Skip to main content
You want Apie to know what your agent is supposed to do — so it can warn when production behavior drifts from your declared boundaries. Capabilities are that contract: a tool name, the actions it may perform, and the resources it may touch. When you finish this page, your agent’s expected boundaries will be registered with Apie.

​
Declare in config

Add capabilities to your config file. They are auto-declared when the agent registers: 
const apie = new Apie({
  agent: { key: "my-agent", name: "My Agent" },
  capabilities: [
    {
      tool: { name: "search", provider: "internal" },
      actions: ["read"],
      resources: ["knowledge_base"],
      environments: ["production", "staging"],
      riskLevel: "low",
    },
    {
      tool: { name: "github.merge_pr", provider: "github" },
      actions: ["merge"],
      resources: ["code_repository"],
      environments: ["production"],
      riskLevel: "high",
    },
  ],
});

​
Declare via CLI

Push capabilities from your config file without restarting the agent: 
npx apie capabilities declare

​
Declare at runtime

await apie.capabilities.declare([
  {
    tool: { name: "deploy.release", provider: "cicd" },
    actions: ["execute"],
    resources: ["deployment_event"],
    environments: ["production"],
    riskLevel: "high",
  },
]);

​
Define tools (schemas)

Register tool definitions — especially useful when MCP discovers tools at runtime: 
await apie.tools.define({
  name: "filesystem.read_file",
  provider: "filesystem-mcp",
  description: "Read a file from the filesystem",
  actionTypes: ["read"],
  resourceTypes: ["file"],
  riskLevel: "medium",
});
The MCP proxy auto-defines tools when it receives tools/list from the upstream server.

​
What you’ll see

A boundary map in the dashboard showing declared tools, actions, and resources. Undeclared tools used at runtime trigger boundary drift warnings when configured.

​
Capability shape

FieldRequiredDescription
tool.nameYesTool identifier
tool.providerNoProvider namespace (github, cicd, mcp)
actionsYesAllowed action types
resourcesYesAllowed resource types
environmentsNoRestrict to specific environments
riskLevelNolow, medium, high, critical
Common action types: read, create, update, delete, execute, communicate, merge Common resource types: code_repository, deployment_event, pipeline_run, secret, work_item, database_record, file

​
Next steps

Action and resource metadata

Deep dive on the metadata model.

Boundary drift

Detect undeclared tools in production.