AWS Savings PlansMCP Configuration & Schema Registry
The AWS Savings Plans Model Context Protocol (MCP) configuration provides a validated, machine-readable JSON schema and executable bridge that connects state-of-the-art AI coding assistants — including Claude Desktop, Cursor IDE, Windsurf, Cline, and VS Code Copilot — directly to the AWS Savings Plans REST API. By leveraging the standardized open Model Context Protocol, AI agents can dynamically discover capabilities, validate input parameters against strict JSON Schemas, and execute live API operations without context switching or manual copy-pasting.
Quick Specs & Integration Summary
Technical Architecture & Protocol Semantics
Under the Model Context Protocol specification, the AWS Savings Plans configuration functions as an isolated protocol adapter. When an AI agent initializes a session, the client establishes a bidirectional JSON-RPC 2.0 communication channel over standard input/output (stdio) or Server-Sent Events (SSE). During the initial handshake, the server publishes its tool manifest extracted from the AWS Savings Plans OpenAPI specification (version 2019-06-28).
The AWS Savings Plans API, provided by Amazon Web Services, is a programmatic interface designed to manage and optimize cloud expenditure through a flexible pricing model. At its core, this API enables organizations to analyze, purchase, and administer Savings Plans—commitments to consistent compute usage (measured in USD per hour) over a one or three-year term—in exchange for substantial discounts compared to standard On-Demand pricing. The API extends the native capabilities of the AWS Management Console, allowing for automation and integration into broader cloud financial management (FinOps) and infrastructure-as-code (IaC) pipelines. Its primary value proposition lies in enabling precise cost optimization for variable workloads, particularly for services like Amazon EC2, AWS Fargate, and AWS Lambda, where usage can be forecasted but may fluctuate. Typical enterprise use cases include automated procurement workflows where a CI/CD pipeline identifies a projected new workload and automatically provisions a matching Savings Plan, and periodic auditing processes that analyze current utilization against purchased commitments to recommend adjustments or identify waste. When this API is exposed as a toolset to an AI coding assistant via the Model Context Protocol (MCP), it transforms the assistant from a static code generator into a dynamic, cloud-aware operational partner. The MCP integration allows the AI to directly interact with the live Savings Plans environment, bridging the gap between development, cost analysis, and optimization. This provides immense value by enabling the assistant to perform real-time cost modeling, validate infrastructure changes against existing commitments, and proactively manage financial resources. For instance, a developer can ask the assistant to analyze the cost impact of deploying a new microservice cluster, and the AI can use the DescribeSavingsPlansOfferings and DescribeSavingsPlanRates endpoints to model various commitment scenarios and recommend the optimal plan. This turns abstract cost-saving advice into actionable, data-driven decisions embedded directly into the development workflow. Practical workflows enabled by this MCP server are numerous and powerful. A developer can instruct the AI agent to perform tasks such as: "Analyze our current EC2 usage over the last month and identify Savings Plans offerings that could provide immediate savings by matching our consistent baseline," which would utilize the DescribeSavingsPlansOfferings endpoint. Another command like "Create a Savings Plan for $200/hr of general purpose compute and tag it with the 'production-team' project code for internal chargeback" would leverage the CreateSavingsPlan and TagResource endpoints. Furthermore, the agent can be tasked with continuous monitoring: "Set up a workflow that queries our Savings Plan utilization daily and alerts us if any commitment is underutilized for more than 10 consecutive days," utilizing DescribeSavingsPlans and ListTagsForResource for filtering. These interactions allow for the automation of complex FinOps tasks, the enforcement of cost governance policies, and the real-time optimization of cloud spending without manual console navigation. It is critical to note that while the API's current description lists its authentication method as "None," any real-world integration into an enterprise environment must adhere to stringent security practices. The API must be accessed through AWS Identity and Access Management (IAM) principals, and all calls should be authenticated using standard AWS Signature Version 4. Developers must follow the principle of least privilege, creating dedicated IAM roles or users with policies that grant only the specific permissions required for the intended workflow (e.g., the `savingsplans:Describe*` permissions for read-only analysis, or adding `savingsplans:CreateSavingsPlan` only for authorized automation). All sensitive operations, especially those that create financial commitments, should be protected with multi-factor authentication (MFA) and subject to approval workflows. It is also imperative to use AWS PrivateLink or VPC endpoints for API traffic to ensure data remains on the AWS private network, avoiding exposure to the public internet. Configuration should involve storing any necessary environment parameters securely and ensuring that AI assistants operating with these tools are themselves subject to robust access controls and audit logging. This architecture guarantees strict process boundary isolation: all sensitive authorization headers and secret tokens remain sandboxed inside the client runtime, never leaking into language model context windows or external logging endpoints.
Hosted Remote Configuration URL
MCP Configuration FileProvide this hosted URL in any client that supports remote MCP schema auto-loading.
https://mcpbridge.org/config/amazonaws-com-savingsplans.json2. AI Assistant Use Cases & Practical Workflows
Tailored for Cloud InfrastructureReal-world execution scenarios demonstrating how LLM agents (Claude 3.7, GPT-4o, Cursor Agent) invoke AWS Savings Plans tools to automate developer workflows.
1. CI/CD Build Failure & Telemetry Diagnostics
CI/CD RemediationInstantly diagnose failing CI/CD builds or deployment pipelines by streaming build logs, isolating failure root causes, and drafting targeted code fixes.
"Fetch recent pipeline run logs from AWS Savings Plans. Isolate the failed step, summarize the exact compiler or test failure error, and propose a pull request fix in Cursor."
2. Cloud Resource Auditing & Cost Optimization
Cloud FinOpsScan active compute clusters, storage buckets, and networking configurations to identify unattached volumes or idle oversized instances.
"Query active cloud infrastructure resources in AWS Savings Plans. Identify unattached storage volumes, idle compute instances, and summarize estimated monthly cost savings."
3. Zero-Downtime Rollout & Canary Health Verification
Deployment OpsOrchestrate progressive deployments, monitor error rate thresholds on newly deployed pods, and execute automated rollbacks if error budgets breach.
"Check the active deployment rollout status in AWS Savings Plans. Monitor canary error rate percentages for 5 minutes and report whether the deployment is safe to promote to 100% traffic."
4. Infrastructure as Code (IaC) Drift Detection
IaC GovernanceCompare live deployed resource state against Terraform or CloudFormation definitions to spot unauthorized manual changes.
"Scan live configurations via AWS Savings Plans and compare against our repository IaC definitions. Highlight any configuration drift in security groups or network routes."
End-to-End Multi-Step Agent Execution Lifecycle
When an engineer submits a task to Claude Desktop or Cursor, the LLM executes an autonomous 4-phase Model Context Protocol loop:
Schema Introspection
Handshake lists all 9 tools and builds argument validators.
Argument Synthesis
Model extracts parameters from prompt and validates types against OpenAPI rules.
Stdio Execution
Bridge invokes live API with injected local credentials and captures raw HTTP response.
Output Remediation
LLM parses JSON results, handles status codes, and presents synthesized answers.
3. Multi-Client Installation Matrix & Setup Guides
Select your AI assistant below to view exact configuration file paths, JSON installation snippets, and launch commands.
Claude Desktop
claude_desktop_config.json~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.json{
"mcpServers": {
"amazonaws-com-savingsplans": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-openapi",
"https://api.apis.guru/v2/specs/amazonaws.com/savingsplans/2019-06-28/openapi.json"
],
"env": {
"AWS_SAVINGS_PLANS_API_KEY": "your_aws_savings_plans_api_key"
}
}
}
}Cursor IDE
.cursor/mcp.jsonOpen Cursor Settings → Features → MCP Servers, or create .cursor/mcp.json in your project root.
{
"mcpServers": {
"amazonaws-com-savingsplans": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-openapi",
"https://api.apis.guru/v2/specs/amazonaws.com/savingsplans/2019-06-28/openapi.json"
],
"env": {
"AWS_SAVINGS_PLANS_API_KEY": "your_aws_savings_plans_api_key"
}
}
}
}Saves as .cursor/mcp.json in the download. Move it to your project root.
VS Code / Cline Extension
cline_mcp_settings.jsonPaste into your Cline extension MCP configuration or Roo Code host settings.
{
"mcpServers": {
"amazonaws-com-savingsplans": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-openapi",
"https://api.apis.guru/v2/specs/amazonaws.com/savingsplans/2019-06-28/openapi.json"
],
"env": {
"AWS_SAVINGS_PLANS_API_KEY": "your_aws_savings_plans_api_key"
}
}
}
}Zed Editor & Docker CLI
Zed / DockerDocker container execution command:
docker run -i --rm -e AWS_SAVINGS_PLANS_API_KEY="YOUR_SECRET_VALUE" node:20-alpine npx -y @modelcontextprotocol/server-openapi https://api.apis.guru/v2/specs/amazonaws.com/savingsplans/2019-06-28/openapi.json
Zed settings context servers JSON:
{
"context_servers": {
"amazonaws-com-savingsplans": {
"command": {
"path": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-openapi",
"https://api.apis.guru/v2/specs/amazonaws.com/savingsplans/2019-06-28/openapi.json"
],
"env": {
"AWS_SAVINGS_PLANS_API_KEY": "your_aws_savings_plans_api_key"
}
}
}
}
}Programmatic SDK Integration (TypeScript / Python)
Initialize the AWS Savings Plans MCP client directly in your backend codebase.
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
// Initialize AWS Savings Plans MCP client transport over stdio
const transport = new StdioClientTransport({
command: "npx",
args: ["-y","@modelcontextprotocol/server-openapi","https://api.apis.guru/v2/specs/amazonaws.com/savingsplans/2019-06-28/openapi.json"],
env: { AWS_SAVINGS_PLANS_API_KEY: process.env.AWS_SAVINGS_PLANS_API_KEY || "YOUR_SECRET_KEY" }
});
const client = new Client(
{ name: "amazonaws-com-savingsplans-client", version: "1.0.0" },
{ capabilities: { tools: {}, resources: {}, prompts: {} } }
);
async function connectAndRun() {
await client.connect(transport);
const tools = await client.listTools();
console.log("Connected to AWS Savings Plans MCP Server.");
console.log("Discovered 9 mapped tools:", tools);
}
connectAndRun().catch(console.error);Raw Stdio Schema Definition
schema.jsonFor standalone CLI wrappers, background daemon daemons, or custom script integrations:
{
"mcpServers": {
"amazonaws-com-savingsplans": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-openapi",
"https://api.apis.guru/v2/specs/amazonaws.com/savingsplans/2019-06-28/openapi.json"
],
"env": {
"AWS_SAVINGS_PLANS_API_KEY": "your_aws_savings_plans_api_key"
}
}
}
}4. Security, Authentication & Credential Management
Safely configure authentication tokens, isolate execution environments, and implement enterprise security best practices.
Required Environment Keys Reference
| Variable Name | Required | Type | Default | Purpose & Guidance |
|---|---|---|---|---|
| AWS_SAVINGS_PLANS_API_KEY | REQUIRED | Secret Key / Token | None (Set in env) | your_aws_savings_plans_api_key |
Zero-Downtime Token Rotation Protocol
- Generate Secondary Key: Create a new secret API token with identical scopes in your AWS Savings Plans developer portal.
- Update Client Configuration: Insert the new token inside the
envblock of your MCP client JSON config. - Validate Connection: Issue a test query in Claude or Cursor to ensure handshake and tool calls succeed.
- Revoke Stale Token: Decommission the legacy key on the vendor portal to prevent unauthorized access.
Least-Privilege & Sandboxing Rules
- Read-Only Token Scoping: Whenever your workflow only requires querying data, provision read-only credentials to prevent accidental mutations.
- Local Process Isolation: Stdio transports run in isolated local subprocesses; secret credentials are never sent across the internet to MCP Bridge servers.
- Prompt Injection Defense: AI model responses are sandboxed; verify generated destructive arguments before confirming execution in agent mode.
Enterprise Security Checklist (Mandatory Practices)
- Never commit
claude_desktop_config.jsonor.cursor/mcp.jsoncontaining raw secrets into public GitHub repositories. - Add
.cursor/mcp.jsonand.env.localto your project's.gitignorefile. - Always enforce TLS/HTTPS encryption on outbound network requests initiated by the server process.
5. Tool Parameter Schemas & Natural Language Execution
Mapped OpenAPI operations converted into discrete Model Context Protocol tools with strict JSON-RPC payload validators.
/CreateSavingsPlanCreateSavingsPlan
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "amazonaws-com-savingsplans_post_CreateSavingsPlan",
"arguments": {}
}
}"Use AWS Savings Plans to execute CreateSavingsPlan and output the formatted result."
/DeleteQueuedSavingsPlanDeleteQueuedSavingsPlan
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "amazonaws-com-savingsplans_post_DeleteQueuedSavingsPlan",
"arguments": {}
}
}"Use AWS Savings Plans to execute DeleteQueuedSavingsPlan and output the formatted result."
/DescribeSavingsPlanRatesDescribeSavingsPlanRates
{
"jsonrpc": "2.0",
"id": 3,
"method": "tools/call",
"params": {
"name": "amazonaws-com-savingsplans_post_DescribeSavingsPlanRates",
"arguments": {}
}
}"Use AWS Savings Plans to execute DescribeSavingsPlanRates and output the formatted result."
/DescribeSavingsPlansDescribeSavingsPlans
{
"jsonrpc": "2.0",
"id": 4,
"method": "tools/call",
"params": {
"name": "amazonaws-com-savingsplans_post_DescribeSavingsPlans",
"arguments": {}
}
}"Use AWS Savings Plans to execute DescribeSavingsPlans and output the formatted result."
/DescribeSavingsPlansOfferingRatesDescribeSavingsPlansOfferingRates
{
"jsonrpc": "2.0",
"id": 5,
"method": "tools/call",
"params": {
"name": "amazonaws-com-savingsplans_post_DescribeSavingsPlansOfferingRates",
"arguments": {}
}
}"Use AWS Savings Plans to execute DescribeSavingsPlansOfferingRates and output the formatted result."
/DescribeSavingsPlansOfferingsDescribeSavingsPlansOfferings
{
"jsonrpc": "2.0",
"id": 6,
"method": "tools/call",
"params": {
"name": "amazonaws-com-savingsplans_post_DescribeSavingsPlansOfferings",
"arguments": {}
}
}"Use AWS Savings Plans to execute DescribeSavingsPlansOfferings and output the formatted result."
/ListTagsForResourceListTagsForResource
{
"jsonrpc": "2.0",
"id": 7,
"method": "tools/call",
"params": {
"name": "amazonaws-com-savingsplans_post_ListTagsForResource",
"arguments": {}
}
}"Use AWS Savings Plans to execute ListTagsForResource and output the formatted result."
/TagResourceTagResource
{
"jsonrpc": "2.0",
"id": 8,
"method": "tools/call",
"params": {
"name": "amazonaws-com-savingsplans_post_TagResource",
"arguments": {}
}
}"Use AWS Savings Plans to execute TagResource and output the formatted result."
6. Interactive Troubleshooting & FAQ Accordion
Diagnose and resolve common JSON-RPC protocol error codes, connection disconnects, and schema refresh issues.
A 401 Unauthorized response indicates that the upstream AWS Savings Plans API rejected the authentication credential supplied in your MCP client's environment configuration. To resolve this: (1) Verify that your secret token is defined inside the "env" block of claude_desktop_config.json or .cursor/mcp.json rather than hardcoded in the command string. (2) Check whether AWS Savings Plans requires a prefix such as "Bearer <token>" in the authorization header. (3) Confirm that your API key has not expired and has been granted sufficient least-privilege scopes on the AWS Savings Plans developer dashboard.
If your MCP client fails to initialize tools for AWS Savings Plans: (1) Test the bridge launcher command ("npx -y @modelcontextprotocol/server-openapi https://api.apis.guru/v2/specs/amazonaws.com/savingsplans/2019-06-28/openapi.json") directly inside your terminal or shell to inspect stdout/stderr diagnostic traces. (2) Verify network connectivity to the schema source (https://api.apis.guru/v2/specs/amazonaws.com/savingsplans/2019-06-28/openapi.json). (3) Ensure Node.js (v18+) is installed and accessible in your system PATH. (4) For authenticated APIs, confirm credentials are configured in your client's "env" mapping rather than command arguments.
MCP clients like Claude Desktop and Cursor query the server's tools list ("tools/list") during startup and cache the resulting JSON Schema for the duration of the application session. If new endpoints or parameters are added to AWS Savings Plans: (1) Fully quit and restart Claude Desktop (Cmd+Q on macOS or File > Exit on Windows). (2) In Cursor IDE, navigate to Settings > Features > MCP Servers, toggle the AWS Savings Plans server off and on, or click the refresh icon to re-execute the initialization handshake.
If the AI model hallucinates parameters or fails to invoke a tool automatically: (1) Add explicit system instructions in your project's .cursorrules or Claude project prompt (e.g., "When querying Cloud Infrastructure, always invoke the amazonaws-com-savingsplans MCP server tools first"). (2) Ensure parameter types match schema specifications (e.g., passing integers as numbers rather than strings). (3) Check that required parameters marked in Section 5 are not omitted from the model's generated payload.
When the AWS Savings Plans upstream endpoint returns an HTTP 429 Too Many Requests response, the MCP server bubbles the structured error payload back to the AI client over stdio. Modern LLMs like Claude 3.7 and Cursor Agent recognize rate-limiting status codes, inspect the "Retry-After" header if present, and will automatically introduce backoff delays or ask the user before retrying the operation.
The Hosted Config URL (https://mcpbridge.org/config/amazonaws-com-savingsplans.json) provides a static, remote JSON schema definition that cloud-native MCP clients can fetch over HTTPS for dynamic discovery. In contrast, local stdio configurations execute a local subprocess on your workstation. Local stdio processes offer maximum security because secret API keys remain strictly on your local machine and never transit third-party proxy servers.
Similar Cloud Infrastructure Configurations
Explore related API bridges with ready-to-use Model Context Protocol schemas.
Supabase API
Cloud InfrastructureManage Supabase projects, databases, authentication, and storage through your AI agent.
https://mcpbridge.org/config/supabase.jsonCloudflare API
Cloud InfrastructureManage Cloudflare DNS, CDN, Workers, and security settings through your AI agent.
https://mcpbridge.org/config/cloudflare.jsonVercel API
Cloud InfrastructureDeploy projects, manage domains, and monitor deployments through your AI agent.
https://mcpbridge.org/config/vercel.jsonDigitalOcean API
Cloud InfrastructureThe DigitalOcean API is a comprehensive, RESTful interface provided by DigitalOcean, a leading cloud infrastructure provider focused on simplifying cloud computing for developers, startups, and enterprises. It serves as the programmatic backbone for managing the entire DigitalOcean ecosystem, enabling users to provision, configure, and control cloud resources such as Droplets (virtual private servers), Kubernetes clusters, managed databases, networks, storage volumes, and application platforms. Core capabilities include full lifecycle management of these resources, from creation and scaling to monitoring and deletion, mirroring the functionality available in the DigitalOcean control panel. Its primary use cases range from automating infrastructure setup for CI/CD pipelines and enabling infrastructure-as-code practices to supporting dynamic application scaling and resource optimization for SaaS products, e-commerce sites, and development environments. The API is designed for both developers seeking to automate their cloud operations and businesses that require programmable, scalable cloud infrastructure without the complexity of larger hyperscale providers. When exposed as tools via the Model Context Protocol (MCP) to an AI coding assistant, the DigitalOcean API transforms from a traditional developer tool into a dynamic, context-aware resource for intelligent infrastructure automation. The MCP server acts as a bridge, allowing the AI model to understand and execute API calls based on natural language instructions and the current project context. This integration provides immense value by enabling the AI to perform real-time cloud management tasks directly within the development workflow. For instance, the AI can instantly query account details to verify resources, list and manage SSH keys for secure access, or retrieve and monitor the status of infrastructure actions. This contextual access means the AI can make informed suggestions or take automated actions—like recommending a cost-optimized Droplet size based on current usage patterns or verifying that a new SSH key has been correctly added before proceeding with a deployment script—thereby reducing context-switching and accelerating development cycles. Practical workflow examples demonstrate the power of this MCP integration. A developer could instruct the AI agent with commands like, "Query our account for all active SSH keys and ensure the one named 'ci-bot' is present; if not, create it using this public key," automating a common security and setup step. Another example involves asking the AI to "Check the status of our last ten infrastructure actions to see if any are stuck in a 'pending' state," which would leverage the actions endpoints to provide an immediate operational health check. More complex automations are possible, such as "Based on the current Droplet inventory from the API, generate a Terraform configuration file that replicates this setup," or "Scan our Kubernetes 1-Click apps and suggest one for deploying a new microservice based on the project requirements." These interactions turn the AI into a proactive DevOps partner capable of auditing, reporting, and modifying cloud infrastructure through simple, conversational directives. Critical to the secure operation of this MCP server is rigorous attention to authentication and access control, despite any initial configuration notes indicating "None" for simplicity. In any real-world deployment, authentication via a DigitalOcean Personal Access Token is non-negotiable. This token should be treated as a high-privilege secret. Developers must adhere to the principle of least privilege by creating tokens with the minimum scopes required for the specific tasks—such as read-only access for monitoring or write access only for specific resource types. Best practices include storing tokens in secure environment variables or a secrets manager, never hardcoding them, and ensuring the MCP server configuration does not expose them in logs or client-side code. Furthermore, regular token rotation and monitoring of API activity through DigitalOcean's audit logs are essential to maintain a secure posture when integrating cloud management capabilities directly into AI-assisted development environments.
https://mcpbridge.org/config/digitalocean-com.json