Agent Integration

chant integrates with AI coding agents through three surfaces: skills (operational knowledge), MCP tools (programmatic actions), and spells (task orchestration). You write TypeScript; the agent uses these surfaces to understand and execute the build → validate → deploy → troubleshoot workflow.

Skills

Skills are operational playbooks — structured markdown documents contributed by lexicons. They teach agents how to work with a specific infrastructure platform: which commands to run, what to validate, how to deploy, and how to troubleshoot failures.

Skills are installed by chant init and refreshed by chant update. They live in the project root at skills/:

my-project/
  skills/
    chant-aws/
      SKILL.md
    chant-aws-eks/
      SKILL.md
  src/
    index.ts

Agents that support file-based skill discovery load these automatically. Skills are also inlined into spell prompts when a spell declares a lexicon (see Spells below).

You don’t need to read or manage skill files yourself — they’re installed once and the agent reads them as needed.

MCP Tools

The MCP (Model Context Protocol) server gives agents programmatic access to chant operations. When an agent connects via MCP, it can build projects, run lint checks, scaffold files, and more — without the user typing commands.

Setup

chant init configures MCP automatically by writing to your IDE’s global MCP config file.

To configure manually, add the chant MCP server to your IDE’s MCP config:

{
  "mcpServers": {
    "chant": {
      "command": "npx",
      "args": ["chant", "serve", "mcp"]
    }
  }
}

Available Tools

MCP tool	Description
build	Synthesize and write infrastructure output
lint	Run lint checks on TypeScript intent definitions
import	Import infrastructure templates and generate TypeScript files
explain	Summarize project resources by lexicon and kind
scaffold	Generate starter files from lexicon templates
search	Search available resource types across lexicons

Resources

MCP resource	Description
chant://context	Lexicon-specific instructions and patterns for chant development
chant://examples/list	List of available chant examples

Lexicon plugins can contribute additional tools and resources.

Spells

Spells orchestrate multi-step agent tasks like deployments. A spell defines what to do (deploy this stack, take a state snapshot). When a spell declares a lexicon, the relevant skills are automatically inlined into the generated prompt — the agent gets the full operational playbook without the spell needing to spell out every step.

chant spell cast lambda-function

This produces a markdown prompt containing the spell overview, resolved context, inlined skills, and a task checklist. Paste it into your agent to start the work.

See the Spells guide for details.

When to Use What

Surface	When	Example
Skills	Always-on guidance — installed once, agent reads as needed	Agent checks the AWS skill before deploying a CloudFormation stack
MCP tools	Programmatic actions during execution	Agent calls build to synthesize templates, lint to validate
Spells	Structured multi-step tasks	Orchestrating a full deploy + state snapshot across dependencies

Skills and MCP tools are complementary: skills tell the agent what to do, MCP tools let it do it. Spells tie both together into repeatable workflows.