Skip to main content
Glama
specdog

dotdog

by specdog
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

dotdog

npm version npm downloads License: MIT CI

Feed the dog. Ship with specs. Write .dog specs. Dog checks them. AI agents fetch them.

Install

npm install -g dotdog

Requires Node.js >= 20.

Related MCP server: CodeGraph

Quick Start

dotdog init my-project     # scaffold a spec genome
dotdog validate            # score completeness (0-100%)
dotdog analyze             # deep analysis : gaps, suggestions, entity audit

Commands

Command

Description

dotdog validate [dir]

Score spec completeness. Checks file existence, entity descriptions, section counts.

dotdog analyze [dir]

Deep analysis. Detects domain, stack, gaps with severity, entity quality audit.

dotdog parse <file>

Parse a .dog file into sections.

dotdog compile [dir]

Compile .dog files into a .dag graph (JSON).

dotdog visualize [dir]

Output Mermaid graph from .dag. --save writes .md for GitHub rendering.

dotdog serve [dir]

Start MCP server over stdio. AI agents query specs without hallucination.

dotdog staleness [dir]

Detect drift between spec and reality. Compares plan.dog tasks against code.

dotdog generate [dir]

Generate missing spec files from SPEC.dog (data-model, COPY, INDEX).

dotdog simulate <scenario>

Run a simulation scenario. Reads SPEC.dog scenarios, checks pre/postconditions.

dotdog init <project>

Scaffold a new spec genome project with templates.

dotdog list

List all projects and their .dog file counts.

File Formats

.dog : Human-Written Spec Genome

Markdown prose + YAML structured blocks. Free and open source. Define entities, relationships, events, predictions, and copy in a single format that both humans and parsers understand.

### Entity: User

A person who uses the app.

` ``yaml
entity: User
type: entity
properties:
  id:
    type: string
    required: true
  email:
    type: string
    required: true
states: [active, suspended]
lifecycle: active → suspended
` ``

.dag : Machine-Compiled Graph

JSON graph compiled from .dog files. Nodes, edges, properties, and states in a deterministic structure. 85% token savings vs raw .dog files for AI agents.

MCP Server : AI Agent Integration

dotdog serve exposes specs to any MCP-compatible AI agent over stdio. Six tools:

Tool

Description

getEntity

Exact entity with properties, states, lifecycle, and connected edges

traverse

BFS subgraph from any starting node to any depth

search

Find entities by name or type

schema

Property definitions only : zero prose, agent-optimized

summary

Node count, edge count, file count, compile time

listProjects

Array of project names

Agent workflow: listProjects → getEntity → traverse graph.

Dogfood

dotdog validates its own specs. Every PR:

dotdog validate → find gaps → fix spec → PR → merge → tag → CI publish

Eat your own dogfood. The tool is the project.

VS Code Extension

Syntax highlighting for .dog files. Install:

cp -r extensions/vscode ~/.vscode/extensions/dotdog

Format Specifications

Links

Spec-Driven Development

dotdog is built for SDD. Write your spec first. Validate it. Compile it. Let AI agents query it. The spec is the source of truth.

spec → validate → compile → serve → AI agent queries

No more specs that rot in a wiki. No more agents guessing from prose. One source. Zero ambiguity.

License

MIT

This server cannot be installed

A
license - permissive license
-
quality - not tested
C
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/specdog/dotdog'

If you have feedback or need assistance with the MCP directory API, please join our Discord server