delega.ai for AWS Pricing Calculator

Enable AI agents to create, edit, save, and load AWS Pricing Calculator estimates via MCP.

CommunityOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • Create Estimate: Create a new isolated calculator workspace and return its workspace_id. Use this before stateful calculator tools. Each workspace_id is scoped to the authenticated account.
  • Search Services: Search for AWS services by name or description. Returns matches ranked by relevance. Use this to discover the correct serviceCode(s) before calling add_services. Pass all queries in o
  • Add Services: Requires workspace_id. Add one or more services to the estimate. Returns the full list of configurable fields for each. Always call search_services first to obtain the exact `serviceCode

What data it sees

Do you need an account

No: the server works without sign-in

Enable AI agents to create, edit, save, and load AWS Pricing Calculator estimates via MCP. The toolset lets agents estimate deployment costs and generate official shareable calculator.aws URLs.

Generated estimates are saved to the delega.ai dashboard, so users can revisit and manage their work. Team plans add customer and opportunity tracking, shared notes, and AWS Co-Sell pipeline tracking.

How to connect

How to connect delega.ai for AWS Pricing Calculator to Claude

The server address to paste into Claude settings:

https://aws-pricing-calculator--delega.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect delega.ai for AWS Pricing Calculator to ChatGPT

The server address to paste into ChatGPT settings:

https://aws-pricing-calculator--delega.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect delega.ai for AWS Pricing Calculator to Cursor

The server address to paste into Cursor settings:

https://aws-pricing-calculator--delega.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (11)

Raw names from tools/list. Only developers need these.

create_estimateCreate a new isolated calculator workspace and return its workspace_id. Use this before stateful calculator tools. Each workspace_id is scoped to the authenticated account.
search_servicesSearch for AWS services by name or description. Returns matches ranked by relevance. Use this to discover the correct serviceCode(s) before calling add_services. Pass all queries in one call for multi-service estimates. When region is provided, results include a regionWarning field for services that may not be available in AWS Pricing Calculator for that region. IMPORTANT: Calculator service codes differ from AWS Pricing API codes (e.g., "ec2Enhancement" not "AmazonEC2").
add_servicesRequires workspace_id. Add one or more services to the estimate. Returns the full list of configurable fields for each. Always call search_services first to obtain the exact `serviceCode` and `components[]`. For IPM / instanceMatrix fields, inline option lists in the returned inspect view are contextual: they may be narrowed by current defaults or sibling selections. Use list_field_options with the fieldId + columnSelectorId to discover other valid values. For composite services (S3, DynamoDB, Bedrock, etc.), pass the components from search results. For template variants (Lambda, Aurora, etc.), use the compound code from search results (e.g., "aWSLambda/lambdaWithFreeTier"). The name is the display label in the saved estimate. For composite services, the name also serves as the group — adding components to an existing name appends them (does not replace). Pass all services in one call for multi-service estimates. Partial failures are reported per service.
set_service_fieldsRequires workspace_id. Set field values on one or more services in the estimate. Applies updates sequentially in array order. Each update sees the state produced by prior updates in the same call. Use this to batch normal estimate edits while still getting per-target validation, [NEW] fields, transferred values, dropped fields, and warnings. Partial success is allowed per update.
describe_servicesRe-read current fields, values, types, and hints for one or more services. Use after many turns or to verify before saving. For composites, omit component to inspect all current components under that name. For IPM / instanceMatrix fields, inline option lists are contextual and may be narrowed by current/default sibling values; call list_field_options for the column to browse alternatives. Targets are processed independently — partial success is allowed. This tool is read-only.
rename_servicesRename one or more services (and their composite groups, if applicable). Each target must include newName. Targets are processed independently — partial success is allowed.
remove_servicesRemove one or more services from the estimate. Pass component to remove just one component when the service is composite; omit it to remove the whole service. Targets are processed independently — partial success is allowed. This action is destructive.
list_field_optionsRequires workspace_id. Get valid options for a large IPM column, EC2 instance types, or a large plain dropdown. Use this when add_services or describe_services shows "use list_field_options" for a field or IPM column. Also use it for small IPM option sets when you want alternatives beyond the current/default sibling selection — inspect output is contextual and may not be exhaustive. For plain dropdowns (field.type = dropdown), omit columnSelectorId. For EC2 instance search fields, omit columnSelectorId and filters are ignored. Options are automatically scoped to the service's region. Output: a markdown list of option values, prefixed with a count header. When an unqueried result has >50 values, it switches to a grouped "browse by family" view (e.g., db.m5, r5, m7i). Family names are browse handles, not valid values to set — re-query a family name with the `query` parameter to see its members. A trailer line reports the region scope, any applied filters, and any ignored filter keys. Examples: list_field_options(name="OpenSearch Domain", fieldId="weightedComponent", columnSelectorId="Instance Type") list_field_options(name="OpenSearch Domain", fieldId="weightedComponent", columnSelectorId="Instance Type", query="r6g") list_field_options(name="Txtria 2", fieldId="columnFormIPM", columnSelectorId="Instance Type", filters={"TermType":"Reserved","Deployment Option":"Multi-AZ"}) list_field_options(name="My EC2", fieldId="instanceType", query="m5")
save_estimateRequires workspace_id. Persist all configured services to calculator.aws and return the shareable estimate URL with a validated cost summary. Cost fields: 'costs.monthly' is steady-state monthly, 'costs.upfront' is one-time charges (e.g. Reserved Instance upfront), 'costs.annual' is first-year total and INCLUDES upfront (matches the AWS Calculator summary). For steady-state ARR use costs.monthly * 12. If the response reports validation errors, fix the offending field values with set_service_fields and call save_estimate again.
load_estimateLoad an existing calculator.aws URL into a workspace. If workspace_id is omitted, a new isolated workspace is created automatically. Load an existing estimate from a calculator.aws URL into the workspace for editing. Returns a breakdown of services and cost (total and per service). Use describe_services(targets=[{name}]) to inspect individual service fields. All loaded services become editable — use set_service_fields, describe_services / rename_services / remove_services, add_services, etc. to modify them. Cost fields: 'costs.monthly' is steady-state monthly, 'costs.upfront' is one-time charges (e.g. Reserved Instance upfront), 'costs.annual' is first-year total and INCLUDES upfront (matches the AWS Calculator summary). For steady-state ARR use costs.monthly * 12. This replaces any services currently in the workspace.
search_saved_estimatesSearch this account's saved AWS cost estimates by keyword, customer, service, region, review status, funding request status, or saved date, or resolve a calculator.aws share URL back to its saved estimate. Returns matching estimates with their services, regions, costs, and status, plus links to the AWS estimate and the workspace, and a breakdown across all matches.