Integration
Connect Buildkite to TWZRD Agent Intel
When New build fires in Buildkite, your agent runs Check payment preflight in TWZRD Agent Intel. Describe the whole flow and it is built, tested on every scenario and kept running.
What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.
Build solutions, not workarounds.
What do you want Buildkite and TWZRD Agent Intel to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.
Set it up in your client
Claude Code
Run this in the directory you want to work in.
claude mcp add --transport http -s project apiant-ai https://mcp.apiant.aiStart Claude Code there, approve the server, and sign in in the browser page it opens.
Claude Code guide (opens in a new tab)Claude, web and desktop
Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.
Setup guide (opens in a new tab)Cursor
Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.
Setup guide (opens in a new tab)Zed
Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.
Setup guide (opens in a new tab)Codex and the ChatGPT desktop app
Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.
Setup guide (opens in a new tab)Any other MCP client
Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.
Setup guide (opens in a new tab)Example flows
What Buildkite can start in TWZRD Agent Intel
When New build in Buildkite
then Check payment preflight in TWZRD Agent Intel
Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.
Everything your agent can do with Buildkite and TWZRD Agent Intel
Triggers and actions 2 triggers · 25 actions
- Build finished
Triggers when a Buildkite build finishes (passed, failed, canceled or otherwise completed).
- New build
Triggers when a new build is scheduled in a Buildkite pipeline.
- Add annotation
Creates an annotation (a Markdown or HTML note) on a Buildkite build, optionally appending to an existing annotation with the same context.
- Add build
Creates (triggers) a new build on a Buildkite pipeline for a given commit and branch, and returns the new build.
- Add pipeline
Creates a new pipeline in a Buildkite organization from a repository and YAML steps configuration.
- Cancel build
Cancels a running or scheduled build in a Buildkite pipeline and returns the updated build.
- Delete pipeline
Permanently deletes a pipeline from your Buildkite organization.
- Get build
Returns a single build of a Buildkite pipeline by its build number, including its state, commit, jobs and pipeline details.
- Get pipeline
Returns a Buildkite pipeline's full details, including its repository, default branch, steps and build counts.
- List agents
Returns the connected and stopping agents in a Buildkite organization, optionally filtered by name, hostname, version or queue.
- List builds
Returns the builds of a Buildkite pipeline, newest first, optionally filtered by branch, commit, state, creator or date range.
- List pipelines
Returns the pipelines in a Buildkite organization, optionally filtered by pipeline name or repository URL.
- Rebuild build
Starts a new build that re-runs an existing build of a pipeline, and returns the new build.
- Update pipeline
Updates one or more settings of an existing Buildkite pipeline, such as its name, repository, YAML steps or branch filters.
- Analyze merchants for provider reputation
Batch-analyze up to 100 Solana merchant wallets for heavy-fleet concentration and captive-payer patterns, returning a reputation tier for each.
- Analyze wallets for wash trading
Batch-analyze up to 100 Solana wallets for circular payment flow, ring detection, and collusion signals.
- Check payment preflight
Get a free readiness check before paying an x402 resource, returning can_spend, trust_score, proof, caveats, and a decision for the seller about to be paid.
- Compare wallets
Get side-by-side observed intel for two Solana wallets, comparing score and counterparty breadth, before paying either one.
- Get merchant card
Get a free first-pass counterparty risk summary for a Solana seller wallet before paying, based on observed receive-side graph quality.
- List resources
List callable x402 resources from the persisted service catalog, joined to settlement-graph reputation on the receiving wallet where available.
- List sellers
List scoreable Solana receive wallets from the live settlement graph, with wash label, reputation tier, and demand shape for each.
- List top intel agents
List the leaderboard of observed x402 payers ranked by intel score, for exploring the payer corpus.
- List wallet counterparties
List the top distinct merchants or resources a Solana wallet has paid, from the observed x402 payer graph.
- List watches
List the active re-check watches registered for a payer wallet, with current score, decision, and next re-check time.
- Score wallet
Get a 0-100 intel score for a Solana wallet computed from its on-chain x402 payment history.
- Score wallets batch
Get 0-100 intel scores for up to 25 Solana wallets in one call, from their observed on-chain x402 payment history.
- Verify x402 endpoint readiness
Probe a seller's x402 payment surface (discovery docs, unpaid-402 conformance, wash screen) and get a signed receipt describing what was observed, including failures.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from Buildkite
Buildkite to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Buildkite to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Buildkite to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Buildkite to Google SheetsGoogle Sheets
Buildkite to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Buildkite to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
More into TWZRD Agent Intel
Questions
Buildkite and TWZRD Agent Intel, answered
What can start an automation from Buildkite?
Any of Buildkite's 2 triggers in the catalog, including New build and Build finished. Describe the moment in plain language and your agent picks the right one.
What can your agent do in TWZRD Agent Intel when something happens in Buildkite?
Any of TWZRD Agent Intel's 13 actions, including Analyze merchants for provider reputation, Analyze wallets for wash trading, Check payment preflight and Compare wallets. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from TWZRD Agent Intel to Buildkite?
TWZRD Agent Intel has no triggers in the catalog today, so automations start in Buildkite. If you need the other direction, ask: your agent reads TWZRD Agent Intel's API documentation and adds it.
Do I have to build a connector for Buildkite or TWZRD Agent Intel?
No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.
Can my AI client use Buildkite and TWZRD Agent Intel without building an automation?
Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.
What happens when something fails?
Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.
Is there a free plan?
Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.