Skip to content
MCP server

Moretes Architect MCP

48 deterministic architecture tools and 10 architect personas for your coding agent

Install
Pricing
Open source
Platforms
CLI, API, Web
Runs
Locally or Remotely
Version
0.5.0
Listing updated
3 days ago

About Moretes Architect MCP

Moretes Architect MCP is an open-source MCP server for cloud and infrastructure. It can run locally on your machine or as a hosted remote server.

This workbench does the calculating and structuring while your client's own model does the reasoning. The server never calls a model, never receives credentials and needs no API key. Each tool takes strict input, returns structured output with provenance and stated limitations, and the reviews are heuristic triage for a person to decide on, not certification.

The tools run from requirements checks and reference architectures through ADRs, STRIDE threat prompts, capacity, latency and SLO budgets, cost models and migration plans. Review tools scan pasted source code and dependency manifests for hazards such as hardcoded endpoints, disabled TLS or unpinned versions, and the site also mentions Terraform, Kubernetes and AI-agent security reviews. architect_panel convenes personas such as solution, security, data and FinOps, each returning questions, checks and tools to call.

A public server needs no signup and allows 300 requests per day per client, 3,000 in total, so run it locally for volume or private inputs. The same engine also runs offline as a CLI that outputs Markdown, JSON or SARIF. The author is Fernando Azevedo, and a free video course accompanies it.

Install

Run in a terminal

claude mcp add --transport http moretes-aws-architect-mcp https://mcp.moretes.com/mcp

Add to Settings → Connectors → Add custom connector

https://mcp.moretes.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "moretes-aws-architect-mcp": {
      "url": "https://mcp.moretes.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "moretes-aws-architect-mcp": {
      "type": "http",
      "url": "https://mcp.moretes.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "moretes-aws-architect-mcp": {
      "serverUrl": "https://mcp.moretes.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "moretes-aws-architect-mcp": {
      "type": "http",
      "url": "https://mcp.moretes.com/mcp"
    }
  }
}

Tools this server provides (12)

Taken from the project documentation; the running server may differ.

architect_panel
Convenes architect personas on a subject, each returning questions, checks, deliverables and tools to call.
code_review_architecture
Heuristic architecture and security scan of pasted source code.
dependency_manifest_review
Reviews dependency manifests for unpinned ranges, git sources and missing lockfile hints.
requirements_check
Turns a workload brief into explicit requirements, gaps and research questions.
architecture_pattern
Selects a reference architecture for a workload pattern with tradeoffs and Mermaid.
service_compare
Compares curated AWS service families against user constraints.
decision_record
Generates an ADR from alternatives, decision and consequences.
well_architected_review
Organizes evidence by six pillars.
threat_model
Creates STRIDE review prompts for supplied assets and trust boundaries.
failure_rehearsal
Designs a controlled failure drill with success criteria and stop conditions.
capacity_plan
Calculates concurrency and daily data volume from traffic assumptions.
latency_budget
Sums serial steps and the largest parallel step to show where time goes.

What it does

Persona panel
Ten architect personas return questions, checks and deliverables for a subject.
No model calls
The server never calls an LLM or receives credentials.
Decision records
Generate an ADR from explicit alternatives, decision and consequences.
Budgets and plans
Compute capacity, latency, SLO and cost figures from stated assumptions.
Code and manifest review
Scan pasted code and dependency files for common hazards.
CLI and SARIF output
The same engine runs offline in pipelines with exit codes by severity.

Good for

  • Turn a vague API request into explicit requirements and gaps
  • Compare AWS service families against constraints
  • Record an architecture decision as an ADR
  • Sum a latency budget across serial and parallel steps
  • Gate a risky Terraform apply in a pipeline

Pricing

Open source

Open source; public server free within daily quota

Prices change. Check fernando.moretes.com before you buy.

Moretes Architect MCP FAQ

Does it need an API key?

No. There is no key and no signup for the public server.

What are the usage limits?

The public server allows 300 requests per day per client and 3,000 in total, with a 429 beyond that.

Does the server call an AI model?

No. It returns calculations, structures and official sources, and your client's model does the reasoning.

Can I run it locally?

Yes, over stdio with the npm package, which the README recommends for volume or private inputs.

Is Moretes Architect MCP free?

Yes. Moretes Architect MCP is open source, so you can use and self-host it for free.

How do I add Moretes Architect MCP to Claude Code?

Run this command in your terminal: claude mcp add --transport http moretes-aws-architect-mcp https://mcp.moretes.com/mcp

What are the best alternatives to Moretes Architect MCP?

The closest alternatives to Moretes Architect MCP are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Moretes Architect MCP

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools