Documentation
Build with Confidence
Everything you need to create, deploy, and scale AI agents. From quickstart guides to full API reference.
š
Getting Started
Set up your first agent in under 5 minutes with our quickstart guide.
āš§
Agent Configuration
Learn how to define tools, prompts, guardrails, and model settings.
āš
Integrations
Connect to Slack, GitHub, databases, and 50+ services out of the box.
āš
Monitoring & Logs
Set up dashboards, alerts, and dig into execution traces for debugging.
āš
Security & Permissions
Configure sandboxing, API keys, role-based access, and audit logs.
āā”
API Reference
Full REST & SDK reference. Create, manage, and invoke agents programmatically.
āQuick Start
Define agents with simple markdown files. Configure personality, tools, guardrails, and behavior ā all in one place.
agents/calliope.md
---
name: Calliope
role: Content Writer
model: gpt-4o
temperature: 0.7
max_tokens: 4096
tools:
- web_search
- grammar_check
- plagiarism_scan
guardrails:
- no_hallucination
- brand_voice_check
---
# Calliope ā Content Writer
## Personality
You are Calliope, a seasoned content writer with 10 years
of experience in SaaS marketing. You write in a clear,
conversational tone that balances authority with approachability.
## Instructions
- Always research the topic before writing
- Include data points and statistics where possible
- Structure content with clear headings and short paragraphs
- End every piece with a compelling CTA
- Match the brand voice guide in `/docs/brand-voice.md`
## Examples
**Good:** "AI agents reduced manual QA time by 73% ā here's how."
**Bad:** "AI is really cool and you should use it."crew.yaml
# crew.yaml ā Orchestrate your agent squad
name: content-pipeline
description: End-to-end content production workflow
agents:
- agent: agents/odin.md # Researcher
step: 1
task: "Research the topic and produce a brief"
- agent: agents/calliope.md # Writer
step: 2
depends_on: [1]
task: "Write a blog post based on the research brief"
- agent: agents/apollo.md # SEO Specialist
step: 3
depends_on: [2]
task: "Optimize the draft for target keywords"
- agent: agents/athena.md # Squad Lead (reviewer)
step: 4
depends_on: [3]
task: "Final review ā quality, tone, accuracy"
settings:
parallel: false # Run steps sequentially
max_retries: 2 # Retry failed steps
timeout: 300s # Per-step timeout
output_dir: ./output # Where to save results
notify:
on_complete: slack://content-team
on_failure: email://admin@company.comterminal
# Install the CLI
$ npm install -g @missioncontrolhq/cli
# Initialize a new project
$ mchq init my-agent-squad
ā Created project structure
ā Generated sample agents/
ā Created crew.yaml
# Project structure:
my-agent-squad/
āāā agents/
ā āāā athena.md # Squad Lead
ā āāā calliope.md # Writer
ā āāā odin.md # Researcher
ā āāā apollo.md # SEO
āāā crew.yaml # Orchestration config
āāā tools/
ā āāā custom-search.js # Custom tool definitions
āāā mchq.config.json # API keys & settings
# Run a single agent
$ mchq run agents/calliope.md --input "Write a post about AI agents"
ā Calliope is researching...
ā Calliope is writing...
ā Done ā output saved to ./output/post.md
# Run the full crew pipeline
$ mchq crew run crew.yaml --input "AI agents for customer support"
ā Step 1: Odin completed research brief
ā Step 2: Calliope wrote the draft (1,847 words)
ā Step 3: Apollo optimized ā SEO score 94
ā Step 4: Athena approved ā no revisions needed
ā Pipeline complete ā output saved to ./output/Need help?
Join our Discord community or reach out to support ā we're here to help you succeed.