Tagged Posts

#Api

4 posts tagged with "Api"

integrations

Integration Capabilities

May 19, 2025 10 min read

Mule provides multiple integration points to extend its capabilities through tools, skills, and WebAssembly modules. These integrations allow you to customize how Mule executes workflows and interacts with external systems.

Supported Integration Types

Mule supports several types of integrations:

HTTP API Integration

REST API endpoints for:

  • External system communication
  • Webhook reception
  • Status queries
  • Workflow triggers
  • Agent management
  • Job creation and monitoring

The HTTP API is the primary integration mechanism for external applications. See the API documentation for details on available endpoints.

Read Article
workflows

Workflows

May 19, 2025 9 min read

Workflows are at the heart of Mule’s ability to coordinate complex AI tasks. A workflow defines a sequence of steps that Mule follows when processing issues and generating code.

Workflow Architecture

Each workflow consists of:

  • Steps: Individual tasks performed by agents or WASM modules
  • Input Mappings: How data flows between steps
  • Output Fields: What data is produced by each step
  • Job Management: Tracking and execution of workflow runs

Workflows enable you to chain together multiple agents, each with specific responsibilities, to solve complex problems collaboratively.

Read Article
wakes

Wakes

Oct 24, 2026 5 min read

A wake is Mule’s proactivity primitive: a stored condition (a cron schedule, a webhook match, an event, a job outcome) plus a target (a Mule workflow or a forge agent conversation) plus a prompt template. The wake scheduler fires due wakes automatically, so agents can act on schedules and events instead of only replying to requests.

Wakes are owner-scoped: every key can list and manage its own wakes. All endpoints require Authorization: Bearer sk_mule_<hex>.

Read Article
policy

Policy Engine

Oct 24, 2026 6 min read

The policy engine is Mule’s control plane for autonomous agent actions: versioned, owner-scoped bundles of deterministic rules that answer (agent_id, tool, input) with a synchronous verdict — allow, deny, or ask. Forge’s before_tool hook is the enforcement point, so an agent cannot run a blocked tool call; the verdict reason is written into the agent transcript.

All endpoints live under /api/v1/policies and require Authorization: Bearer sk_mule_<hex>.

Concepts

ConceptMeaning
PolicyOne row of the policies table: a scope, optional agent_id, a non-empty rules array, an enabled flag, and an auto-incremented version. Owned by an owner-scoped API key.
RuleOne deterministic decision: “when <tool> is called and <match> applies, the verdict is <disposition>.”
Verdictallow | deny | ask, plus the winning rule_id, a transcript-ready reason, and a memoized flag.
MemoA cached verdict keyed by (agent_id, action_hash) — the “human said yes/no” record for an ask round-trip.
ProposalA drafted policy an agent recorded; a human must approve it before it becomes an active policy.

Rules

A rule (the rules array of a policy) looks like:

Read Article

Related Tags

#integrations #skills #tools #websocket #api #workflows #steps #jobs #wakes #scheduler
All Tags Back to Blog