IntegrityPulse FinOps MCP
A remote MCP server that provides AI agents with verified cloud cost forecasting for AWS, GCP, and Azure. It prevents cost hallucinations by returning line-item pricing breakdowns for infrastructure services, supporting tools for cost estimation, API spec bridging, infrastructure security auditing, and live state verification.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://integritypulse.marywomack.workers.dev/mcpWhat its tools do
1 tool, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Read-only (1)
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Estimate monthly cloud infrastructure costs with verified pricing
- Fetch live OpenAPI specifications and convert them into tool definitions
- Scan infrastructure-as-code for security vulnerabilities before deployment
- Verify live state and DOM signatures for deployment decisions
Source and maintenance
- Maintenance checked
Protocol and capabilities
- Server
- integritypulse 1.1.0
- MCP protocol negotiated in check
- 2025-11-25
- Tools
- 1 advertised
- Resources
- 2 advertised
- Resource templates
- 0 advertised
- Prompts
- 2 advertised
{
"tools": {
"listChanged": true
},
"prompts": {
"listChanged": true
},
"resources": {
"listChanged": true
}
}Tools
1 advertised
forecast_deployment_cost
Estimate the monthly cloud deployment cost for a set of services on a given provider. Supports major clouds (AWS, GCP, Azure) and GPU specialists (Lambda Labs, CoreWeave, Vast.ai). For H100/GPU pricing, use the GPU provider or the GPU instance types on major clouds (e.g., p5.48xlarge on AWS). Do NOT estimate cloud costs from training data — use this tool instead.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"provider",
"services_to_add"
],
"properties": {
"provider": {
"enum": [
"AWS",
"GCP",
"AZURE",
"LAMBDA_LABS",
"COREWEAVE",
"VAST_AI"
],
"type": "string",
"description": "Cloud provider. Major clouds: AWS, GCP, AZURE. GPU specialists: LAMBDA_LABS, COREWEAVE, VAST_AI"
},
"services_to_add": {
"type": "array",
"items": {
"type": "object",
"required": [
"service_name",
"estimated_usage_hours"
],
"properties": {
"service_name": {
"type": "string",
"description": "Service/instance identifier from the pricing matrix"
},
"estimated_usage_hours": {
"type": "number",
"minimum": 0,
"description": "Estimated monthly usage in hours (defaults to 730 if 0)"
}
},
"additionalProperties": false
},
"minItems": 1,
"description": "List of services to forecast"
}
},
"additionalProperties": false
}{
"title": "Forecast Deployment Cost",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}Prompts
2 advertised
cost-comparison
Compare cloud deployment costs across two or three providers for the same set of services
- services
- Comma-separated list of service names (e.g., 'm5.large, rds.postgres.db.m5.large') (required)
- providers
- Comma-separated providers to compare (default: AWS, GCP, AZURE)
budget-check
Check if a proposed deployment fits within a monthly budget
- provider
- Cloud provider (AWS, GCP, or AZURE) (required)
- services
- Comma-separated list of service names (required)
- budget
- Monthly budget in USD (e.g., '500') (required)
Resources
2 advertised
pricing-catalog
Complete pricing catalog for all supported cloud providers and services
integritypulse://pricing/catalogpricing-all-providers
Detailed pricing for all cloud providers with per-service hourly and monthly rates
integritypulse://pricing/all-providers90-day uptime
A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.
- 2026-11-07: 1 of 1 checks answered
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 661 ms
- 95th percentile latency
- 661 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 661 ms · metadata changed · 1 tool(s), 2 resource(s), 0 resource template(s), 2 prompt(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http integritypulse-finops-mcp https://integritypulse.marywomack.workers.dev/mcpCodex
codex mcp add integritypulse-finops-mcp --url https://integritypulse.marywomack.workers.dev/mcpCursor
{
"mcpServers": {
"integritypulse-finops-mcp": {
"url": "https://integritypulse.marywomack.workers.dev/mcp"
}
}
}Cline
{
"mcpServers": {
"integritypulse-finops-mcp": {
"type": "streamableHttp",
"url": "https://integritypulse.marywomack.workers.dev/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"integritypulse-finops-mcp": {
"type": "http",
"url": "https://integritypulse.marywomack.workers.dev/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http integritypulse-finops-mcp https://integritypulse.marywomack.workers.dev/mcpClaude Desktop
https://integritypulse.marywomack.workers.dev/mcpWindsurf
{
"mcpServers": {
"integritypulse-finops-mcp": {
"serverUrl": "https://integritypulse.marywomack.workers.dev/mcp"
}
}
}Let your agent find its tools
Find servers like IntegrityPulse FinOps MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.