Daedalus MCP
Daedalus MCP is a local Model Context Protocol server that scans your workspace, detects projects and their tech stacks, and creates/runs specialized engineering agent pipelines for planning, code review, and architectural analysis.
Core Capabilities:
Initialize Engineering Agents (
daedalus_init): Scans the workspace to detect projects and technologies (language, framework, build tool, etc.), creates reusable agent templates, and generates per-projectagents.config.yamlandagents/directories. Supports options likeforce,refreshProjectKnowledge,refreshTemplates, andmaxDepth.List Detected Projects (
daedalus_listProjects): Lists all projects found during the lastinitscan.List Project Groups (
daedalus_listGroups): Lists auto-generated groups such asall,java-all,angular-all,java21-spring-boot-all, etc., for targeting multiple related projects at once.Run Agent Pipelines (
daedalus_run): Executes a named pipeline (e.g.,planorreview) over a group or explicit list of projects, returning a per-agent/per-project report.planpipeline:plan → rules → performance → architecturereviewpipeline:code-review → rules → performance → architecture
Slash-Style Command Parser (
daedalus): Parses commands like/daedalus init,/daedalus listProjects,/daedalus plan --group:java-all "task", or/daedalus review --project [a,b] "task"into structured tool calls.Legacy Aliases (
agent_init,agent): Backward-compatible aliases fordaedalus_initanddaedalus.
Example Use Cases:
Scan a monorepo and auto-generate engineering agent configurations for each sub-project.
Run a planning or review pipeline across all Java/Spring Boot services simultaneously.
Generate and reuse technology-specific agent templates (e.g.,
java21-spring-boot-plan,typescript-angular-plan).
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Daedalus MCP plan --group:all 'add healthcheck'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Daedalus MCP
Daedalus MCP is a local Model Context Protocol (MCP) server for creating and running specialized engineering agents per project or workspace.
It is designed for workspaces that may contain:
a single backend service;
several related microservices;
a frontend + BFF + backend setup;
a monorepo or folder with multiple related projects.
Daedalus scans the current workspace, detects the projects and their technologies, creates reusable agent templates, generates project-specific rules/knowledge, and lets you run sequential agent pipelines such as planning, rules validation, performance review, and architecture review.
Main idea
Given a workspace like:
workspace/
catalog/
data-mirror/
vendors-bff/
admin-ui/Daedalus can detect stacks such as Java/Spring Boot or Angular and create:
workspace/
.engineering-agents/
workspace.agents.yaml
catalog/
agents.config.yaml
agents/
plan/
rules/
performance/
architecture/
admin-ui/
agents.config.yaml
agents/
plan/
rules/
performance/
architecture/Reusable templates live inside this MCP project:
templates/
java21-spring-boot-plan/
typescript-angular-plan/
project-rules-validator/
performance-jvm/
performance-web-node/
architecture-microservice/
architecture-frontend/Daedalus does not overwrite existing files by default.
Related MCP server: portuni
Available MCP prompts / slash commands
Daedalus also registers MCP prompts named daedalus and daedalus-init. In clients that expose MCP prompts as slash commands, you can use:
/daedalus init
/daedalus listProjects
/daedalus plan --group:java-all "agregar healthcheck estándar"
/daedalus review --group:java-all "revisar el diff actual"If the client says the slash command does not exist, use natural language or the daedalus tool directly, for example: “Use Daedalus and run /daedalus init”. Slash command availability is controlled by the host client, not by the MCP server alone.
Available MCP tools
daedalus_init
Scans the current workspace and initializes agents.
Equivalent slash-style command:
/daedalus initWhat it does:
Detects the current workspace from MCP roots or
cwd.Finds projects inside the workspace.
Detects language, framework, build tool, package manager and architecture.
Creates missing reusable templates.
Creates
agents.config.yamlandagents/inside each detected project.Creates workspace groups like
all,java-all,angular-all, etc.
Options:
{
workspacePath?: string,
force?: boolean,
refreshProjectKnowledge?: boolean,
refreshTemplates?: boolean,
maxDepth?: number
}daedalus_listProjects
Lists projects detected by the last init.
Slash-style command:
/daedalus listProjectsdaedalus_listGroups
Lists generated project groups.
Slash-style command:
/daedalus listGroupsExamples of groups:
all
java-all
java21-spring-boot-all
spring-boot-all
angular-all
typescript-alldaedalus_run
Runs an agent pipeline over a group or selected projects.
Slash-style examples:
/daedalus plan --group:java-all "agregar healthcheck estándar"/daedalus plan --group:angular-all "agregar healthcheck estándar"/daedalus plan --group:all "agregar healthcheck estándar"/daedalus plan --project [catalog,data-mirror,vendors-bff] "agregar healthcheck estándar"The report includes the response from every agent for every selected project.
Default plan pipeline:
plan -> rules -> performance -> architecturedaedalus_review
Runs the code-review pipeline over a group or selected projects. It reviews code, diffs, files or change descriptions using language/framework best practices and project-specific rules.
Slash-style examples:
/daedalus review --group:java-all "revisar el diff actual"/daedalus review --project [catalog,data-mirror] "revisar cambios de healthcheck"Default review pipeline:
code-review -> rules -> performance -> architecturedaedalus
Convenience parser for slash-style commands.
Input example:
{
"command": "/daedalus plan --group:java-all \"agregar healthcheck estándar\""
}Legacy aliases agent and agent_init are also available, but /daedalus is preferred.
Installation from local checkout
1. Clone the repository
git clone https://github.com/daedalus/daedalus-mcp.git
cd daedalus-mcpReplace the URL with the real repository URL if different.
2. Install dependencies
npm install3. Build
npm run build4. Link the local binary
npm linkThis exposes:
daedalus-mcpVerify:
which daedalus-mcpIf your MCP client does not inherit your shell PATH, use the absolute path returned by which daedalus-mcp.
Add to Codex
Edit:
~/.codex/config.tomlAdd:
[mcp_servers.daedalus]
command = "daedalus-mcp"
startup_timeout_sec = 60If Codex cannot find daedalus-mcp, use the absolute path:
[mcp_servers.daedalus]
command = "/absolute/path/to/daedalus-mcp"
startup_timeout_sec = 60Restart Codex.
Claude Code slash command /daedalus
Claude Code slash commands are client-side prompt files. If /daedalus is not recognized even though the MCP server is running, create this user-level command:
mkdir -p ~/.claude/commands
cat > ~/.claude/commands/daedalus.md <<'EOF'
---
description: Run Daedalus MCP commands
allowed-tools: mcp__daedalus__daedalus, mcp__daedalus__daedalus_init, mcp__daedalus__daedalus_listProjects, mcp__daedalus__daedalus_listGroups, mcp__daedalus__daedalus_run
---
Use the Daedalus MCP server. Run the MCP tool `daedalus` with:
```json
{ "command": "/daedalus $ARGUMENTS" }If $ARGUMENTS is empty, use /daedalus init. Summarize the MCP result for the user.
EOF
Restart Claude Code after creating or changing this file. Then use:
```txt
/daedalus init
/daedalus listProjects
/daedalus plan --group:java-all "agregar healthcheck estándar"
/daedalus review --group:java-all "revisar el diff actual"Add to Claude Desktop
Edit:
~/Library/Application Support/Claude/claude_desktop_config.jsonAdd the server inside mcpServers:
{
"mcpServers": {
"daedalus": {
"command": "daedalus-mcp"
}
}
}If Claude cannot find daedalus-mcp, use the absolute path:
{
"mcpServers": {
"daedalus": {
"command": "/absolute/path/to/daedalus-mcp"
}
}
}Restart Claude Desktop.
Prompt to install from another Codex/Claude chat
Once this project is published, you can open a new Codex or Claude chat and say something like:
Install the Daedalus MCP from https://github.com/daedalus/daedalus-mcp.
Clone it, run npm install, npm run build, npm link, and add it as an MCP server named daedalus using the daedalus-mcp command. Then restart or tell me to restart the client.For Codex specifically:
Install the MCP server from https://github.com/daedalus/daedalus-mcp and add this to ~/.codex/config.toml:
[mcp_servers.daedalus]
command = "daedalus-mcp"
startup_timeout_sec = 60For Claude Desktop specifically:
Install the MCP server from https://github.com/daedalus/daedalus-mcp and add it to ~/Library/Application Support/Claude/claude_desktop_config.json under mcpServers as:
"daedalus": {
"command": "daedalus-mcp"
}Typical usage
After adding the MCP server and restarting the client, open a chat in the target workspace and run:
Use Daedalus and run /daedalus initThen inspect what was detected:
Use Daedalus and run /daedalus listProjectsUse Daedalus and run /daedalus listGroupsRun a plan for all Java projects:
Use Daedalus and run /daedalus plan --group:java-all "agregar healthcheck estándar"Run a code review for all Java projects:
Use Daedalus and run /daedalus review --group:java-all "revisar el diff actual"Run a plan for specific projects:
Use Daedalus and run /daedalus plan --project [catalog,data-mirror,vendors-bff] "agregar healthcheck estándar"Generated files
Workspace config
.engineering-agents/workspace.agents.yamlContains detected projects and groups.
Per-project config
agents.config.yamlContains project metadata, agents and pipelines.
Per-project agents
agents/
plan/
prompt.md
agent.yaml
knowledge/
general/
project/
rules/
performance/
architecture/Reusable templates
templates/Templates are shared by technology/version/architecture and reused across projects.
Development
npm install
npm run buildRun directly:
npm startType-check:
npx tsc --noEmitNotes
Daedalus uses MCP
roots/listwhen available to identify the workspace opened in the client.If roots are unavailable, it falls back to the process
cwd.workspacePathcan be provided manually as an override.Existing generated files are preserved by default. If a previous init generated stale project knowledge, rerun init with
refreshProjectKnowledge: trueto regenerate generatedknowledge/generalandknowledge/projectfiles.Pipeline execution uses MCP sampling when the host supports it. Some hosts return
MCP error -32601: Method not foundfor sampling; in that case Daedalus now catches it and returns a handoff report with the prepared agent prompts/context so the host assistant can execute the reasoning in its final response.
Available Tools
7 toolsagentAgent command parser (legacy alias)D
Alias legacy de daedalus. Acepta /agent y /daedalus.
Inputs: command (required), workspacePath.
agent_initInitialize Engineering Agents (legacy alias)D
Alias legacy de daedalus_init.
Inputs: workspacePath, force, refreshProjectKnowledge, refreshTemplates, +1 more.
daedalusAgent command parserB
Parser conveniente para comandos estilo /daedalus init, /daedalus listProjects, /daedalus plan --group:java-all "tarea" o /daedalus plan --project [a,b] "tarea". También acepta /agent por compatibilidad.
Inputs: command (required), workspacePath.
daedalus_initInitialize Engineering AgentsB
Escanea el workspace actual, crea templates reutilizables si faltan y genera agents.config.yaml + agents/ por proyecto sin pisar archivos existentes.
Inputs: workspacePath, force, refreshProjectKnowledge, refreshTemplates, +1 more.
daedalus_listGroupsList project groupsB
Lista grupos disponibles como all, java-all o angular-all generados por /daedalus init.
Inputs: workspacePath.
daedalus_listProjectsList scanned projectsB
Lista los proyectos detectados por /daedalus init en el workspace actual.
Inputs: workspacePath.
daedalus_runRun agent pipelineA
Ejecuta un pipeline como plan sobre un grupo o lista de proyectos y devuelve un reporte por agente/proyecto.
Inputs: task (required), pipeline, group, projects, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Multiple tools serve as aliases (agent vs daedalus, agent_init vs daedalus_init), causing ambiguity. An agent can't easily distinguish which parser to use for command interpretation.
Names mix daedalus_ prefix (daedalus_init, daedalus_listGroups) with bare names (agent, agent_init) and inconsistent styles (agent vs daedalus). No uniform pattern.
7 tools is appropriate for a project management assistant, covering initialization, listing, and execution. Not excessive or insufficient.
Core operations (init, list, run) are present, but missing update/delete actions for projects or groups. Coverage is adequate but not full CRUD.
Maintenance
Related MCP Connectors
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
ArcAgent MCP server for bounty discovery, workspace execution, and verified coding submissions.
MCP Server for an Agent Task Marketplace
MCP server for building and testing AI agents with multi-model experimentation and insights.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceMCP server for automated architectural mapping, security vulnerability detection, ML asset tracking, and code metrics in local repositories.-
- AlicenseNot gradedqualityBmaintenanceAn MCP server that provides a shared graph of an organization's projects, processes, areas, and principles, enabling consistent context for tools and AI agents.2Apache 2.0
- AlicenseNot gradedqualityBmaintenanceMCP server for local-first code intelligence, providing structural code graph, semantic search, and impact analysis to AI agents.2MIT
- AlicenseNot gradedqualityBmaintenanceA self-hosted MCP server that enables AI coding agents to read, edit, search, and run code in local projects with human review loops and policy controls.MIT