling
```python
@app.call_tool()
async def call_tool(name: str, arguments: dict):
try:
if name == "fetch_data":
data = await fetch_data(arguments["url"])
return {"content": [{"type": "text", "text": data}]}
except httpx.HTTPStatusError as e:
return {
"content": [{"type": "text", "text": f"HTTP error: {e.response.status_code}"}],
"isError": True
}
except Exception as e:
return {
"content": [{"type": "text", "text": f"Error: {str(e)}"}],
"isError": True
}
```
## Multiple Tool Registration
```python
TOOLS = {
"list_items": {
"description": "List all items",
"schema": {"type": "object", "properties": {}},
"handler": handle_list_items
},
"get_item": {
"description": "Get specific item",
"schema": {
"type": "object",
"properties": {"id": {"type": "string"}},
"required": ["id"]
},
"handler": handle_get_item
},
"create_item": {
"description": "Create new item",
"schema": {
"type": "object",
"properties": {
"name": {"type": "string"},
"data": {"type": "object"}
},
"required": ["name"]
},
"handler": handle_create_item
}
}
@app.list_tools()
async def list_tools():
return [
{"name": name, "description": t["description"], "inputSchema": t["schema"]}
for name, t in TOOLS.items()
]
@app.call_tool()
async def call_tool(name: str, arguments: dict):
if name not in TOOLS:
raise ValueError(f"Unknown tool: {name}")
return await TOOLS[name]["handler"](arguments)
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |