# Connect Docparser to Agent Toolbelt

When **Parsed Document Data Available** fires in [Docparser](https://apiant.ai/connections/docparser), your agent runs **Extract text data** in [Agent Toolbelt](https://apiant.ai/connections/agent-toolbelt). Describe the whole flow and it is built, tested on every scenario and kept running.

Docparser **2** triggers Docparser **2** actions Agent Toolbelt **9** actions

What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.

## What do you want Docparser and Agent Toolbelt to do together?

Give your AI client this address.

`https://mcp.apiant.ai`

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.ai`

Start Claude Code there, approve the server, and sign in in the browser page it opens.

[Claude Code guide (opens in a new tab)](https://apiant.ai/docs/mcp/claude-code)

### 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)](https://apiant.ai/docs/mcp)

### 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)](https://apiant.ai/docs/mcp)

### Zed

Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### 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)](https://apiant.ai/docs/mcp)

### 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)](https://apiant.ai/docs/mcp)

Example flows

## What Docparser can start in Agent Toolbelt

- When **Parsed Document Data Available** in Docparser then **Extract text data** in Agent Toolbelt
- When **Parsed Table Row Available** in Docparser then **Compare stocks** in Agent Toolbelt

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 Docparser and Agent Toolbelt

## Triggers and actions 2 triggers · 11 actions

- Trigger

**Parsed Document Data Available**

Triggers whenever a new Document is processed and parsed data is available.

- Trigger

**Parsed Table Row Available**

Triggers whenever a new Document is processed and parsed table rows are available.

- Action

**Fetch Document From URL**

Fetches a new document from a publicly accessible URL and imports it into Docparser to begin parsing. (To receive the parsing results, you'll need a separate Zap listening for the "New Parsed Data Available" Trigger).

- Action

**Upload Document**

Uploads a new document to Docparser which will immediately begin parsing after reception. (To receive the parsing results, you'll need a separate Zap listening for the "New Parsed Data Available" Trigger).

- Action

**Compare stocks**

/api/tools/compare-stocks. Head-to-head comparison of 2-3 tickers.

- Action

**Count tokens**

/api/tools/token-counter {text, models}. Token counts across LLMs.

- Action

**Extract text data**

/api/tools/text-extractor. Extracts structured data from raw text.

- Action

**Generate bull vs bear case**

/api/tools/bear-vs-bull {ticker}. Steelmanned bull and bear cases.

- Action

**Generate stock thesis**

/api/tools/stock-thesis {ticker}. Returns verdict, thesis, insider read, watch-for.

- Action

**Get valuation snapshot**

/api/tools/valuation-snapshot {ticker}. Valuation verdict and buy zone.

- Action

**Normalize address**

/api/tools/address-normalizer. Normalizes a US address to USPS format.

- Action

**Review portfolio**

/api/tools/portfolio-review. Reviews held portfolio.

- Action

**Scan watchlist**

/api/tools/watchlist-scan. Ranks a watchlist of 2-15 tickers.

## Each app on its own

- [ **Docparser** Docparser converts your PDF documents into structured and easy-to-handle data.](https://apiant.ai/connections/docparser)
- [ **Agent Toolbelt** AI-generated stock analysis (investment thesis, valuation, insider signal, earnings) from live fundamentals...](https://apiant.ai/connections/agent-toolbelt)

Reviews

## What our customers say

## More from Docparser

- [ **Docparser to Prismix** Real-time uptime for 77 AI APIs (OpenAI, Anthropic, Cursor, Gemini) — free JSON endpoint, no auth required](https://apiant.ai/connect/docparser-to-prismix)
- [ **Docparser to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/docparser-to-hubspot)
- [ **Docparser to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/docparser-to-salesforce)
- [ **Docparser to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/docparser-to-slack)
- [ **Docparser to Google Sheets** Google Sheets](https://apiant.ai/connect/docparser-to-google-sheets)
- [ **Docparser to Gmail** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/docparser-to-gmail)

## More into Agent Toolbelt

- [ **Ontraport to Agent Toolbelt** Ontraport is an all-in-one CRM, marketing automation, and e-commerce platform.](https://apiant.ai/connect/ontraport-to-agent-toolbelt)
- [ **HubSpot to Agent Toolbelt** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-agent-toolbelt)
- [ **Salesforce to Agent Toolbelt** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-agent-toolbelt)
- [ **Slack to Agent Toolbelt** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-agent-toolbelt)
- [ **Google Sheets to Agent Toolbelt** Google Sheets](https://apiant.ai/connect/google-sheets-to-agent-toolbelt)
- [ **Gmail to Agent Toolbelt** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-agent-toolbelt)

Questions

## Docparser and Agent Toolbelt, answered

###

### What can start an automation from Docparser?

Any of Docparser's 2 triggers in the catalog, including Parsed Document Data Available and Parsed Table Row Available. Describe the moment in plain language and your agent picks the right one.

###

### What can your agent do in Agent Toolbelt when something happens in Docparser?

Any of Agent Toolbelt's 9 actions, including Compare stocks, Count tokens, Extract text data and Generate bull vs bear case. Your agent maps the data both ways and tests every scenario before it ships.

###

### Can it also run from Agent Toolbelt to Docparser?

Agent Toolbelt has no triggers in the catalog today, so automations start in Docparser. If you need the other direction, ask: your agent reads Agent Toolbelt's API documentation and adds it.

###

### Do I have to build a connector for Docparser or Agent Toolbelt?

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.
