MCP serverCurated by metahubEval warningsprompts

maestro-workflow-mcp

Name: maestro-workflow-mcp
Author: sharpdeveye

MCP server for Maestro — exposes 25 workflow skills as tools, prompts, and resources for any MCP-compatible AI client

pinned to #00f9115updated 3 months ago

7/11Verified publisherCurated by MetaHubLicensedDocumentedMCP SDK linkedRunnableClean repo

Ask your AI client: “install mcps/maestro-workflow-mcp”.

Requires the metahub MCP server installed in your client. Set up MCP.

mh install mcps/maestro-workflow-mcp

metahub onboarded this repo on the author's behalf.

If you own github.com/sharpdeveye/maestro on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.

Claim this repo

Stars

402

Last commit

3 months ago

00f9115

Latest release

published

3 months ago

#agent-orchestration
#agents
#ai
#ai-agents
#ai-workflows
#claude-code
#codex
#copilot
#cursor
#developer-tools
#gemini
#maestro
#mcp
#model-context-protocol
#open-source
#prompt-engineering
#skills
#workflow

What this server exposes

Surfaces parsed from this server's source at publish time.

Launches: maestro-workflow-mcp

Evaluation report

WarningsView full report

Automated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.00f9115· 3 months ago

Behavioral checks haven't run yet: the sandbox couldn't execute this artifact (it may need credentials we don't provide, or an unsupported build). An environment limit, not a verdict.

Safety

2 passed1 warning

Dependencies: known vulnerabilitieswarn
3 high/critical advisories — @modelcontextprotocol/[email protected] (HIGH: GHSA-345p-7cg4-v4c7) · @modelcontextprotocol/[email protected] (HIGH: GHSA-8r9q-7v3j-jr4g) (+1)
Update the affected packages, then re-publish. (`npm audit` shows the same data locally.)
LICENSE file at repo root
LICENSE
No sensitive files in the repo
scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found

Release history

releasecurrent00f9115warn3 months ago

View on GitHub

Installation

Local (stdio)

Add to your MCP client configuration:

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "maestro": {
      "command": "npx",
      "args": ["-y", "maestro-workflow-mcp"]
    }
  }
}

Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "maestro": {
      "command": "npx",
      "args": ["-y", "maestro-workflow-mcp"]
    }
  }
}

VS Code / Antigravity (.vscode/mcp.json):

{
  "servers": {
    "maestro": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "maestro-workflow-mcp"]
    }
  }
}

Remote (HTTP)

Start as a public HTTP endpoint:

npx maestro-workflow-mcp --http --port 3001

Clients connect to http://your-server:3001/mcp. Health check at /health.

API Reference

Tools

Tool	Description
`maestro_list_commands`	List all 25 commands grouped by category
`maestro_run_command`	Get full instructions for a specific command
`maestro_read_context`	Read `.maestro/context.md` or `.maestro.md` from a project
`maestro_init`	Generate a `.maestro.md` template
`maestro_wave_start`	Start a multi-phase wave execution
`maestro_wave_advance`	Advance a wave by submitting phase output
`maestro_wave_status`	Get current wave progress
`maestro_write_decision`	Append a decision to `.maestro/decisions.jsonl`
`maestro_read_decisions`	Read recent decisions from the log
`maestro_read_audit`	Read audit trail with duration and cost

Prompts

25 prompt templates — one per command. Select from your client's prompt picker:

diagnose · evaluate · reflect · refine · streamline · calibrate · fortify · zero-defect · amplify · compose · enrich · accelerate · chain · guard · iterate · temper · turbocharge · extract-pattern · adapt-workflow · onboard-agent · specialize · teach-maestro · capture · recap

Resources

URI	Content
`maestro://skill/agent-workflow`	Core workflow design principles
`maestro://reference/prompt-engineering`	Prompt structure, CoT, few-shot
`maestro://reference/context-management`	Window optimization, state
`maestro://reference/tool-orchestration`	Tool design, error handling
`maestro://reference/agent-architecture`	Multi-agent topologies
`maestro://reference/feedback-loops`	Evaluation, self-correction
`maestro://reference/knowledge-systems`	RAG, embeddings
`maestro://reference/guardrails-safety`	Validation, cost controls

License

MIT — see LICENSE.

Reviews

No reviews yet. Be the first.

MCP

Agno

The programming language for agentic software.

#7f510d3UnknownCoding & Refactoring+3

Caveman

MCP proxy that compresses prose fields (tool descriptions, etc.) using caveman rules. Same accuracy, fewer context tokens.

#25d22f8UnknownPrompts, Context & Memory+4

google-example

Example project for Google GenAI

#a0f37a7UnknownCoding & Refactoring+5

ComposioHQ

29,169

agentic-aiagentsai+9

mh install mcps/maestro-workflow-mcp

MCP serverCurated by metahubEval warningsprompts

maestro-workflow-mcp

MCP server for Maestro — exposes 25 workflow skills as tools, prompts, and resources for any MCP-compatible AI client

pinned to #00f9115updated 3 months ago

7/11Verified publisherCurated by MetaHubLicensedDocumentedMCP SDK linkedRunnableClean repo

Ask your AI client: “install mcps/maestro-workflow-mcp”.

Requires the metahub MCP server installed in your client. Set up MCP.

mh install mcps/maestro-workflow-mcp

metahub onboarded this repo on the author's behalf.

Claim this repo

Stars

402

Last commit

3 months ago

00f9115

Latest release

published

3 months ago

#agent-orchestration
#agents
#ai
#ai-agents
#ai-workflows
#claude-code
#codex
#copilot
#cursor
#developer-tools
#gemini
#maestro
#mcp
#model-context-protocol
#open-source
#prompt-engineering
#skills
#workflow

What this server exposes

Surfaces parsed from this server's source at publish time.

Launches: maestro-workflow-mcp

Evaluation report

WarningsView full report

Automated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.00f9115· 3 months ago

Behavioral checks haven't run yet: the sandbox couldn't execute this artifact (it may need credentials we don't provide, or an unsupported build). An environment limit, not a verdict.

Safety

2 passed1 warning

Dependencies: known vulnerabilitieswarn
3 high/critical advisories — @modelcontextprotocol/[email protected] (HIGH: GHSA-345p-7cg4-v4c7) · @modelcontextprotocol/[email protected] (HIGH: GHSA-8r9q-7v3j-jr4g) (+1)
Update the affected packages, then re-publish. (`npm audit` shows the same data locally.)
LICENSE file at repo root
LICENSE
No sensitive files in the repo
scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found

Release history

releasecurrent00f9115warn3 months ago

View on GitHub

Installation

Local (stdio)

Add to your MCP client configuration:

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "maestro": {
      "command": "npx",
      "args": ["-y", "maestro-workflow-mcp"]
    }
  }
}

Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "maestro": {
      "command": "npx",
      "args": ["-y", "maestro-workflow-mcp"]
    }
  }
}

VS Code / Antigravity (.vscode/mcp.json):

{
  "servers": {
    "maestro": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "maestro-workflow-mcp"]
    }
  }
}

Remote (HTTP)

Start as a public HTTP endpoint:

npx maestro-workflow-mcp --http --port 3001

Clients connect to http://your-server:3001/mcp. Health check at /health.

API Reference

Tools

Tool	Description
`maestro_list_commands`	List all 25 commands grouped by category
`maestro_run_command`	Get full instructions for a specific command
`maestro_read_context`	Read `.maestro/context.md` or `.maestro.md` from a project
`maestro_init`	Generate a `.maestro.md` template
`maestro_wave_start`	Start a multi-phase wave execution
`maestro_wave_advance`	Advance a wave by submitting phase output
`maestro_wave_status`	Get current wave progress
`maestro_write_decision`	Append a decision to `.maestro/decisions.jsonl`
`maestro_read_decisions`	Read recent decisions from the log
`maestro_read_audit`	Read audit trail with duration and cost

Prompts

25 prompt templates — one per command. Select from your client's prompt picker:

Resources

URI	Content
`maestro://skill/agent-workflow`	Core workflow design principles
`maestro://reference/prompt-engineering`	Prompt structure, CoT, few-shot
`maestro://reference/context-management`	Window optimization, state
`maestro://reference/tool-orchestration`	Tool design, error handling
`maestro://reference/agent-architecture`	Multi-agent topologies
`maestro://reference/feedback-loops`	Evaluation, self-correction
`maestro://reference/knowledge-systems`	RAG, embeddings
`maestro://reference/guardrails-safety`	Validation, cost controls