⚖ PATENT PENDING TECHNOLOGY
Operable by Claude Code · Live inventory

One prompt. One integration.
Claude Code drives the platform end-to-end.

Install the APIANT Claude Code Plugin and Claude Code gains the ability to build integrations, edit assemblies, run tests, deploy to production, write docs, and diagnose customer issues. Below is the complete inventory: 42 skills, 138 MCP tools, each one a real capability Claude can invoke on your behalf.

APIANT Claude Code Plugin v1.0.0 · build 36
40 plugin skills 127 MCP tools 3 workspaces 1 prompt → shipped integration
How it works

One plugin. Full platform access.

The APIANT Claude Code plugin ships three MCP servers and a skills library. Install it, open Claude Code, and the entire platform becomes addressable through natural language.

01 · INSTALL

apiant-setup

Run once. The plugin verifies MCP connections, env vars, and plugin version. Claude announces what's live and what's missing.

02 · PROMPT

Ask in plain English

"Build a Mindbody to Shopify sync." Claude Code picks the right skill, activates the right toolset, and starts executing with live feedback.

03 · SHIP

Built, tested, deployed

Claude composes assemblies, tests end-to-end, fixes failures, deploys to prod, and monitors the account, without handoffs.

The complete inventory

42 skills across 10 workflows.

Every skill is a procedure a senior APIANT engineer follows, encoded and executable by Claude Code. Click any card for the full what/when/how.

Setup
Verify the plugin, its MCP connections, and environment before anything else runs.
1 skill
/apiant-setup
Set up the plugin

Walk the user through installing or repairing the APIANT Claude Code plugin via the `apiant-cli` Node CLI. Use when the user says "setup", "install", "reinstall", "update plugin", or on first run.

Build
Create new automations, assemblies, integrations, and forms from a natural-language prompt.
4 skills
/build-automation
Build a new automation

Build a new APIANT automation using MCP tools. Use when the user says "build an automation", "create an automation", "connect X to Y", or describes a new workflow.

/build-assembly
Build an app assembly

Build APIANT app assemblies (API integration plumbing) using MCP tools. Use when the user says "build an assembly", "create a connector", "add an API action", or describes API integration work.

/build-integration
Build an integration suite

Build a multi-automation integration suite on APIANT. Use when the user says "build an integration", "create a two-way sync", "build a data pipeline", or any request involving multiple coordinated automations.

/build-form
Design a form

Design a form for an APIANT automation. Use when the user says "build a form", "design a form", "create a form", or describes a form they need.

Edit
Modify live automations and assemblies safely: add steps, swap apps, change endpoints, rename settings.
2 skills
/edit-automation
Edit an automation

Edit an existing APIANT automation using MCP tools. Use when the user says "edit automation", "add a step", "fix the mapping", "swap X for Y", "move step", "disable step", or describes changes to an existing automation.

/edit-assembly
Edit an assembly

Edit an existing APIANT assembly using MCP tools. Use when the user says "edit assembly", "fix the JSP", "update the API call", "change the endpoint", "rename a setting", "edit the dropdown", or describes changes to an existing assembly's code or settings.

Test & deploy
End-to-end validation, branch coverage, failure diagnosis, and dev-to-prod publication.
3 skills
/test-automation
Test an automation

Test and validate an APIANT automation end-to-end. Executes it, inspects results, diagnoses failures, applies fixes, retests, and runs branch coverage. Use when the user says "test this automation", "run a test", "why is automation X failing", or "diagnose automation X".

/test-integration
Test the whole suite

Integration test a multi-automation suite on APIANT. Verifies data flows between automations, shared state consistency, loop prevention, and cross-automation coordination. Use after building an integration suite or when the user says "test the integration end to end".

/deploy-automation
Deploy dev to prod

Publish template automations from dev to prod and deploy them to customer accounts (linked or unlinked, user's choice per deploy). Use when the user says "publish", "deploy", "push to prod", or "update customers".

Assembly triggers
Every way APIANT can start a run: polling, webhooks (three flavors), and protocol threads.
6 skills
assembly-trigger-new
NEW_ITEM polling trigger

Type-specific instructions for building a NEW_ITEM polling trigger assembly. Invoked by /build-assembly after type classification.

assembly-trigger-updated
NEW_OR_UPDATED polling

Type-specific instructions for building a NEW_OR_UPDATED polling trigger assembly. Invoked by /build-assembly after type classification.

assembly-trigger-manual-webhook
Manual webhook

Type-specific instructions for building a WEBHOOK (manual registration) trigger assembly. Invoked by /build-assembly after type classification.

assembly-trigger-self-registering-webhook
Self-registering webhook

Type-specific instructions for building a WEBHOOK_SELF_REGISTERING trigger assembly and its companion Delete webhook action. Invoked by /build-assembly after type classification.

assembly-trigger-service-webhook
Service webhook

Type-specific instructions for building a SERVICE_WEBHOOK trigger assembly (credential-based webhook URL with event filtering). Invoked by /build-assembly after type classification.

assembly-trigger-protocol-thread
Protocol thread

Type-specific instructions for building protocol thread triggers (PROTOCOL_THREAD_RECEIVER and PROTOCOL_THREAD). Invoked by /build-assembly after type classification.

Assembly actions
CRUD primitives: every API supports at least one of these. The atoms of every integration.
7 skills
assembly-action-add
ADD

Type-specific instructions for building an ADD action assembly. Invoked by /build-assembly after type classification.

assembly-action-delete
DELETE

Type-specific instructions for building a DELETE action assembly. Invoked by /build-assembly after type classification.

assembly-action-find
FIND

Type-specific instructions for building a FIND action assembly. Invoked by /build-assembly after type classification.

assembly-action-get
GET

Type-specific instructions for building a GET action assembly. Invoked by /build-assembly after type classification.

assembly-action-list
LIST

Type-specific instructions for building a LIST action assembly. Invoked by /build-assembly after type classification.

assembly-action-update
UPDATE

Type-specific instructions for building an UPDATE action assembly. Invoked by /build-assembly after type classification.

assembly-action-invoke
INVOKE

Type-specific instructions for building an INVOKE action assembly: RPC-style POST that returns rich data (AI inference, generation, computation, transformation). Invoked by /build-assembly after type classification.

Connector
The auth layer every assembly rests on, plus the tools to register and migrate.
3 skills
assembly-connector
Connector assembly

Type-specific instructions for building an app connector assembly (OAuth V2, API Key, or No Credentials). Invoked by /build-assembly during Phase 2.

/register-oauth-app
Register an OAuth app

Register an OAuth app on a vendor's developer portal by driving a browser, capturing client_id and client_secret, and storing them in the APIANT keyvault. Use when the user says "register oauth app", "get oauth credentials", "sign up for oauth", or asks to automate getting client ID/secret from a vendor like Salesforce, HubSpot, Google, etc.

/convert-assembly
Convert human to AI template

Convert a human-built APIANT assembly to the AI template pattern. Use when asm_load returns is_human_built=true, or the user says 'convert assembly', 'migrate assembly', 'convert to AI template'.

Two-way sync
Paired triggers and actions that keep two systems in sync without fighting each other.
1 skill
assembly-bidirectional-sync
Bidirectional sync

Type-specific instructions for building two-way sync (bidirectional) trigger and action assemblies. Invoked by /build-assembly after type classification.

Patterns
Reusable flow templates for common automation shapes. Loaded on demand during /build-automation.
10 skills
AI
pattern-chat-widget
Chat widget

Pattern reference for chat widget automations, from simple AI chatbots to multi-goal conversation flows with tool automations. Loaded by /build-automation when the intent involves chat widget, chatbot, chat goal, conversation memory, AI agent with tools, or multi-turn chat.

pattern-csv-mapping
CSV field mapping

Pattern reference for importing field mappings from a CSV or spreadsheet. Loaded by /build-automation when the user provides a CSV file defining how fields should map between systems.

pattern-execute-automation
Execute Automation chaining

Pattern reference for Execute Automation chaining, parent/child automations, query string parameter passing, webhook payload forwarding. Loaded by /build-automation when the intent involves executing, calling, or chaining automations.

pattern-human-moderation
Human moderation

Pattern reference for human moderation, pause an automation until a person approves or denies an item via a moderation queue link. Loaded by /build-automation when the intent involves human approval, review, moderation, decision gates, or approve/deny workflows.

pattern-latches
Fan-out / fan-in latches

Pattern reference for fan-out/fan-in automation latches, launch N child automations in parallel, wait for all to finish. Loaded by /build-automation when the intent involves parallel execution, fan-out, fan-in, or latch groups.

pattern-snooze
Snooze

Pattern reference for snoozing/pausing automations until a future datetime. Loaded by /build-automation when the intent involves snoozing, delaying, pausing, sleeping, or waiting until a specific time.

pattern-collector
Collector

Pattern reference for Collector automations, aggregate items into named buckets across executions, then drain the bucket on a schedule or trigger. Loaded by /build-automation when intent involves "aggregate", "collect over time", "daily digest", "batch", "bucket", or "send a summary email of today's items".

MCP AI
pattern-mcp-tool
MCP tool

Pattern reference for MCP tool automations, automations exposed to MCP clients (Claude Desktop, Cursor, ChatGPT MCP, etc.) as callable tools. Loaded by /build-automation when the intent involves "expose to Claude", "expose to MCP client", "MCP tool", "Model Context Protocol", or "make this callable from an AI assistant".

CSV
pattern-system-utilities
System utilities

Cookbook of small system-utility recipes, Feed (RSS/Atom/RDF), PDF generation, Datafile (daily CSV), and other one-action utilities. Loaded by /build-automation when intent matches "RSS", "Atom", "feed", "publish a feed", "monitor a news source", "generate a PDF", "PDF attachment", "log to CSV", "datafile", "daily CSV export", or "feed data into ChatGPT".

pattern-web-service
Web service

Pattern reference for web service automations, synchronous HTTP endpoints where the caller waits for a response. Loaded by /build-automation when the intent involves "expose as an HTTP endpoint", "REST API", "synchronous webhook with response", "callable from another system", or "automation that returns data to the caller".

Ops & support
Keep production healthy: monitor accounts, diagnose failures, tune alert behavior.
5 skills
/monitor-account
Monitor a customer account

Monitor a customer account's automations for execution errors on prod. Use when the user says "monitor account", "check for errors", "watch this account", or after deploying automations to a customer. Designed for recurring use via /loop.

/support
Diagnose a customer issue

Diagnose customer automation issues, halt misbehaving runs, bulk-disable an account group as an incident kill-switch (with later restore), and provision new customer accounts. Searches execution history, traces failures, extracts HTTP requests, halts runaway automations, snapshots and disables all currently-on automations across a parent account plus its linked children, then restores them after the incident. Creates new APIANT accounts for integration products via admin_create_account. Use when support says "why did X not process", "check customer Y", "what's broken", "stop this automation", "turn off all automations for X", "kill switch", "disable across parent and children", "GHL outage", "the API is choking the queue", "restore automations after the incident", "what's still disabled from incident X", "create a new account for [product]", "provision an account", "spin up an account for [integration]".

/alert-handling
Tune alert behavior

Inspect, tune, or debug how APIANT handles automation errors, retry eligibility, 401 auto-turnoff, alert message transforms, and the dismissal list. Use when the user says "alert mapping", "suppress alert", "alert rule", "noisy alerts", "why did my error message say...", "my alert isn't firing", "why didn't my automation retry", "automation got turned off with 401", "add to retryable errors", "ignore 401 for this domain", or asks why an error email was rewritten.

/docs
Answer how-to questions

Answer questions about APIANT grounded in the public documentation at info.apiant.com, how things work, how to do something, what a feature is, where to find a setting. Use when the user asks "how do I", "what is", "where is", "explain", "what does X do", or any platform question that isn't a build, test, or diagnose request.

/report-mcp-issue
Report MCP bug

File a bug report to APIANT's internal triage when you observe the MCP server itself returning wrong or broken behavior, wrong response shape, contract drift between docs and behavior, unhandled errors, schema violations, missing required fields in the response, regression on inputs that previously worked, or documented behavior that doesn't actually work. NOT for your own tool misuse, bad user input, or platform behavior that's working as designed. Autonomous, file the report immediately when you see it, don't ask the user for permission first. Use when you see "tool returned wrong shape", "schema violation", "this should work but doesn't", "contract drift", "MCP returned an unhandled error", "the tool description says X but it does Y", "the response is missing a required field", "this used to work", "documented behavior is broken", "regression in [tool]", or any time you're tempted to silently work around an MCP-layer bug instead of reporting it.

MCP tools

138 tools. 10 toolsets. Activated on demand.

Skills drive the workflow. MCP tools do the actual work against APIANT's dev, prod, and docs environments. Tools are grouped into toolsets. Only the core set is always loaded; the rest activate when a skill asks for them, so the agent's context stays lean and the capability stays deep.

Dev and prod share the same 132-tool surface. Prod is read-only by default; writes gate on explicit confirmation. Toggle any card to see the prod variant.
Core tools always loaded
The set Claude Code needs at session start to orient, pick a skill, and activate more tools as needed.
7 tools
activate_toolset
Activate a toolset

Load the specific toolset needed for the current skill. Keeps the context window lean.

asm_manage
Manage assemblies

Load, list, create, update, rename, and delete assemblies. The low-level assembly API.

auto_get_summary
Automation summary

Structured overview of an automation: triggers, steps, mappings. Fast context for edits.

auto_list
List automations

Flat list of every automation in a scope. Filter by name, folder, or status.

auto_folder
List folders

Navigate the folder tree. Find automations grouped by customer, product, or environment.

auto_manage
Manage automations

Create, rename, duplicate, move, enable, disable. Every CRUD operation for automations.

catalog_list_apps
List catalog apps

The full catalog of available app integrations. Filter by category, vendor, or capability.

On-demand toolsets lazy-loaded
Nine named toolsets activated by the skill that needs them. Keeps the context window lean while the full capability stays one call away.
10 toolsets · 138 tools
automation_builder
Build + edit

21 tools. Search the catalog, compose triggers and actions, edit mappings, commit versions, save patterns. The full automation authoring surface.

automation_exec
Runtime inspection

17 tools. Run test executions, inspect every step's input and output, mutate data, replay webhooks, walk branch-coverage test points. Debugging with full ground truth.

automation_manage
Automation lifecycle

14 tools. List and organize committed automations, version them, compare versions, roll back. The git-like layer over automation drafts and releases.

admin
Tenant ops

24 tools. Switch between customer accounts, query usage and health across a tenant, read the keyvault, run ad-hoc SQL, tune retryable errors, manage lookups. The operator's toolbox.

admin_alerts
Alert governance

6 tools. Tenant-wide alert rules, suppressed-alert lists, retry policy, 401 domain carve-outs. Requires Switch Account context.

alerts
Alert mapping

10 tools. Per-automation alert mapping rules, step-level alert triggers, mapping trace, suppression, system-level mappings.

patterns
Pattern library

3 tools. Search, save, and delete reusable pattern recipes: field mappings, transforms, gotchas, templates.

deploy
Dev to prod

7 tools. Publish folders or individual assemblies from dev to prod. Roll changes out to linked customer accounts in a single coordinated step.

assembly
Connector + assembly build

35 tools. Create connectors, inject settings, compile JSP, test API endpoints, wire dynamic field discovery, finalize assemblies. The low-level integration plumbing.

apiant-docs knowledge base
The docs workspace. Search, read, author, illustrate, and version the APIANT knowledge base.
11 tools
docs
docs_api_key
API key auth

Programmatic access. Issue a docs API key for CI/CD or automated publishing.

docs
docs_chat
Chat with docs

Retrieval-augmented Q&A. Claude asks the docs corpus before writing code or answering.

docs
docs_create
Create a page

Publish a new doc. Title, body, parent, tags, and status, in one call.

docs
docs_list
List docs

Browse the full table of contents. Filter by section, tag, or status.

docs
docs_login
Login

Authenticate the docs session. Tokens cached for the session.

docs
docs_read
Read a page

Fetch the full contents of any doc. Markdown, images, and metadata included.

docs
docs_screenshot
Capture screenshot

Take a live screenshot of the editor or platform UI and embed it into a doc.

docs
docs_search
Full-text search

Semantic + keyword search across the entire docs corpus. Ranked results with context.

docs
docs_update
Update a page

Edit title, body, tags, or status. Revisions tracked automatically.

docs
docs_upload_image
Upload image

Attach an illustration or diagram to any page. Auto-alt-text generated.

docs
docs_version
Version history

List revisions, diff between versions, roll back if needed.

Nothing matches ''

Try a shorter query, remove a filter, or clear the search.

Run log

Six minutes, one prompt, one production integration.

A SaaS team runs a boutique fitness CRM on HubSpot. Two thousand paying customers want their HubSpot contacts to sync two-way with Mindbody clients. Classic white-label integration. Historically: four to six weeks of engineering.

>Build a two-way contact sync between HubSpot and Mindbody. Handle the membership tier enum mismatch, survive Mindbody's flaky polling, and respect HubSpot's rate limits.
00:00 · Scope
T+00:03
/build-integrationClaude scopes the suite: two automations, one shared pattern.
Reads the prompt, recognizes a bidirectional sync, allocates a folder for the customer, and plans the two child automations.
tool calls
catalog_list_apps({ vertical: 'wellness' }) -> hubspot, mindbody
auto_folder({ action: 'create', path: '/customers/boutique-fit' }) -> ok
pattern_search({ shape: 'bidirectional-sync' }) -> 2 matches
00:40 · Build A
T+00:41
/build-automationDirection A: HubSpot to Mindbody.
Trigger: assembly-trigger-updated on HubSpot contacts. Action: assembly-action-find then ADD/UPDATE on Mindbody.
tool calls
auto_build({ trigger: 'assembly-trigger-updated', source: 'hubspot.contact' })
auto_edit_structure({ add_step: 'assembly-action-find', app: 'mindbody.client' })
auto_edit_structure({ add_step: 'assembly-action-add-or-update' })
auto_edit_mapping({ fields: [email, firstName, lastName, phone, membership_tier] })
Why · membership_tier enum normalization

HubSpot stores tier as a free-text dropdown. Mindbody expects one of four enum values. Claude detects the mismatch, adds a lookup-table transform, and saves it as a pattern so the reverse direction reuses it.

02:10 · Build B
T+02:12
/build-automationDirection B: Mindbody to HubSpot.
Trigger: assembly-trigger-new polling (Mindbody's webhooks are notoriously unreliable). Action: find-then-upsert on HubSpot with the shared enum pattern applied in reverse.
tool calls
auto_build({ trigger: 'assembly-trigger-new', source: 'mindbody.client', interval: '5m' })
pattern_search({ name: 'membership_tier_enum' }) -> reusing from A
auto_edit_mapping({ reverse: true, pattern: 'membership_tier_enum' })
Why · polling, not webhooks

Mindbody webhooks silently drop events during high-volume periods. Claude defaulted to polling with a 5-minute cursor, and noted this as a known-gotcha in the pattern library so future Mindbody integrations get the same treatment.

03:20 · Harden
T+03:24
/edit-assemblyRate limiter inserted on the HubSpot action.
HubSpot caps at 100 requests per 10 seconds per app. Claude inserts a sliding-window limiter at the assembly level, not the automation, so every automation that touches HubSpot inherits it.
tool calls
asm_set_action_throttle({ assembly: 'hubspot.contact.update', rate: 100, window: '10s' })
asm_set_connector_throttle({ connector: 'hubspot.v3', burst: 20 })
Why · throttle at the assembly layer

Throttling per automation would let any other HubSpot flow exhaust the budget. Throttling at the assembly (connector + action) applies the limit across every automation in the tenant, which is the only correct level for a shared API.

04:05 · Test
T+04:08
/test-integrationEnd-to-end: push from each side, verify, check for echo loops.
Creates a synthetic contact in HubSpot, watches it appear in Mindbody, edits in Mindbody, watches the update flow back. Confirms no echo loop.
tool calls
exec_test_automation({ direction: 'A', input: <synthetic> }) -> ok (1.2s)
exec_test_automation({ direction: 'B', input: <synthetic> }) -> ok (1.8s)
exec_get_assembly_log({ check: 'echo_loop' }) -> suppressed
14/14 test cases pass
05:40 · Deploy
T+05:44
/deploy-automationPublished to prod. Two thousand customer accounts linked.
Publishes the template to prod, then fans out to every linked customer account in one coordinated step.
tool calls
deploy_publish_assembly({ folder: '/customers/boutique-fit' }) -> v1.0.0
deploy_list_linked_accounts({ template: 'hubspot-mindbody-sync' }) -> 2000 accounts
deploy_to_accounts({ batch_size: 50 }) -> 2000/2000 ok
SOURCE Mindbody clients APIANT Bidirectional sync enum normalizer TARGET HubSpot contacts
0MIN
0SKILLS
0TOOL CALLS
0HUMAN EDITS

What the builder did not do: write a single line of JSP. Hand-map a single field. Open the Mindbody developer docs. File a ticket about the tier enum. Wait four to six weeks.

Diagnose a production failure

2 minutes · 2 skills · 6 tool calls
> Customer Alpine Clinic says nothing synced last night.

● /support
  searching execution history
  found 47 failures at 02:14 UTC
  root cause: Cliniko API returned 429
  (rate limit) during bulk backfill
● /edit-automation
  -> adding exponential backoff to step 3
  retested. replayed failed runs.

Alert hygiene tuneup

90 seconds · 1 skill · 4 tool calls
> Stop auto-disabling Shopify on 401s from the sandbox tenant.

● /alert-handling
  admin_ignore_401_domains += sandbox.shopify.com
  alert_suppress: 'Stale sandbox token' pattern
  verified against last 24h history
  noise dropped from 140 to 3 alerts/day
Why this is newsworthy

No other iPaaS is operable like this.

Traditional platforms wrap APIs in UI. APIANT wraps the entire platform in a Claude-Code-addressable plugin. The difference shows up everywhere.

SPEED

Minutes, not sprints

Integrations that used to take weeks ship in a single Claude Code session. Iteration is conversational.

QUALITY

Every skill is a procedure

Skills encode what senior APIANT engineers do. Claude doesn't improvise. It follows vetted playbooks with verification steps.

CONTROL

Prod is read-only by default

The plugin separates dev and prod. Claude can inspect prod freely; writes require an explicit deploy skill.

Ready to see it in your own stack?

Get access. Ship an integration this week.

The APIANT Claude Code plugin ships with an APIANT license. Tell us what you are integrating, we set you up, and Claude runs the platform from your terminal.