MCP.Market

Evolith Architecture Governance MCP server

by beyondnetcode·io.github.beyondnetcode/evolith·v1.3.3·2 stars
No reviews yet

Executable architecture governance: an unevaluated rule is reported as a failure, never a pass.

A91/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A91/100

full report

Adoption
Growing

2 stars68 downloads/wk

Reviews

Write one

Nobody has reviewed Evolith Architecture Governance yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Evolith Architecture Governance tools (56, 8 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • AGENTS.md

    AI agent configuration and rules

  • MASTER_INDEX.md

    Master documentation index

  • README.md

    Project overview and getting started

  • evolith-adr-createwrite action

    Create a new Architecture Decision Record. Writes reference/architecture/adrs/<id>.md and updates the matrix.

  • evolith-adr-get

    Get the full details of a single ADR by id (e.g. ADR-0001) or number.

  • evolith-adr-list

    List all Architecture Decision Records (id, title, status, date).

  • evolith-adr-matrix

    Get the ADR matrix summary (totals by status + recent ADRs).

  • evolith-adr-updatewrite action

    Update the status of an existing ADR (Proposed | Accepted | Deprecated | Superseded | Amended).

  • evolith-agent-install

    Install a new Evolith agent

  • evolith-agent-list

    List all installed Evolith agents

  • evolith-agent-removewrite action

    Remove an Evolith agent

  • evolith-agent-runwrite action

    Run an intent through the Agent Runtime pipeline

  • evolith-agent-upgrade

    Upgrade an existing Evolith agent

  • evolith-agent-validate

    Validate a specific agent ruleset

  • evolith-architecture-validate

    Validate repository architecture along the progressive maturity axis

  • evolith-auto-fix

    Apply automatic fixes to architectural violations reported by Evolith Core rule evaluators

  • evolith-composable-validate

    Validate using the composable engine (GT-312). Supports multiple validation modes: SDLC, Architecture, Ruleset, ADR, Ad-hoc. Can combine modes.

  • evolith-config-get

    Get Evolith configuration value

  • evolith-config-set

    Set Evolith configuration value

  • evolith-docs-scaffold

    Scaffold the base documentation required by Evolith (README.md, AGENTS.md, MASTER_INDEX.md, evolith.yaml) into a target directory. Mirrors the CLI `docs` command. Mutative: writes files unless dryRun is set.

  • evolith-dora-metrics

    Calculate DORA metrics approximations using Git log history

  • evolith-drift-detect

    Detect architecture drift in a repository

  • evolith-evaluate

    Evaluate a canonical EvaluationContext (gates, artifacts, rules, compliance) and return an EvaluationResult (ADR-0073 envelope). Stateless: product/tenant/initiative are opaque context only.

  • evolith-fixtures

    Seed reproducible fixtures and sample data (evolith.yaml, ADRs, rulesets) for demos and tests. Mirrors the "evolith fixtures" CLI command.

  • evolith-gate-evaluate

    Evaluate a specific SDLC phase gate

  • evolith-init-batch

    Non-interactive (batch/CI) initialization of an Evolith satellite. Parity with the CLI

  • evolith-knowledge-search

    Search the Evolith architecture knowledge corpus (ADRs, rulesets, standards) with BM25-first hybrid retrieval. Returns ranked chunks with full citations. Optimised for exact identifiers such as ADR-0111 as well as natural-language questions.

  • evolith-metrics

    Get MCP server metrics (per-tool call counts, latency, failures)

  • evolith-moscow-createwrite action

    Create a new MoSCoW prioritization analysis

  • evolith-moscow-list

    List all MoSCoW analyses in a repository

  • evolith-moscow-load

    Load an existing MoSCoW analysis

  • evolith-moscow-removewrite action

    Remove a specific item from a MoSCoW analysis

  • evolith-moscow-report

    Generate a markdown report of a MoSCoW analysis

  • evolith-moscow-updatewrite action

    Update a specific item in a MoSCoW analysis

  • evolith-moscow-validate

    Validate a MoSCoW analysis rules (e.g. 60/20/20 split)

  • evolith-pattern-get

    Get one canonical pattern (PAT-NNNN) by id, case-insensitively. Returns the full record — problem,

  • evolith-pattern-list

    List the canonical architectural patterns and anti-patterns (PAT-NNNN) published by Evolith Core,

  • evolith-pattern-list-by-topology

    List the canonical patterns that apply to a topology, how strongly (required → recommended → optional)

  • evolith-phase-advance

    Propose an SDLC phase transition by evaluating the current phase exit criteria

  • evolith-phase-artifacts-evaluate

    Measure downstream-phase artifact completeness for a confirmed topology composition

  • evolith-ruleset-list

    List the ruleset packs this Core can evaluate. Returns the canonical refs accepted by

  • evolith-satellite-adopt

    Adopt an existing GitHub repository as an Evolith satellite. Returns an ADR-0073 output envelope.

  • evolith-satellite-createwrite action

    Create a new satellite repository on GitHub and register it with Evolith. Returns an ADR-0073 output envelope.

  • evolith-satellite-list

    List all registered Evolith satellites from the local satellite-registry.json.

  • evolith-satellite-status

    Get the status and details of a registered Evolith satellite by its ID.

  • evolith-scaffold

    Scaffold an Evolith satellite along the progressive maturity axis

  • evolith-sdlc-generate

    Generate a Hexagonal Architecture scaffold from a Mermaid classDiagram in a Markdown DDD model (parity with the CLI `sdlc generate`). Supply the model inline via `model` or as a file via `from`. Writes files unless `dryRun` is true.

  • evolith-sdlc-handoff

    Perform a phase gate handoff (e.g. phase-0 to phase-1)

  • evolith-sdlc-status

    Get the current SDLC phase status

  • evolith-topology-get

    Get a specific architecture topology by ID

  • evolith-topology-list

    List all available architecture topologies in Evolith Core.

  • evolith-topology-recommend

    Recommend a topology composition from technical signals (advisory, ADR-0104 / GT-430).

  • evolith-upgrade-apply

    Apply a satellite upgrade from the upstream Evolith core. Writes files into the satellite. Set force=true to proceed when breaking changes are detected.

  • evolith-upgrade-plan

    Plan a satellite upgrade against the upstream Evolith core (read-only / dry-run). Computes the change plan, breaking changes and estimated risk without writing any files.

  • evolith-validate

    Validate a satellite repository against Evolith rules. Supports end-to-end evaluation pipeline via manifest.

  • evolith.yaml

    Evolith satellite contract (validated against evolith-yaml.schema.json)

Public scan report

scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it

no findings
  • Code scan462 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 91/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Evolith Architecture Governance compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
91/100
higher than 85% of 48,255 servers
Tools
56
the typical server has 7
Tools that change things
14%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
2
more than 75% of 28,688 servers
Downloads a week
68
more than 53% of 12,191 servers with a package

What its tools let an agent do: 48 read · 8 change

Install Evolith Architecture Governance in Claude Code, Cursor or VS Code

Runs npx -y @beyondnet/evolith-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add evolith -- npx -y @beyondnet/evolith-mcp
Add to Cursor

What the publisher says

From the Evolith Architecture Governance repository's README, as published. We do not edit it. Read it on GitHub

Evolith Core

Bilingual Navigation: Versión en Español

Your architecture rules, running on every PR.

Real output of the published CLI on an empty repository (2026-09-14, abridged; full 71-row capture).

Architecture decisions tend to live in documents nobody reads again. Evolith turns them into rules that are checked automatically every time someone opens a pull request.

What it does

It reads your repository — folders, workflows, manifests, architecture decisions — and compares it against a library of rules about layering, dependencies, security and CI/CD. If a blocking rule is not met, the PR does not pass. It is a linter, but for architecture.

What makes it different

  1. It counts what it could not check. A regular linter only reports what failed. Evolith also reports the rules it never got to evaluate; if one of them is blocking, the PR fails just the same. So "all green" never means "nothing was checked".
  1. It follows the product lifecycle. Every product is in a phase: Discovery → Design → Construction → QA → Delivery. Evolith evaluates the gates of the current phase and does not recommend moving to the next one until they pass, keeping evidence of every step. Architecture decisions (ADRs) are written with the same tool and many rules derive from them.

Who it is for

  • Teams that want their architecture decisions enforced automatically, not reviewed by hand.
  • Platforms that need to block non-conformant artifacts before they reach production.
  • AI agents that must validate their own output against the same rules as the human team.

Where to start

  1. Try it in two minutes — one npx and you see your first result.
  2. Four terms you need — rule, pack, topology and phase.
  3. Use it in CI — so it runs on every PR.

Want more context? The phase gate, in the CLI and in the Tracker · What is inside · How it compares · What it is not · Documentation · Interactive atlas

Try it in two minutes

You need Node ≥ 18. No database, no server, no Docker; your code never leaves your machine.

npx -y @beyondnet/evolith-cli init --name my-project --yes   # writes evolith.yaml in the current directory
npx -y @beyondnet/evolith-cli validate --engine opa          # evaluates; exits 2 if anything blocking did not pass

The first run will fail, and that is fine: it is a baseline, not a grade. Many rules assume a layout your repository does not have yet. To start only from what you have already adopted:

npx -y @beyondnet/evolith-cli rulesets                        # lists the packs your installation loads
npx -y @beyondnet/evolith-cli validate --engine opa --select rulesets/acl/anti-corruption-layer.rules.json

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Evolith Architecture Governance: common questions

Is Evolith Architecture Governance MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the Evolith Architecture Governance safety report
How do I install Evolith Architecture Governance?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Evolith Architecture Governance need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Evolith Architecture Governance maintained?
The last commit was 3 days ago (2026-11-01). The latest release is v1.3.3.
How does Evolith Architecture Governance compare with other MCP servers?
safety score 91/100 (higher than 85% of 48,255 servers); tools 56 (the typical server has 7); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.