# Connect Tally to Hermes Agent Prepare a grounded submission review briefing

> Read forms with Hermes Agent and Agent200. Prepare a submission review briefing within the configured Tally account scope.

- Page: https://www.agent200.com/connectors/tally/framework/hermes-agent/
- Connector: [Tally](https://www.agent200.com/connectors/tally.md)
- Framework: Hermes Agent
- Updated: 2026-11-17

## Instructions for AI agents

Goal: connect Tally to Hermes Agent with Agent200, through its MCP server.
Guide: https://www.agent200.com/connectors/tally/framework/hermes-agent/

1. The user needs an Agent200 API key. If they have none, send them to https://agent200.com/platform/apikeys/ to choose "Create an API key". They paste it into Hermes Agent's settings themselves: never ask for it in chat and never write it into files you share.
2. Make sure Tally is enabled for their project in the Agent200 dashboard (Connectors), with the tools the task needs.
3. Add Agent200's MCP server to Hermes Agent: URL https://api.agent200.com/mcp/, transport streamable HTTP, header "Authorization: Bearer <the user's Agent200 API key>". Follow the setup steps on the guide page for Hermes Agent's exact menus or commands.
4. Check it works with this request: "Read the Tally form I identify and prepare a submission review briefing. Name the source and use only form, question, submission and answer fields. State access gaps; do not change records."
   What should come back:
   - The selected form is identified.
   - Only the returned form, question, submission and answer fields are reported.
   - Access gaps and missing context are explicit; no source data is changed.
5. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard, then retry.

## Overview

Inspect the Agent200 tools Hermes advertises after connection. Use discovered names and input schemas for the form read, not guesses from catalogue labels.

Start with one identified form. Preserve returned form, question, submission and answer fields; report missing data and keep the workflow read-only.

Provider reference: [Tally API](https://developers.tally.so/api-reference/introduction).

Use the provider credential described on the Tally parent page. Keep it in secure configuration and verify the selected tenant or account before reading.

- **Connector:** [Tally](https://www.agent200.com/connectors/tally/)
- **Works with:** Hermes Agent · Agent app, through MCP
- **Authentication:** Your Agent200 API key
- **You need:** [An Agent200 API key](https://agent200.com/platform/apikeys/)
- **Tools:** [5 tools](https://www.agent200.com/connectors/tally/framework/hermes-agent/#tools)
- **MCP server:** `https://api.agent200.com/mcp/`

## Before you start

- **An Agent200 API key.** Create one on the [API keys page](https://agent200.com/platform/apikeys/) of the dashboard.
- **Tally enabled for your project.** In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- **Hermes Agent, with custom MCP servers allowed.** Hermes Agent is open source and self-hosted: anyone running it can add MCP servers in its config file.

## Connect Tally to Hermes Agent

### Step 1: Create your Agent200 API key

Open the API keys page in the Agent200 dashboard and choose Create an API key. You add it to Hermes Agent in the next step, as "Authorization: Bearer <your key>". One key covers Tally and every other connector enabled for your project. Keep it out of chats and source control.

Create an API key: https://agent200.com/platform/apikeys/

### Step 2: Store your key in ~/.hermes/.env

Keep the key out of `config.yaml`: Hermes reads it from `~/.hermes/.env`.

File `~/.hermes/.env`:

```bash
AGENT200_API_KEY=your-agent200-api-key
```

### Step 3: Add the server to ~/.hermes/config.yaml

Add an entry under `mcp_servers` with the URL and the Authorization header. Do not set `transport: sse`: Agent200 serves streamable HTTP.

File `~/.hermes/config.yaml`:

```text
mcp_servers:
  agent200:
    url: "https://api.agent200.com/mcp/"
    headers:
      Authorization: "Bearer ${AGENT200_API_KEY}"
```

### Step 4: Reload and test

In a running session, run `/reload-mcp`, or restart Hermes. Then check what the server returned from a terminal.

File `Terminal`:

```bash
# In a running Hermes session: /reload-mcp
hermes mcp test agent200
hermes mcp list
```

## Test your connection

Ask: "Read the Tally form I identify and prepare a submission review briefing. Name the source and use only form, question, submission and answer fields. State access gaps; do not change records."

What should come back:

- The selected form is identified.
- Only the returned form, question, submission and answer fields are reported.
- Access gaps and missing context are explicit; no source data is changed.

Check the selected form ID, account scope, read permission and pagination. Submission pages expose hasMore and total. Follow them before claiming a count; treat answers as personal data where applicable.

## Tally tools Hermes Agent can call

- **List forms** (`tally_list_forms`, read): Find forms visible to the API token.
- **Read a form** (`tally_get_form`, read): Retrieve one identified form.
- **List questions** (`tally_list_questions`, read): Read question definitions for a selected form.
- **List submissions** (`tally_list_submissions`, read): Find submissions with supported filters and pagination.
- **Read a submission** (`tally_get_submission`, read): Retrieve one identified submission.

## How it works

1. **You ask Hermes Agent.** In your own words, for something in Tally.
2. **Hermes Agent picks a tool.** It sees the Tally tools on the Agent200 MCP server and calls the one the request needs.
3. **Agent200 runs the call.** It reaches Tally with your Agent200 API key, within the endpoints your project allows.
4. **Hermes Agent answers.** It gets the result back from the MCP server and uses it in its reply or its next step.

**Permissions at every level.** Your project settings decide which services and endpoints the agent may use.

## Troubleshooting

### The source cannot be read

Check the selected form ID, account scope, read permission and pagination. Submission pages expose hasMore and total. Follow them before claiming a count; treat answers as personal data where applicable.

## FAQ

### How do I verify this result?

Compare the named form and returned form, question, submission and answer fields with the source. Treat missing information as missing, not as a fact.

## Use Tally with another framework

- [Tally + Claude](https://www.agent200.com/connectors/tally/framework/claude.md)
- [Tally + ChatGPT](https://www.agent200.com/connectors/tally/framework/chatgpt.md)
- [Tally + Claude Code](https://www.agent200.com/connectors/tally/framework/claude-code.md)
- [Tally + Muse](https://www.agent200.com/connectors/tally/framework/muse.md)
- [Tally + Grok Bot](https://www.agent200.com/connectors/tally/framework/grok-bot.md)
- [Tally + OpenAI Dots](https://www.agent200.com/connectors/tally/framework/openai-dots.md)
- [Tally + Claude Duet](https://www.agent200.com/connectors/tally/framework/claude-duet.md)
- [Tally + OpenClaw](https://www.agent200.com/connectors/tally/framework/openclaw.md)

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
