DevTools Docs - SDKs (Python + Node.js)

DevTools Documentation

SDKs (Python + Node.js)

Cloud logging, MCP integrations, frontend tooling, and SSH workflows for production DevTools teams.

Account Settings Resources MCP Servers

SDK Repo

MCP Access

Cloud Logger

Frontend Tools

SSH Ready

SDK Reference (Python + Node.js + curl)

Production Ready

Use the SDK for structured cloud logging and MCP tool-spec generation. Both SDKs support ALERT, and both can disable cloud forwarding explicitly with NONE. Use curl when you want direct HTTP control. For both SDK and curl, copy the Resource Details Resource URL into ALSHIVAL_RESOURCE (owned or shared).

pip install git+https://github.com/Alshival-Ai/alshival.git@main

npm install @alshival.ai/alshival

Configuration

ALSHIVAL_USERNAME=your_username
ALSHIVAL_API_KEY=your_api_key
ALSHIVAL_RESOURCE=https://alshival.dev/u/resource_owner_username/resources/resource_uuid/
ALSHIVAL_CLOUD_LEVEL=INFO
ALSHIVAL_DEBUG=false

import alshival

alshival.configure(
    username='your_username',
    api_key='your_api_key',
    resource='https://alshival.dev/u/resource_owner_username/resources/resource_uuid/',
    cloud_level='ALERT',
    debug=False,
)

# Disable cloud forwarding explicitly:
# alshival.configure(cloud_level='NONE')

const alshival = require('@alshival.ai/alshival');

alshival.configure({
  username: 'your_username',
  apiKey: 'your_api_key',
  resource: 'https://alshival.dev/u/resource_owner_username/resources/resource_uuid/',
  cloudLevel: 'ALERT',
  debug: false,
});

// Disable cloud forwarding explicitly:
// alshival.configure({ cloudLevel: 'NONE' });

Cloud forwarding threshold values: DEBUG, INFO, WARNING, ERROR, ALERT, NONE. Disable forwarding with NONE.

Log Shipping (Python / Node.js / curl)

import logging
import alshival

logging.basicConfig(level=logging.INFO)
alshival.configure(cloud_level='WARNING')

alshival.log.info('local only')
alshival.log.warning('local + cloud', extra={'service': 'api'})
alshival.log.alert('on-call alert', extra={'severity': 'high'})

const alshival = require('@alshival.ai/alshival');

alshival.configure({ cloudLevel: 'WARNING' });

alshival.log.info('local only');
alshival.log.warning('local + cloud', { extra: { service: 'api' } });
alshival.log.alert('on-call alert', { extra: { severity: 'high' } });

curl -X POST \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $ALSHIVAL_API_KEY" \
  -d '{
    "logs": [
      {
        "level": "alert",
        "message": "database latency threshold exceeded",
        "ts": "2026-02-20T00:00:00+00:00",
        "extra": {"service": "postgres", "p95_ms": 822}
      }
    ]
  }' \
  "${ALSHIVAL_RESOURCE%/}/logs/"

MCP Tool Specs From SDK

Both SDKs expose helper builders that return OpenAI Responses-compatible MCP tool objects.

import alshival
from openai import OpenAI

client = OpenAI()

tools = [
    alshival.mcp,
    alshival.mcp.github,
]

response = client.responses.create(
    model='gpt-5.2',
    input='Summarize the latest issues in my repo.',
    tools=tools,
)

const OpenAI = require('openai');
const alshival = require('@alshival.ai/alshival');

const client = new OpenAI();

const tools = [
  alshival.mcp,
  alshival.mcp.github,
];

const response = await client.responses.create({
  model: 'gpt-5.2',
  input: 'Summarize the latest issues in my repo.',
  tools,
});

curl -sS https://mcp.alshival.ai/mcp/ \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $ALSHIVAL_API_KEY" \
  -H "X-User-Username: $ALSHIVAL_USERNAME" \
  -d '{"jsonrpc":"2.0","id":"1","method":"tools/list","params":{}}'

curl -sS https://mcp.alshival.ai/github/ \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $ALSHIVAL_API_KEY" \
  -H "X-User-Username: $ALSHIVAL_USERNAME" \
  -d '{"jsonrpc":"2.0","id":"1","method":"tools/list","params":{}}'

Set ALSHIVAL_API_KEY and ALSHIVAL_USERNAME (or ALSHIVAL_EMAIL) in env first. Use github-mcp after linking your GitHub account in DevTools.