# Connect Supermemory to Hermes Agent Prepare a grounded source-backed memory briefing

> Read documents with Hermes Agent and Agent200. Prepare a source-backed memory briefing within the configured Supermemory account scope.

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

## Instructions for AI agents

Goal: connect Supermemory to Hermes Agent with Agent200, through its MCP server.
Guide: https://www.agent200.com/connectors/supermemory/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 Supermemory 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 Supermemory document I identify and prepare a source-backed memory briefing. Name the source and use only document content, source and container tags. State access gaps; do not change records."
   What should come back:
   - The selected document is identified.
   - Only the returned document content, source and container tags 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 document read, not guesses from catalogue labels.

Start with one identified document. Preserve returned document content, source and container tags; report missing data and keep the workflow read-only.

Provider reference: [Supermemory API](https://api.supermemory.ai/reference).

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

- **Connector:** [Supermemory](https://www.agent200.com/connectors/supermemory/)
- **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:** [4 tools](https://www.agent200.com/connectors/supermemory/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.
- **Supermemory 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 Supermemory 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 Supermemory 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 Supermemory document I identify and prepare a source-backed memory briefing. Name the source and use only document content, source and container tags. State access gaps; do not change records."

What should come back:

- The selected document is identified.
- Only the returned document content, source and container tags are reported.
- Access gaps and missing context are explicit; no source data is changed.

Check the selected document ID, account scope, read permission and pagination. A semantic match is not proof of complete recall. Name returned sources and container scope, and allow for indexing or processing lag.

## Supermemory tools Hermes Agent can call

- **Search documents** (`supermemory_search_documents`, read): Search indexed documents within a specified container.
- **Read a document** (`supermemory_get_document`, read): Retrieve one identified document when available.
- **List documents** (`supermemory_list_documents`, read): Find indexed documents in the key’s scope.
- **Search memories** (`supermemory_search_memories`, read): Search generated memories with source references.

## How it works

1. **You ask Hermes Agent.** In your own words, for something in Supermemory.
2. **Hermes Agent picks a tool.** It sees the Supermemory tools on the Agent200 MCP server and calls the one the request needs.
3. **Agent200 runs the call.** It reaches Supermemory 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 document ID, account scope, read permission and pagination. A semantic match is not proof of complete recall. Name returned sources and container scope, and allow for indexing or processing lag.

## FAQ

### How do I verify this result?

Compare the named document and returned document content, source and container tags with the source. Treat missing information as missing, not as a fact.

## Use Supermemory with another framework

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

---

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