AWS Infrastructure MCP Server — 21 AI Tools

AWS Infrastructure MCP ServerAWS Infrastructure MCP server with 21 ready-to-use AI tools. Connect AWS Infrastructure to Claude, ChatGPT, Gemini, or any MCP-compatible AI assistant. Cloud MCP connector — no install, no Docker, works from any browser.Category: Developer Tools. 21 tools available. Authentication: API Key.Monitor and manage your AWS infrastructure through conversationWhy AWS Infrastructure + AI?The AWS Console is powerful but slow for quick checks. Switching between EC2, S3, CloudWatch, and Lambda consoles wastes time when you just need to check instance status, read a log, or verify an alarm. Ask your AI instead.Example prompts you can send your AI about AWS Infrastructure

Ask: "Show me all running production instances and their CPU usage"
AI does: AI lists EC2 instances filtered by tag:Environment=production, then queries CloudWatch CPUUtilization metric for each, presenting a summary table.

Ask: "Search Lambda logs for errors in the last 30 minutes"
AI does: AI finds the Lambda log group, searches with filter pattern "ERROR", and returns matching log events with timestamps and messages.

Ask: "What CloudWatch alarms are currently firing?"
AI does: AI queries alarms with state=ALARM and returns alarm names, metrics, thresholds, and when they triggered.

Ask: "Read the deployment config from s3://my-bucket/configs/deploy.json"
AI does: AI retrieves the S3 object content and displays the JSON configuration file.

Featured AWS Infrastructure Tools

list-ec2-instances: List EC2 instances in the configured region. Returns instance ID, name, state, type, IPs, VPC, and tags. Supports filtering by state, instance type, VPC, tags, and more. FILTER EXAMPLES: By state: filters=[{"name":"instance-state-name","values":["running"]}]. By tag: filters=[{"name":"tag:Environment","values":["production"]}]. By type: filters=[{"name":"instance-type","values":["t3.micro","t3.small"]}]. By VPC: filters=[{"name":"vpc-id","values":["vpc-abc123"]}]. By specific IDs: instance_ids=["i-abc123","i-def456"]. STEP-BY-STEP for troubleshooting: 1) list-ec2-instances → find instance. 2) get-metric-statistics with namespace="AWS/EC2" → check CPU/network. 3) search-logs → check application logs. WHEN TO USE: User asks "show my EC2 instances", "what servers are running?", "list instances in production", "find instance i-abc123".

get-metric-statistics: Get CloudWatch metric data points for a specific time range. Returns timestamp + statistic values. CRITICAL: You must specify namespace, metric_name, start_time, end_time, period, and at least one statistic. COMMON METRICS: EC2 CPUUtilization (namespace="AWS/EC2", dimensions=[{"name":"InstanceId","value":"i-xxx"}]). Lambda Errors (namespace="AWS/Lambda", dimensions=[{"name":"FunctionName","value":"my-func"}]). PERIOD: In seconds. 60=1min, 300=5min, 3600=1hr. Minimum 60s for recent data. STATISTICS: "Average", "Sum", "Minimum", "Maximum", "SampleCount". EXAMPLE: CPU usage last hour: namespace="AWS/EC2", metric_name="CPUUtilization", start_time="2024-01-15T10:00:00Z", end_time="2024-01-15T11:00:00Z", period=300, statistics=["Average"]. WHEN TO USE: User asks "what is the CPU usage?", "show me Lambda errors", "how much network traffic?", "check memory usage".

search-logs: Search CloudWatch log events using filter patterns. Returns matching log messages with timestamps. FILTER PATTERNS: "ERROR" (case-sensitive exact match). "ERROR TIMEOUT" (both words present). "?ERROR ?WARN" (either ERROR or WARN). '{ $.statusCode = 500 }' (JSON field match). "" (empty = return all events). CRITICAL: log_group_name is required. Use list-log-groups to find it first. TIME RANGE: Use start_time and end_time in ISO 8601 format. Default: last hour. STEP-BY-STEP for debugging: 1) list-log-groups → find log group. 2) search-logs with filter_pattern="ERROR" → find errors. WHEN TO USE: User asks "search logs for errors", "show me Lambda errors", "find 500 errors in the API logs", "what happened at 3am?".

list-alarms: List CloudWatch alarms. Returns alarm name, state (OK/ALARM/INSUFFICIENT_DATA), metric being monitored, threshold, and actions. FILTER BY STATE: state_value="ALARM" (only firing alarms), "OK" (healthy), "INSUFFICIENT_DATA" (no data). WHEN TO USE: User asks "show me alarms", "are there any active alarms?", "what alerts are firing?", "list CloudWatch alarms". STEP-BY-STEP for incident investigation: 1) list-alarms with state_value="ALARM" → see what is alerting. 2) get-metric-statistics → check the metric. 3) search-logs → look for related errors.

list-s3-buckets: List all S3 buckets in the AWS account. Returns bucket name and creation date. NOTE: S3 buckets are global — this returns ALL buckets regardless of region. STEP-BY-STEP to explore S3: 1) list-s3-buckets → find bucket name. 2) list-s3-objects with bucket → browse contents. 3) get-s3-object → read a file. WHEN TO USE: User asks "show my S3 buckets", "list storage buckets", "what buckets exist?".

list-lambda-functions: List Lambda functions in the configured region. Returns function name, runtime, memory, timeout, state, and last modified date. WHEN TO USE: User asks "show my Lambda functions", "list serverless functions", "what functions exist?". STEP-BY-STEP for Lambda troubleshooting: 1) list-lambda-functions → find function. 2) get-lambda-function → get config details. 3) search-logs with log_group_name="/aws/lambda/{function-name}" → check logs. 4) get-metric-statistics with namespace="AWS/Lambda" → check invocations/errors/duration.

Frequently Asked Questions about AWS InfrastructureHow do I connect AWS Infrastructure to Claude or ChatGPT?Create a free LearnToSpeak.ai account, add your AWS Infrastructure credentials in the dashboard, and paste the generated OAuth URL into Claude.ai's custom connectors or ChatGPT's developer apps. The integration runs fully in the cloud — no desktop app, no CLI, no local install.Does it cost anything to connect AWS Infrastructure?The AWS Infrastructure integration is free during the LearnToSpeak.ai public beta. You only need a paid plan from Anthropic or OpenAI (Claude Pro/Max/Team or ChatGPT Plus/Pro/Team) since custom connectors require it on the AI provider side.Which AI assistants support the AWS Infrastructure connector?Claude.ai (Pro, Max, Team, Enterprise) and ChatGPT (Plus, Pro, Team) both support the AWS Infrastructure integration via the MCP (Model Context Protocol) standard. The same credentials work across both platforms — add the connector once, use it everywhere.How many AWS Infrastructure tools does my AI get access to?Your AI gets 21 ready-to-use tools for AWS Infrastructure, covering the most common read and write operations. Each tool is a discrete action the AI can call on demand — no multi-step prompting, no screen scraping, no workarounds.Is it safe to give an AI access to my AWS Infrastructure account?Yes. Your AWS Infrastructure credentials are encrypted at rest with AES-256-GCM and only decrypted in memory when the AI makes a request. LearnToSpeak.ai uses OAuth 2.1 with mandatory PKCE for the AI-to-platform connection, and you can revoke access instantly from the dashboard. We never store or log the actual tool responses returned to the AI.Why use LearnToSpeak.ai instead of running an MCP server locally?Cloud MCP servers work from any browser on any device — no Node.js install, no Docker, no local ports, no maintenance. Configure AWS Infrastructure once in the dashboard and your AI connects from claude.ai or chat.openai.com directly. That's the entire value proposition: web AI assistants don't read your filesystem, they read our servers.What is the AWS Infrastructure MCP server?The AWS Infrastructure MCP server is a cloud-hosted integration that gives AI assistants direct access to AWS Infrastructure through 21 tools via the Model Context Protocol (MCP) standard. It works with Claude, ChatGPT, Gemini, and any MCP-compatible AI — no local installation or Docker required.How do I connect AWS Infrastructure to Claude via MCP?Sign up at LearnToSpeak.ai, add your AWS Infrastructure credentials, and copy the generated MCP URL into Claude.ai's custom connectors (Settings → Developer → Custom Connectors). The cloud MCP server handles the connection — no CLI, no local server, no Docker.How do I connect AWS Infrastructure to ChatGPT via MCP?Sign up at LearnToSpeak.ai, add your AWS Infrastructure credentials, and copy the generated MCP URL into ChatGPT's developer apps (Settings → Apps → Advanced → Developer mode). Works with any ChatGPT Plus, Pro, or Team account.What can AI do with AWS Infrastructure through MCP?AWS Infrastructure offers 21 MCP tools covering Manage EC2 instances, S3 storage, CloudWatch monitoring, and Lambda functions in AWS. Ask your AI to perform any of these actions in natural language — it calls the right tool automatically.What is MCP (Model Context Protocol)?MCP is an open standard that lets AI assistants like Claude, ChatGPT, and Gemini connect directly to external apps and services. LearnToSpeak.ai hosts cloud MCP servers so you don't need to install anything locally — your AI connects from any browser.Related MCP Servers

GitHub MCP Server — 44 tools

GitLab MCP Server — 90 tools

NetBox MCP Server — 179 tools

Cisco CPNR MCP Server — 36 tools

Grafana MCP Server — 50 tools

Browse all 34 MCP servers