canonical: https://jentic.com/apis/chatnode.ai/chatnode

# ChatNode API

The ChatNode API sends queries to your trained chat agents and returns their responses, with each agent addressed by its bot identifier. It lists the conversation and session IDs recorded for a bot, retrieves the messages exchanged with users, and verifies an API key. The endpoints are scoped to interacting with an already-trained agent rather than building one.

## For AI agents

Send prompts to a trained ChatNode chat agent, read its conversation history and session IDs, and verify an API key through the ChatNode API.

## Scope

Does not handle chatbot training, document uploads, or voice calls. Use for querying trained ChatNode agents and reading their conversations only.

## Capabilities

- Send a query or prompt to a trained chat agent by its bot identifier
- Retrieve the messages and conversations exchanged with a bot
- List the conversation and session IDs recorded for a bot
- Verify that an API key is valid

## Use cases

### AI Agent Query Relay

An AI agent connected through Jentic can route a user's question to a trained ChatNode agent and return its answer. The orchestrating agent passes the bot identifier and prompt, and ChatNode responds from the agent it already trained, so the workflow adds conversational answers without hosting a model itself.

Example prompt: Send a user's question to a trained agent by its bot identifier and return the agent's answer

### Conversation History Retrieval

Review past interactions by retrieving the messages and conversations recorded for a bot. ChatNode returns the exchange history so a workflow can summarize sessions or audit what the agent told users.

Example prompt: Retrieve the recent messages and conversations for a bot and summarize the main topics

### Lead and Session Export

Feed downstream systems by listing the conversation and session IDs a bot has recorded, each tied to its captured lead. ChatNode exposes these identifiers so an integration can pull sessions for CRM or analytics.

Example prompt: List the conversation and session IDs for a bot and export them for downstream processing

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/{bot_id}` | Send a query to a trained agent |
| POST | `/get-chats/{bot_id}` | Get messages and conversations for a bot |
| POST | `/get-conversation-ids/{bot_id}` | List conversation and session IDs |
| GET | `/auth_me` | Check the validity of an API key |

## Key resources

- **Agent** — Send queries to a trained agent by its bot identifier
- **Conversations** — Retrieve the messages and conversation history for a bot
- **Sessions** — List conversation and session IDs with their captured leads
- **Authentication** — Verify that an API key is valid

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 35 / 100
- **Maturity:** Non-Ready
- **Dimensions:**
  - Foundational Compliance: 100 / 100
  - Developer Experience & Jentic Compatibility: 68 / 100
  - AI-Readiness & Agent Experience: 13 / 100
  - Agent Usability: 94 / 100
  - Security: 60 / 100
  - AI Discoverability: 59 / 100
- **View full report:** https://jentic.com/apis/chatnode.ai/chatnode/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring ChatNode by hand means handling its bearer-token auth and tracking the bot-query, conversation, and session paths yourself. Through Jentic you install once, import ChatNode from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** The ChatNode surface is query and read operations, so a rule can allow your agent to query a bot and read its conversations and nothing more. You choose which operations it may call, so anything you leave out stays unavailable.
- **Credential handling:** Your ChatNode token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'query a chat agent' or 'read conversation history', and Jentic returns the matching ChatNode operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Chat Data API** — Chat Data builds chatbots on your data and serves live chat and WhatsApp.
- **OpenAI API** — OpenAI provides raw language models for generation and reasoning.
- **Cohere API** — Cohere offers language models and embeddings for retrieval and classification.

## FAQ

### What authentication does the ChatNode API use?

The ChatNode API authenticates with a bearer token sent in the Authorization header, per its OpenAPI spec, and it offers an API-key check operation so you can confirm a key is valid. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it never appears in the agent's prompt or logs.

### Can I query a trained agent with the ChatNode API?

Yes. You send a query or prompt to a trained agent by its bot identifier and receive the agent's response. The API is scoped to interacting with an agent you have already trained, not to building or retraining one.

### Can I read conversation history with the ChatNode API?

Yes. The API retrieves the messages and conversations recorded for a bot and lists the conversation and session IDs it has captured. This lets a workflow summarize sessions or export leads to another system.

### Is there a ChatNode MCP server?

You do not need an MCP server to give your agent the ChatNode API. Jentic connects it directly from the API Directory: import ChatNode, store your token once, and your agent queries bots and reads conversations through the operations the API already exposes. Operations are discovered on demand, so no extra tool definitions are loaded into the agent's context.

### Can I limit what my agent is allowed to do with the ChatNode API?

Yes. Write a rule that allows only the operations the agent needs, for example sending a query and reading conversations, so you expose just the bot interactions you intend. The agent works within those bounds, and every call it makes is logged.

### How do I query a bot through Jentic with the ChatNode API?

Search Jentic for 'query a chat agent', which returns the ChatNode operation with its input schema, then supply the bot identifier and prompt and the agent runs it. To run it on your own infrastructure, install Jentic One from its GitHub repo.