How to integrate HydraDB MCP with Atomic Agent

Connect Atomic Agent to HydraDB MCP. Query hydradb for recent customer complaint trends, ingest product documentation into hydradb context, and more using natural language, with authentication handled for you.

HydraDB logoHydraDB
Api Key

HydraDB is a hosted context layer for ingesting, connecting, and querying data for AI applications. It helps teams give AI systems organized, searchable context from their data.

43 Tools

Introduction

Atomic Agent is an open-source AI agent that runs on your machine and supports local models through llama.cpp. Connect it to 1,700+ apps through Composio, including HydraDB.

This guide uses Atomic Agent's built-in Composio integration. You need Atomic Agent v0.5.6 or later, your own Composio API key, and a HydraDB account. See the Atomic Agent documentation for installation instructions.

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate HydraDB with

How Atomic Agent connects to HydraDB

Atomic Agent connects to Composio's Tool Router over Streamable HTTP MCP. It discovers the tools needed for your request, and Composio handles account authentication.

Execution and account-connection tools follow Atomic Agent's configured approval policy. Review any approval prompt before allowing an action on your connected account.

Connect HydraDB to Atomic Agent

  1. Sign up or sign in to the Composio dashboard. Copy your API key.
  2. In Atomic Agent, open the Integrations tab and select Composio. Select API key, press e, paste the key, and press Enter. The tools become available immediately, without a restart.
  3. Ask Atomic Agent to do something in HydraDB. It searches Composio for the right tool.
  4. On first use, open the sign-in link returned in the chat. Connect your HydraDB account, then return to Atomic Agent to continue.

Headless setup

Add the following line to ~/.atomic-agent/.env, replacing YOUR_COMPOSIO_API_KEY with your key. Start Atomic Agent after saving the file.

bash
COMPOSIO_API_KEY=YOUR_COMPOSIO_API_KEY

What is the HydraDB MCP server, and what's possible with it?

The HydraDB MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your HydraDB account. It provides structured and secure access to your databases, collections, connected data sources, contexts, and indexing workflows, so your agent can ingest data, search knowledge, manage connected providers, explore relationships, and monitor processing on your behalf.

  • Knowledge ingestion and search: Have your agent add documents, application knowledge, memories, or graph data to HydraDB, then query the resulting context with filters for collections, metadata, sources, access controls, and retrieval settings.
  • Database and collection management: Let the agent create, inspect, list, and remove HydraDB databases and collections, check database readiness, review usage statistics, and manage metadata schema fields.
  • Connected data source management: Direct your agent to review supported connector providers, create and configure connectors, discover available resources, select resources for syncing, pause or resume connectors, trigger syncs, and check connector health.
  • Context exploration and processing: Instruct your agent to inspect stored context, check ingestion status, list knowledge or memory contexts, retrieve extracted relations, and traverse related context subgraphs.
  • Indexing webhook operations: Have your agent register and test indexing webhooks, manage signing secrets, review delivery attempts, retry failed deliveries, and remove webhook registrations.

Use HydraDB from Atomic Agent

With your account connected, ask Atomic Agent to work with HydraDB in natural language. You can connect more apps through the same Composio integration as you need them.

Visit the Atomic Agent website or inspect the Atomic Agent source code.

Troubleshooting

Why is my API key rejected?

Copy the key directly from the Composio dashboard. Atomic Agent requires ASCII characters because it sends the key in an HTTP header. Remove any extra characters introduced when copying.

Why are Composio tools unavailable after saving a key?

Check that you use Atomic Agent v0.5.6 or later and that Composio is enabled in your configuration. A "composio": { "enabled": false } setting disables the integration while keeping the saved key on disk.

Does Composio have a free plan?

The Hobby plan includes 100,000 tool calls per month. Composio-managed OAuth apps have a lower included allowance. See Composio pricing for the current limits that apply to your connection.

TOOLS

Supported Tools

Every HydraDB action and event your agent gets out of the box.

Add Connector Resource

Add one discovered provider resource to an existing connector with optional routing, filters, metadata, instructions, and access control.

Add Metadata Schema Fields

Add new fields to a database metadata schema; existing fields cannot be deleted, renamed, retyped, or reconfigured.

Configure Connector Resources

Activate selected discovered resources on a connector and start their sync; unlisted existing resources remain unchanged.

Create Connector

Create a HydraDB connector and store the provider authorization required to sync one external account.

Create Database

Provision a HydraDB database asynchronously.

Delete Collection

Permanently delete one HydraDB collection and all of its data while leaving the database intact.

Delete Connector

Permanently delete a HydraDB connector, all resource mappings, and its stored provider authorization.

Delete Connector Resource

Permanently remove one resource mapping from a HydraDB connector.

Delete Context

Permanently delete specific HydraDB knowledge or memory contexts.

Delete Database

Permanently delete a HydraDB database and all associated data.

Delete Indexing Webhook

Unregister the account's indexing webhook and stop all future event deliveries.

Disable Webhook Signing

Remove the indexing webhook signing secret.

Discover Connector Resources

List resources available through an existing connector's stored provider credentials.

Generate or Set Webhook Signing Secret

Generate or set and replace the indexing webhook signing secret.

Get Connector

Get one connector's configuration and lifecycle state by connector ID.

Get Connector Status

Check a connector's overall health, sync state, errors, and per-resource health in one call.

Get Context Relations

Return extracted entity relations for one context or an entire collection, one page at a time.

Get Context Status

Check processing status for one or more ingested or connector-synced context IDs.

Get Context Subgraph

Traverse context-level relations from one context and return reachable contexts and graph evidence up to bounded depth and size.

Get Database Stats

Get knowledge and memory collection row counts for one database.

Get Database Status

Check whether one database's scheduler, graph, and vector infrastructure is ready for ingestion.

Get Indexing Webhook

Get the account's indexing webhook URL, subscribed event types, registration state, and whether signing is configured.

Get Metadata Schema

Get the declared metadata fields and types for one database.

Get Webhook Delivery

Get one indexing webhook delivery attempt by delivery ID for failure diagnosis.

Ingest Context

Ingest documents, app knowledge, memories, or an explicit graph into a HydraDB database and return context IDs for asynchronous status checks.

Inspect Context

Fetch one context's stored content, enrichment, and/or a time-limited download URL.

List Collections

List the collections in one HydraDB database.

List Connector Providers

List supported connector providers, or describe one provider's resource types, credential schema, and setup requirements.

List Connector Resources

List the resources currently configured on a connector, including routing, filters, access controls, and per-resource health metadata.

List Connectors

List the connected data providers in the account, optionally filtered by provider, with optional health rollups.

List Contexts

List knowledge or memory contexts in a database or collection, one bounded page at a time.

List Databases

List HydraDB databases and preserve per-database provisioning or failure diagnostics.

List Webhook Deliveries

List recent indexing webhook delivery attempts, optionally filtered by status, one page at a time.

Query Context

Search a HydraDB database for ranked chunks and graph context, with optional collection, metadata, source, ACL, and retrieval controls.

Register Indexing Webhook

Register or replace the organization's HTTPS endpoint and event subscriptions for HydraDB indexing events.

Retry Webhook Delivery

Queue one failed indexing webhook delivery for another attempt.

Set Connector Paused State

Pause scheduled syncs or resume a paused HydraDB connector.

Submit Query Feedback

Record a rating, comment, or known ground truth for a prior HydraDB query.

Test Indexing Webhook

Send one test event to the currently registered indexing webhook endpoint.

Trigger Connector Sync

Start a connector sync now, causing external provider reads and HydraDB ingestion.

Update Connector

Update an existing HydraDB connector's sync cadence, default ingestion instructions, or provider credentials.

Update Connector Resource

Replace a HydraDB connector resource's access rules or change its ingestion instructions for subsequent syncs.

Update Context Metadata

Merge metadata into one HydraDB context or replace its access-control list without re-ingesting content.

FAQ

Frequently asked questions

Start with HydraDB.It takes 30 seconds.

Managed auth, hosted MCP servers, and every HydraDB tool your agent needs.Free to start.

Start building