Build solutions, not workarounds.
What do you want finlight and Orq Ai to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiAny 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 finlight can start in Orq Ai
When New Article in finlight
then Add agent in Orq Ai
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 finlight and Orq Ai
Triggers and actions 1 trigger · 24 actions
- New Article
Triggered when a new article is published that matches the filters you set.
- Get article by link
Fetches one news article from finlight by its web address, returning the headline, summary, publication date, sentiment and the rest of the article record.
- List sources
Lists the news sources finlight covers, with each source's domain, home country and publication languages.
- Search Recent Articles
Returns recent news articles matching your search words, sources, tickers, countries, categories and date range.
- Add agent
Create a new managed agent.
- Add datapoint
Adds a datapoint (inputs, conversation messages and an expected output) to an Orq.ai dataset.
- Add dataset
Creates a new dataset in the specified Orq.ai project.
- Add evaluator
Create a new evaluator.
- Add prompt
Creates a new prompt in the Orq.ai workspace.
- Add tool
Creates a new tool (function, JSON schema, HTTP or Python code tool) in the Orq.ai workspace.
- Delete datapoint
Permanently deletes a specific datapoint from a dataset.
- Delete dataset
Permanently deletes a dataset and all its datapoints. This cannot be undone.
- Delete prompt
Delete a prompt and all its versions by ID.
- Get dataset
Retrieves a specific dataset by its unique identifier.
- Get prompt
Retrieves a prompt by its id, including its model configuration, messages and metadata.
- Invoke deployment
Run a deployed prompt/model configuration and get the generation result.
- List agents
Lists all agents in the Orq.ai workspace with their full configuration, newest first.
- List datapoints
Retrieves a list of datapoints from a specific dataset.
- List datasets
Lists datasets in the current Orq workspace, optionally filtered by display name or last updater.
- List deployments
Returns the workspace's deployments, most recently created first.
- List evaluators
Lists evaluators in the Orq.ai workspace, optionally filtered by search text or project. Returns up to 200 evaluators.
- List prompts
Returns the prompts in the workspace, most recently created first.
- List tools
Lists every tool in the Orq.ai workspace (function, JSON schema, HTTP and code execution tools).
- Update dataset
Update a dataset's name/config.
- Update prompt
Update an existing Orq.ai prompt's name, description, model configuration, metadata or storage path. Only the fields you fill in are changed.
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 finlight
finlight to MagileadsMagileads is an marketing automation application to create list of contacts and engage campaigns.
finlight to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
finlight to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
finlight to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
finlight to Google SheetsGoogle Sheets
finlight to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
More into Orq Ai
Google Calendar to Orq AiGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Questions
finlight and Orq Ai, answered
What can start an automation from finlight?
Any of finlight's 1 trigger in the catalog, including New Article. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Orq Ai when something happens in finlight?
Any of Orq Ai's 21 actions, including Update dataset, Update prompt, Add agent and Add datapoint. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Orq Ai to finlight?
Orq Ai has no triggers in the catalog today, so automations start in finlight. If you need the other direction, ask: your agent reads Orq Ai's API documentation and adds it.
Do I have to build a connector for finlight or Orq Ai?
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.
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.