IntegrityPulse FinOps

io.github.maryadawson-codePublished by GitHub account maryadawson-codev1.1.0Updated Oct 24, 2026

Verified cloud cost forecasting for AI agents. AWS, GCP, Azure pricing matrix.

VerifiedStreamable HTTPWeb executableCloud & InfrastructureFinance

Overview

AI-generated overview

A remote MCP server that gives AI assistants verified AWS, GCP and Azure pricing forecasts so cloud cost estimates come from a fixed matrix instead of guesses.

What you can do
Forecast deployment cost: price a list of named services with usage hours against AWS, GCP or Azure and get a line-item monthly breakdown with a total. Supported services cover a small fixed set of compute instances, managed Postgres, Redis and S3 standard storage. Requests are metered per API key against a monthly operation quota.
When to use it
Useful when an assistant is sizing or comparing cloud deployments and you want grounded monthly cost figures rather than model-generated estimates, for example when drafting architecture or infrastructure plans.
Requirements
A remote streamable HTTP endpoint; no local runtime or package. A required API key sent in the x-api-key header. The free tier allows 25 operations per month; higher usage requires a paid upgrade.
Before you install
The API key is a secret and should be kept out of shared configs. Usage is metered, and once the free quota is exhausted the tool returns an error result containing an upgrade prompt and billing link, so paid tiers may be offered mid-conversation. Pricing covers only a short fixed list of services, so results are not a full cloud bill.

Installation

In SourceWeft

  1. Open IntegrityPulse FinOps in the dashboard and add it to a workspace.
  2. Connect x-api-key credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.maryadawson-code%2Fintegritypulse/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "integritypulse-finops": {
      "type": "http",
      "url": "https://integritypulse.marywomack.workers.dev/mcp",
      "headers": {
        "x-api-key": "<YOUR_API_KEY>"
      }
    }
  }
}

README

IntegrityPulse FinOps

Stop your AI agents from hallucinating cloud costs. Get real pricing forecasts inside the conversation.

[MCP Server] [Cloudflare Workers] [License: MIT]

What is this?

IntegrityPulse FinOps is a remote MCP server that gives AI coding agents accurate, real-time cloud deployment cost forecasts. Instead of your agent guessing that "an EC2 instance costs around $50/month," it calls a tool backed by a verified pricing matrix and returns a line-item breakdown.

One tool. Three providers. Zero hallucinations.

User: "What would it cost to run our API on AWS with an m5.large, a managed Postgres, and Redis?"
Agent (via IntegrityPulse FinOps):  | Service                    | Category | Hours | Est. Cost |  |----------------------------|----------|-------|-----------|  | m5.large                   | Compute  | 730   | $70.08    |  | rds.postgres.db.m5.large   | Database | 730   | $204.40   |  | elasticache.redis.t3.micro | Cache    | 730   | $11.68    |
  Total Estimated Monthly Cost: $286.16

Quick Start

Claude Desktop

Add this to your claude_desktop_config.json:

json
{  "mcpServers": {    "integritypulse": {      "type": "streamable-http",      "url": "https://integritypulse.marywomack.workers.dev/mcp",      "headers": {        "x-api-key": "YOUR_API_KEY"      }    }  }}

Cursor

Add to your .cursor/mcp.json:

json
{  "mcpServers": {    "integritypulse": {      "type": "streamable-http",      "url": "https://integritypulse.marywomack.workers.dev/mcp",      "headers": {        "x-api-key": "YOUR_API_KEY"      }    }  }}

cURL

bash
curl -X POST https://integritypulse.marywomack.workers.dev/mcp \  -H "Content-Type: application/json" \  -H "Accept: application/json, text/event-stream" \  -H "x-api-key: YOUR_API_KEY" \  -d '{    "jsonrpc": "2.0",    "id": 1,    "method": "tools/call",    "params": {      "name": "forecast_deployment_cost",      "arguments": {        "provider": "AWS",        "services_to_add": [          {"service_name": "m5.large", "estimated_usage_hours": 730}        ]      }    }  }'

The Tool: forecast_deployment_cost

ParameterTypeDescription
provider"AWS" | "GCP" | "AZURE"Cloud provider to price against
services_to_addArray<{ service_name, estimated_usage_hours }>Services to include in the forecast

Supported services:

AWSGCPAzure
t3.micro, t3.medium, m5.largee2-micro, e2-medium, n2-standard-2B1s, B2s, D2s_v3
rds.postgres.db.t3.micro, rds.postgres.db.m5.largecloudsql.postgres.db-custom-1-3840, cloudsql.postgres.db-custom-4-15360postgresql.flexible.b1ms
elasticache.redis.t3.micromemorystore.redis.1gb
s3.standard.1tb

Why It Exists: FinOps for the Agentic Era

AI agents are moving from "write me code" to "deploy this for me." When an agent provisions infrastructure, cost accuracy isn't a nice-to-have -- it's a financial control.

The problem: LLMs hallucinate pricing. They confidently tell you an RDS instance costs "$15/month" when the real number is $204. When agents start executing deployments autonomously, these hallucinations become real invoices.

The solution: IntegrityPulse FinOps is a grounded pricing oracle that agents call as a tool. The pricing matrix is maintained, versioned, and deterministic. No generation, no guessing.

Agentic Commerce & the Revenue Gate

This server is also a reference implementation of Revenue-Gated MCP -- a pattern for monetizing MCP tools without breaking the agent experience.

Here's how it works:

  1. Every request carries an x-api-key header.
  2. The server checks the user's tier and monthly_usage_count in Supabase.
  3. Free tier users get 25 operations/month.
  4. When the limit is hit, the server does NOT return an HTTP error. Instead, it returns a valid MCP tool result with isError: true:
json
{  "jsonrpc": "2.0",  "id": 1,  "result": {    "content": [{      "type": "text",      "text": "IntegrityPulse FinOps Alert: Your free monthly tier (25/25 operations) has been exhausted. To generate this architectural cost forecast, please upgrade to the Pro tier here: https://billing.openclaw.com/upgrade. Once upgraded, ask me to retry."    }],    "isError": true  }}

Why isError: true instead of HTTP 402/429?

Because the consumer is an LLM, not a browser. An HTTP error gets swallowed by the MCP transport layer and the user never sees it. By returning a tool result with isError: true, the upgrade CTA lands directly in the conversation where the user is already engaged. The agent reads it, surfaces it, and the user can act on it immediately. This is commerce at the point of intent.

Stripe Integration

When a user upgrades via the billing link, Stripe fires a checkout.session.completed webhook to /api/webhook/stripe. The server automatically:

  • Updates their tier from FREE to PRO
  • Resets their usage counter to 0
  • The next agent request goes through seamlessly

Architecture

                         +-----------------+  Claude / Cursor        |  Cloudflare     |       +------------+  (MCP Client)  -------->|  Worker (Hono)  |------>|  Supabase  |                POST     |                 |       |  (users)   |                /mcp     |  Revenue Gate   |       +------------+                         |  MCP Server     |                         |  Stripe Webhook |------>  Stripe API                         +-----------------+
  • Runtime: Cloudflare Workers (edge, ~0ms cold start)
  • Framework: Hono (lightweight, Workers-native)
  • MCP SDK: @modelcontextprotocol/sdk with Streamable HTTP transport
  • Auth: API key in x-api-key or Authorization: Bearer header
  • Database: Supabase (PostgreSQL)
  • Payments: Stripe Checkout + Webhooks

Self-Hosting

bash
git clone https://github.com/maryadawson-code/integritypulse.gitcd integritypulsenpm install
# Configure secretscp .env.example .env# Edit .env with your Supabase and Stripe credentials
# Local developmentnpx wrangler dev
# Deploy to Cloudflare Workersnpx wrangler secret put SUPABASE_URLnpx wrangler secret put SUPABASE_SERVICE_KEYnpx wrangler secret put STRIPE_SECRET_KEYnpx wrangler secret put STRIPE_WEBHOOK_SECRETnpx wrangler deploy

License

MIT

Source: README.md at commit 72abbde

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.1.0LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.