Daedalus Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Daedalus Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
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:
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.
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.
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.
daedalus_initScans the current workspace and initializes agents.
Equivalent slash-style command:
/daedalus initWhat it does:
cwd.agents.config.yaml and agents/ inside each detected project.all, java-all, angular-all, etc.Options:
{
workspacePath?: string,
force?: boolean,
refreshProjectKnowledge?: boolean,
refreshTemplates?: boolean,
maxDepth?: number
}daedalus_listProjectsLists projects detected by the last init.
Slash-style command:
/daedalus listProjectsdaedalus_listGroupsLists generated project groups.
Slash-style command:
/daedalus listGroupsExamples of groups:
all
java-all
java21-spring-boot-all
spring-boot-all
angular-all
typescript-alldaedalus_runRuns 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_reviewRuns 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 -> architecturedaedalusConvenience 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.
git clone https://github.com/daedalus/daedalus-mcp.git
cd daedalus-mcpReplace the URL with the real repository URL if different.
npm installnpm run buildnpm 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.
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.
/daedalusClaude 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:
{ "command": "/daedalus $ARGUMENTS" }
If `$ARGUMENTS` is empty, use `/daedalus init`. Summarize the MCP result for the user.
EOFRestart Claude Code after creating or changing this file. Then use:
/daedalus init
/daedalus listProjects
/daedalus plan --group:java-all "agregar healthcheck estándar"
/daedalus review --group:java-all "revisar el diff actual"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.
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"
}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".engineering-agents/workspace.agents.yamlContains detected projects and groups.
agents.config.yamlContains project metadata, agents and pipelines.
agents/
plan/
prompt.md
agent.yaml
knowledge/
general/
project/
rules/
performance/
architecture/templates/Templates are shared by technology/version/architecture and reused across projects.
npm install
npm run buildRun directly:
npm startType-check:
npx tsc --noEmitroots/list when available to identify the workspace opened in the client.cwd.workspacePath can be provided manually as an override.refreshProjectKnowledge: true to regenerate generated knowledge/general and knowledge/project files.MCP error -32601: Method not found for 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.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.