SkillAgentSearch skills...

atlas-mcp-server

A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - implementing a three-tier architecture (Projects, Tasks, Knowledge) to manage complex workflows. Now with Deep Research.

Install / Use

claude mcp add cyanheads -- npx -y github:cyanheads/atlas-mcp-server

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

46/100

Category

Automation

Supported Platforms

Claude Code
Claude Desktop

Our assessment of atlas-mcp-server

atlas-mcp-server scores 46/100 on our quality scale, 2780th of 2,864 Automation skills we index.

Its MCP Server is 3.6 KB long, written without headings and no code examples: a solid amount of guidance for an agent.

It has no GitHub stars yet, so there is no community track record; judge it on its content.

Substance
26/30
Structure
0/20
Description
15/15
Adoption
0/20
Freshness
5/15

Maintenance, license and trust

  • We could not determine when the repository was last updated.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

atlas-mcp-server compared with similar skills

All 4 of these similar skills score higher than atlas-mcp-server; compare them before choosing.

SkillScoreStarsUpdatedFormat
atlas-mcp-server (this skill)by cyanheads460—MCP Server
Agent-Reachby Panniantong100105.5k3d agoCLAUDE.md
headroomby headroomlabs-ai10078.1ktodayCLAUDE.md
CowAgentby zhayujie10047.7ktodayCLAUDE.md
Scraplingby D4Vinci10090.2ktodayMCP Server

Frequently asked questions

How do I install atlas-mcp-server?
Run claude mcp add cyanheads -- npx -y github:cyanheads/atlas-mcp-server. The install tabs above show the steps for each supported agent.
Which AI agents does atlas-mcp-server work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is atlas-mcp-server safe to use?
It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is atlas-mcp-server still maintained?
We could not determine when the repository was last updated.

{ "name": "atlas-mcp-server", "version": "2.8.15", "description": "ATLAS (Adaptive Task & Logic Automation System): An MCP server enabling LLM agents to manage projects, tasks, and knowledge via a Neo4j-backed, three-tier architecture. Facilitates complex workflow automation and project management through LLM Agents.", "type": "module", "main": "dist/index.js", "exports": "./dist/index.js", "files": [ "dist" ], "bin": { "atlas-mcp-server": "dist/index.js" }, "repository": { "type": "git", "url": "git+https://github.com/cyanheads/atlas-mcp-server.git" }, "bugs": { "url": "https://github.com/cyanheads/atlas-mcp-server/issues" }, "homepage": "https://github.com/cyanheads/atlas-mcp-server#readme", "scripts": { "build": "tsc && node --loader ts-node/esm scripts/make-executable.ts dist/index.js", "db:backup": "node --loader ts-node/esm src/services/neo4j/backupRestoreService/scripts/db-backup.ts", "db:import": "node --loader ts-node/esm src/services/neo4j/backupRestoreService/scripts/db-import.ts", "dev": "tsc -w", "docker:down": "docker-compose down", "docker:logs": "docker-compose logs -f", "docker:up": "docker-compose up -d", "docs:generate": "typedoc", "fetch-spec": "ts-node --esm scripts/fetch-openapi-spec.ts", "format": "prettier --write "**/*.{ts,js,json,md,html,css}"", "inspector": "mcp-inspector --config mcp.json --server atlas-mcp-server", "rebuild": "ts-node --esm scripts/clean.ts && npm run build", "start": "node dist/index.js", "start:http": "MCP_LOG_LEVEL=debug MCP_TRANSPORT_TYPE=http node dist/index.js", "start:stdio": "MCP_LOG_LEVEL=debug MCP_TRANSPORT_TYPE=stdio node dist/index.js", "tree": "ts-node --esm scripts/tree.ts", "webui": "npx serve src/webui -l 8000" }, "keywords": [ "ai-integration", "agent", "atlas", "authentication", "automation", "client-server", "collaboration", "dependency-tracking", "graph-database", "http", "jwt", "knowledge-management", "llm", "llm-agent", "mcp", "model-context-protocol", "model-context-protocol-server", "neo4j", "project-management", "server", "task-management", "three-tier-architecture", "typescript", "unified-search", "workflow-automation" ], "author": "cyanheads casey@caseyjhand.com (https://github.com/cyanheads/atlas-mcp-server#readme)", "license": "Apache-2.0", "engines": { "node": ">=16.0.0" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.12.1", "@types/node": "^22.15.29", "@types/node-cron": "^3.0.11", "chrono-node": "2.8.0", "commander": "^14.0.0", "cross-env": "^7.0.3", "date-fns": "^4.1.0", "dotenv": "^16.5.0", "express": "^5.1.0", "fuzzysort": "^3.1.0", "ignore": "^7.0.5", "jsonwebtoken": "^9.0.2", "nanoid": "^5.1.5", "neo4j-driver": "^5.28.1", "node-cron": "^4.1.0", "node-schedule": "^2.1.1", "openai": "^5.1.1", "partial-json": "^0.1.7", "sanitize-html": "^2.17.0", "tiktoken": "^1.0.21", "validator": "^13.15.15", "winston": "^3.17.0", "winston-daily-rotate-file": "^5.0.0", "yargs": "^18.0.0", "zod": "^3.25.51" }, "devDependencies": { "@types/express": "^5.0.2", "@types/js-yaml": "^4.0.9", "@types/jsonwebtoken": "^9.0.9", "@types/node-schedule": "^2.1.7", "@types/sanitize-html": "^2.16.0", "@types/validator": "^13.15.1", "axios": "^1.9.0", "js-yaml": "^4.1.0", "prettier": "^3.5.3", "ts-node": "^10.9.2", "typedoc": "^0.28.5", "typescript": "^5.8.3" } }

Related Skills

View on GitHub
GitHub Stars0
CategoryAutomation
UpdatedNaNy ago
Forks0

Trust signals

68/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

2 medium1 low