Synlake MCP Server

![npm](https://www.npmjs.com/package/@synlake-ai/mcp-server) ![MCP Registry](https://registry.modelcontextprotocol.io) ![License: MIT](LICENSE)

The MCP connector for Synlake — B2AI infrastructure for autonomous agents. Synlake normalizes AWS, GCP, and Azure into one schema, generates ready-to-run execution kits (Terraform HCL + CLI), and prices them before deploy — so an AI agent can discover, evaluate, and provision cloud infrastructure with zero human intervention.

This repository is the open-source MCP server (a thin stdio ↔ HTTP proxy). The infrastructure intelligence — cross-cloud normalization, the cost engine, and execution-kit generation — runs as a hosted service at api.synlake.ai.

🌐 synlake.ai · 📖 Docs · 🔌 MCP: ai.synlake/synlake

---

An agent deploys infrastructure — no human in the loop

A coding agent needs a Kubernetes node pool. It doesn't open a cloud console, compare pricing pages, or hand-write Terraform. It asks Synlake, and gets back a deployable answer:

Agent → Synlake:  "compute, 4 vCPUs, 16 GB RAM, us-east-1, budget $100/mo"

Synlake → Agent:  best:  gcp · e2-standard-4 · $97.82/mo   (19.5% cheaper than the priciest)
                  also:  aws t3.xlarge $121.47 · azure Standard_B4ms $121.18
                  kit:   { terraform: "resource \"google_compute_instance\"…",
                           cli: "gcloud compute instances create…" }
                  ✓ validated: no public ingress, encryption on, within budget

The agent reviews the kit, applies the Terraform, and moves on. Every response is dense, deterministic JSON — built for machine consumption, not dashboards. Synlake tools are read-only: they recommend, price, and validate. A human (or the agent's own policy) runs the execution kit.

Architecture

flowchart LR
    A[AI Agent] -- MCP / REST --> B[Synlake API]
    B --> C[Normalizer]
    C --> D1[AWS adapter]
    C --> D2[Azure adapter]
    C --> D3[GCP adapter]
    C --> E[Ranking engine<br/>cost + constraints]
    E --> F[Execution-kit generator<br/>Terraform + CLI]
    F --> G[Guardrails & validation<br/>budget · region · security]
    G --> H[Audit log]
    H --> A

An agent sends an intent. Synlake normalizes options across clouds, ranks them by cost and constraints, generates a deploy-ready execution kit, runs guardrail checks, logs the call, and returns one machine-ready payload. This repo ships the open-source MCP connector (the AI Agent ↔ Synlake API edge); the boxes to the right of Synlake API run as the hosted service.

Quickstart

Hosted (recommended) — MCP over Streamable HTTP

Point any MCP client at the hosted server — three lines, nothing to install:

{
  "mcpServers": {
    "synlake": {
      "url": "https://api.synlake.ai/api/mcp",
      "headers": { "Authorization": "Bearer sk_synlake_YOUR_KEY" }
    }
  }
}

Local stdio wrapper (this package)

For clients that speak stdio (e.g. Claude Desktop), run the npm wrapper — it proxies to the same hosted server:

{
  "mcpServers": {
    "synlake": {
      "command": "npx",
      "args": ["-y", "@synlake-ai/mcp-server"],
      "env": { "SYNLAKE_API_KEY": "sk_synlake_YOUR_KEY" }
    }
  }
}

Get a free API key at synlake.ai (100 calls/month, no card required). The estimate endpoint is even callable without a key — zero friction to try.

Tools

| Tool | REST endpoint | Description | |------|---------------|-------------| | synlake_query | POST /v1/infrastructure/query | Full recommendation + execution kit (Terraform + CLI) | | synlake_estimate | POST /v1/infrastructure/estimate | Cross-cloud cost comparison — no API key required | | synlake_validate | POST /v1/execution/validate | Dry-run an execution kit (security + budget checks) | | synlake_providers | GET /v1/providers | List supported providers and services | | synlake_usage | GET /v1/agent/usage | Your usage, costs, and spending cap |

Full reference (OpenAPI 3.1, rendered): synlake.ai/docs. Local copy: docs/openapi.yaml. Machine-readable summary for agents: synlake.ai/llms.txt.

Why Synlake

| Approach | Multi-cloud | Agent-ready JSON | Execution kit | Cost guardrails | Audit trail | | ------------------- | ----------- | ---------------- | ------------- | --------------- | ----------- | | DIY Terraform | Manual | No | You write it | No | No | | Pulumi / Crossplane | Yes | No | Partial | No | Partial | | Cloud provider SDKs | Single | Partial | No | No | Partial | | Agent frameworks | Via tools | Partial | No | No | No | | Synlake | 3 clouds| 100% | Full kit | Built-in | Every call |

Use it from a Claude Managed Agent

Wire Synlake as an mcp_toolset — the agent gets all five tools natively, your key stays in an Anthropic vault:

{
  "type": "mcp_toolset",
  "name": "synlake",
  "server": {
    "url": "https://api.synlake.ai/api/mcp",
    "authorization_token": { "vault_secret": "synlake_api_key" }
  }
}

See the MCP quickstart for the Managed Agents API, ant CLI, and Agent SDK flows.

Build from source

npm install
npm run build       # tsc → dist/ (pure proxy)
SYNLAKE_API_KEY=sk_synlake_... node dist/bin.js

SYNLAKE_API_URL overrides the remote endpoint (default https://api.synlake.ai/api/mcp).

Pricing

Pay per call. No subscriptions, no commitments. Free tier: 100 calls/month, no card required.

| Call type | Price | |-----------|-------| | Estimate | $0.01 _(free, no key, IP rate-limited)_ | | Query (basic) | $0.05 | | Query (full + Terraform) | $0.10 | | Validate | $0.05 |

License

The MCP connector in this repository is MIT licensed (see LICENSE). The Synlake service (api.synlake.ai) — the cost engine, cross-cloud normalization, and execution-kit generation — is proprietary.

El conector MCP de este repo es MIT. El servicio Synlake (api.synlake.ai) es propietario.

Synlake — Cloud Infrastructure for AI Agents