Skip to main content
Glama
Sign In
SpendGuard AI

SpendGuard AI

by ketankshukla
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

SpendGuard AI

A production-shaped MCP portfolio application. SpendGuard AI helps a FinOps team investigate cloud-spend anomalies, draft a savings action, obtain independent approval, execute it through a safe simulated provider, survive retries and restarts, and produce an authoritative receipt plus operational evidence.

The default provider is simulated and deterministic. This public portfolio never spends money, mutates a real cloud account, exposes customer data, or requires a real cloud credential.

Live

Related MCP server: cloudlens

Monorepo Layout

apps/web           Next.js App Router product (marketing + product UI, MCP transport, AI host)
services/risk-engine  Independently deployable Python MCP server (proposal scoring, simulation)
packages/           domain, contracts, db, auth, policy, mcp-server, mcp-host, registry, config, ...
docs/               implementation-plan.md, worklog.md, ADRs, runbooks

Local Development

pnpm install
pnpm turbo lint typecheck test build
pnpm --filter web dev

Requires Node.js >= 20, pnpm (via Corepack or npm install -g pnpm), and — for the Python risk service — Python 3.14 and uv.

Status

See docs/implementation-plan.md for phase-by-phase status and docs/worklog.md for a running log of decisions, commands, and results.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessSyncing

Resources

Related MCP Connectors

Related MCP Servers

  • AWS FinOps MCP Server

    ravikiranvm
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables natural language analysis of AWS costs, automated FinOps waste audits, and budget monitoring across multiple profiles and regions while keeping credentials secure locally.
    29 PyPI
    184
    MIT

  • cloudlens

    Rishabhusesit
    A
    license
    A
    quality
    D
    maintenance
    Enables analyzing AWS cloud costs from billing data, identifying waste, and providing mergeable fixes, with findings reconciled to actual invoices and priced at your negotiated rates.
    6
    27 PyPI
    MIT

  • govmcp

    sarathalapad
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to operate a simulated IT operations environment through policy-enforced, risk-tiered tool calls with human approval for risky writes, dry-run previews, rate limits, emergency lockdown, and tamper-evident auditing.
    MIT

  • dry-run

    HMAKT99
    A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI agents to rehearse risky actions — SQL, shell, git, Terraform, cloud and SaaS operations — against simulations of the real system before executing them, so they can see the consequences first. Returns a consequence report with a safe, confirm or block verdict, blast radius, reversibility and evidence, without ever executing the action itself.
    Apache 2.0