Integration
Connect Cursor to TWZRD Agent Intel
When Agent Pull Request Created fires in Cursor, 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 Cursor 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 Cursor can start in TWZRD Agent Intel
When Agent Pull Request Created in Cursor
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 Cursor and TWZRD Agent Intel
Triggers and actions 3 triggers · 24 actions
- Agent Pull Request Created
Triggers when the selected Cursor cloud agent opens a new GitHub pull request.
- Agent Status Equals
Triggers when a run on the chosen Cursor agent reaches the status you select, such as Finished or Error.
- New Agent
Triggered when a new Cursor cloud agent is created.
- Add Followup Instruction to Agent
Sends a follow-up instruction to an existing Cursor cloud agent, either starting a new run or steering the run in progress. Returns the new run or how the steer was delivered.
- Cancel run
Cancels the active run of a Cursor cloud agent. The run ends in the Cancelled state; start a new run to continue the conversation.
- Delete Agent
Permanently deletes a Cursor cloud agent. This cannot be undone. Returns the ID of the deleted agent.
- Find Agent Status
Looks up a Cursor cloud agent by its ID and returns its status, name, repositories, latest run and link.
- Get run
Returns the status, timestamps, duration, final reply and pushed branches for one run of a Cursor cloud agent.
- Launch Agent
Creates a Cursor cloud agent and immediately starts its first run on the task you describe. Returns the new agent and its run.
- List agents
Returns the Cursor cloud agents for the connected user, newest first, optionally filtered by pull request URL.
- List artifacts
Returns the files a Cursor cloud agent has produced, with each file's path, size and last modified time. Returns at most 100 artifacts.
- List models
Returns the recommended Cursor models you can choose from when creating an agent, including their names, aliases, parameters and variants.
- List repositories
Returns the GitHub repositories the connected Cursor user can access through Cursor's GitHub App installation.
- List runs
Returns the runs of a Cursor cloud agent, newest first, including each run's status, duration, and final reply.
- 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 Cursor
Cursor to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Cursor to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Cursor to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Cursor to Google SheetsGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Cursor to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Cursor to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
More into TWZRD Agent Intel
Questions
Cursor and TWZRD Agent Intel, answered
What can start an automation from Cursor?
Any of Cursor's 3 triggers in the catalog, including Agent Pull Request Created, New Agent and Agent Status Equals. 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 Cursor?
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 Cursor?
TWZRD Agent Intel has no triggers in the catalog today, so automations start in Cursor. 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 Cursor 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 Cursor 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.