MCP integration

Your coding agent forgets your codebase every time you close the tab.

You spent 20 minutes explaining your project to Claude. Tomorrow it won't remember any of it. The Hebbrix MCP server fixes that for good. Set it up once, and your agent keeps your architecture decisions, conventions, bug fixes, and project context across every session.

Works with Claude Desktop, Cline, Cursor, and any MCP-compatible agent.

Setup guide →Optional API account

one-time setup

Under 30 seconds, then you're done

Add the hosted endpoint to your MCP client and reconnect. There is no server to install and guest access needs no Hebbrix account or API key.

Open your MCP client settings

Open the MCP server configuration in Claude Desktop, Cursor, Cline, or another MCP-compatible client.

Add the hosted endpoint

Set https://mcp.hebbrix.com/mcp as the server URL. Save and reconnect.

Start using persistent memory

Tell it something worth remembering, search it later, inspect its graph, or record an action and report its outcome.

claude_desktop_config.json

{
  "mcpServers": {
    "hebbrix": {
      "url": "https://mcp.hebbrix.com/mcp"
    }
  }
}

# Save and reconnect. No account, API key,
# local process, or package install required.
# Your agent now has persistent memory.

33 live tools

What your agent can do now

Thirty-three tools make Hebbrix a persistent learning layer: memory, temporal graph, grounded reasoning, procedures, account workflows, and Outcome Memory. Four representative entry points are shown below.

hebbrix_remember

Remember anything from the conversation

"Remember that we use PostgreSQL with Prisma ORM, and all API routes go through the auth middleware." Your agent stores this, and it's still there next week and next month.

hebbrix_ask

Answer from memory and temporal graph evidence

"Who manages Orion now, and what database does it use?" One tool combines memory retrieval, graph evidence, and a grounded answer.

hebbrix_graph_query

Query relationships and truth over time

Traverse entities and relationships, inspect timelines, and distinguish current facts from superseded history.

hebbrix_choose_action

Choose from measured action outcomes

Record a decision receipt with candidates and propensity, then report delayed outcomes so future choices use evidence and uncertainty.

a week with memory

What it actually feels like

When your coding agent remembers your project, conversations stop repeating themselves.

A Cursor chat where the agent uses a Hebbrix MCP tool to recall a stored architecture decision

Monday

You explain your auth architecture

JWT tokens, refresh rotation, middleware validation. The agent stores the whole pattern, not a summary, including the specific decisions and why you made them.

Wednesday

New protected endpoint, no explanation needed

You ask Claude to add a new route. Without you saying anything, it uses your JWT pattern, adds the middleware, and follows your error handling style, because it already knows it.

Friday

A bug. Claude already knows where to look.

Auth issue. Claude remembers Monday's implementation, including the quirk where the token refresh overlaps with rate limiting. It finds the bug in seconds instead of hours.

Next week

New sprint, same context

New conversation, same agent brain. It knows your bug fix, your auth pattern, your team's coding style, and your deployment process. It picks up right where you left off.

Give your coding agent a memory it keeps

One hosted URL. Under 30 seconds. No account required.

Setup guide →Optional API account