TeamDay Admin Tool
The TeamdayAdmin tool gives agents full control over platform resources. Available as a built-in MCP tool at mcp__teamday-admin__TeamdayAdmin.
Use it to create workspaces, configure agents, install MCPs, schedule missions, manage skills, and store secrets --- all from within a conversation.
Resources Overview
| Resource | Description | Key Actions |
|---|---|---|
| Spaces | Workspaces / project directories | list, create, get, update, delete, discover |
| Agents | Lightweight AI agents | list, create, get, update, delete |
| Characters | Full AI personas with marketing content | list, create, get, update |
| MCPs | Tool integrations (Google Analytics, etc.) | list, create, get, update, delete |
| Missions | Scheduled AI tasks | list, create, get, update, delete |
| Skills | Reusable agent capabilities | list, create |
| Secrets | Encrypted environment variables | list, store, remove |
| Registry | Browse available skills and MCPs | browseSkillsRegistry, browseMcpRegistry |
Spaces
Spaces are workspaces --- think of them as project directories where agents do their work.
Create a Space
{
"action": "createSpace",
"data": {
"name": "Marketing Hub",
"description": "Content creation and SEO workspace",
"visibility": "organization"
}
}
Update a Space
Add agents, skills, or a cover image:
{
"action": "updateSpace",
"resourceId": "space-abc123",
"data": {
"addAgents": ["agent-id-1", "agent-id-2"],
"addSkills": ["core:research"],
"coverImage": "https://images.unsplash.com/photo-123",
"coverImageAttribution": {
"source": "unsplash",
"photographerName": "Jane Doe"
}
}
}
Discover Space
Scan the space filesystem for agents (.claude/agents/*.md), skills (.claude/skills/*/SKILL.md), and sync them to the platform database:
{
"action": "discoverSpace",
"resourceId": "space-abc123"
}
This is useful after creating agents or skills via files --- the discover action makes them visible in the UI.
Agents vs Characters
TeamDay has two levels of AI personas:
Agents (Lightweight)
Quick to create --- just a name, role, and system prompt.
{
"action": "createAgent",
"data": {
"name": "Research Assistant",
"role": "Research and summarization",
"systemPrompt": "You are a research assistant that finds and summarizes information.",
"image": "https://www.teamday.ai/agents/agent-robot-1.png"
}
}
Characters (Full Persona)
Rich AI team members with marketing content, SEO metadata, skill/MCP references, and more. Use for production-ready, public-facing agents.
{
"action": "createCharacter",
"data": {
"name": "Sarah",
"role": "SEO Analyst",
"category": "marketing",
"system_message": "You are Sarah, an SEO specialist...",
"skillIds": ["seo", "content-analysis"],
"advanced_tools": ["ahrefs"],
"longDescription": "Sarah helps businesses improve their search rankings...",
"faq": [
{
"question": "What can Sarah do?",
"answer": "Sarah analyzes your website's SEO performance..."
}
],
"useCases": ["SEO audits", "Keyword research", "Competitor analysis"],
"visibility": "public"
}
}
Character categories: marketing, finance, hr, engineering, operations, general, data
Adding Agents to Spaces
This is a two-step process --- agents are created independently, then added to spaces:
// Step 1: Create the agent
{
"action": "createAgent",
"data": { "name": "Data Analyst", "role": "SQL and reporting" }
}
// Returns: { "id": "agent-xyz" }
// Step 2: Add to space
{
"action": "updateSpace",
"resourceId": "space-abc123",
"data": { "addAgents": ["agent-xyz"] }
}
MCPs (Tool Integrations)
Install MCP servers so agents can use external tools like Google Analytics, Ahrefs, or custom APIs.
Create an MCP
{
"action": "createMcp",
"data": {
"name": "google-analytics",
"type": "stdio",
"command": "npx",
"args": ["-y", "@anthropic-ai/mcp-google-analytics"],
"env": {
"GA_PROPERTY_ID": "12345678"
}
}
}
Browse Available MCPs
{
"action": "browseMcpRegistry"
}
Missions (Scheduled Tasks)
Missions are scheduled AI tasks that run automatically. Bind them to a Character to run with that persona's personality, skills, and MCPs.
Create a Mission
{
"action": "createMission",
"data": {
"title": "Weekly SEO Report",
"goal": "Analyze this week's search performance, compare to last week, and email the summary.",
"spaceId": "space-abc123",
"characterId": "char-sarah",
"schedule": {
"type": "cron",
"value": "0 9 * * MON"
}
}
}
Schedule Types
| Type | Description | Example |
|---|---|---|
none | Manual trigger only | --- |
once | Run once at scheduled time | "2026-03-01T09:00:00Z" |
cron | Recurring schedule | "0 9 * * MON" (Mondays 9am) |
continuous | Run continuously | --- |
Update a Mission
Pause, change schedule, or update the goal:
{
"action": "updateMission",
"resourceId": "mission-abc",
"data": {
"status": "paused",
"schedule": { "type": "cron", "value": "0 9 * * 1-5" }
}
}
Skills
Skills are reusable capabilities that teach agents how to perform specialized tasks.
Browse Available Skills
{
"action": "browseSkillsRegistry"
}
Create a Skill via API
{
"action": "createSkill",
"data": {
"name": "report-generator",
"description": "Generate formatted PDF reports from data",
"content": "---\nname: report-generator\ndescription: Generate reports\nallowed-tools: Bash, Read, Write\n---\n\n# Report Generator\n\n..."
}
}
Create a Skill via Files (Recommended)
Write the skill directly to the workspace filesystem, then run discoverSpace:
.claude/skills/report-generator/
SKILL.md # Skill definition
scripts/
generate.ts # Executable script
Secrets
Store encrypted environment variables for spaces. These are injected into agent sessions at runtime.
Store Secrets
{
"action": "storeSecrets",
"resourceId": "space-abc123",
"data": {
"secrets": {
"OPENAI_API_KEY": "sk-...",
"DATABASE_URL": "postgres://..."
}
}
}
List Secrets
Returns secret names (not values) for a space:
{
"action": "listSecrets",
"resourceId": "space-abc123"
}
Remove Secrets
{
"action": "removeSecrets",
"resourceId": "space-abc123",
"data": {
"keys": ["OPENAI_API_KEY"]
}
}
Agent Images
Use built-in avatar images from TeamDay's collection:
https://www.teamday.ai/agents/{style}-{number}.png
Available styles (numbers 1-9 each):
agent-new--- Modern, cleanagent-sketch--- Hand-drawn styleagent-geo--- Geometricagent-robot--- Robot/mechanicalagent-animal--- Animal charactersagent-fruit--- Playful fruit characters
Or use any public image URL.
File-Based Creation
The recommended workflow for agents and skills is file-based:
1. Write agent file to .claude/agents/{name}.md:
---
name: Sarah
role: PPC Specialist
skills: [campaign-reporting]
tools: [WebSearch, Read, Write]
---
You are Sarah, a PPC specialist who helps manage advertising campaigns...
2. Write skill file to .claude/skills/{name}/SKILL.md:
---
name: campaign-reporting
description: Generate campaign performance reports
allowed-tools: Bash, Read, Write
env: GA_API_KEY, OPENAI_API_KEY?
---
# Campaign Reporting Skill
...
3. Run discoverSpace to sync files to the platform database.
The env field in skills supports these patterns:
API_KEY--- requiredA | B | C--- any one of (OR)A, B--- all required (AND)KEY?--- optional
Error Handling
All actions return consistent response formats:
Success:
✅ Success
space: "Marketing Hub" (space-abc123)
Validation error:
❌ Validation failed for createSpace: name: Required
API error:
❌ Error: Insufficient permissions
The tool validates data client-side before making API calls, catching common mistakes like missing required fields.