Claude Code

Claude Code is Anthropic’s AI coding agent that runs in your terminal. NeuralRepo integrates with Claude Code through two complementary methods: the MCP remote connector for conversational access and the nrepo CLI for direct commands.

Method 1: MCP Remote Connector

The MCP connector gives Claude Code direct access to all eight NeuralRepo tools — save, search, update, delete, get, list tags, link, and unlink.

Setup

claude mcp add --transport http neuralrepo https://neuralrepo.com/mcp/

On your next Claude Code session, NeuralRepo tools are available. The first time Claude uses a tool, you will be prompted to authorize via OAuth.

Verify the connection:

claude mcp list

You should see neuralrepo listed with a status of connected or pending auth.

Using MCP in Claude Code

Once connected, you can ask Claude Code to interact with your ideas naturally:

“Search my NeuralRepo for ideas about authentication”
“Save this project concept as an idea tagged with api and v2”
“Get idea 42 with full context and use it as the spec for this project”
“Update idea 42 to status building”

Method 2: nrepo CLI

The CLI provides direct command-line access to your NeuralRepo, which Claude Code can invoke as shell commands.

Setup

Install the CLI globally:
Terminal window
```
npm install -g @neuralconfig/nrepo
```
Authenticate:
Terminal window
```
nrepo auth login
```
This opens a browser window for OAuth. Your session token is stored locally.

Key Commands for Claude Code Workflows

# Search ideas
nrepo search "authentication flow"

# Pull an idea into the current project directory
nrepo pull 42 --to ./

# Push a new idea from a file
nrepo push "API redesign" --body "$(cat ./notes.md)" --tag api --tag v2

# Update status
nrepo move 42 building

# View the idea graph
nrepo graph 42

Recommended Workflow

The most productive pattern combines both methods:

Search for context. Ask Claude Code to search NeuralRepo via MCP: “Do I have any ideas about a CLI dashboard?”
Pull the idea locally. Use the CLI to bring the full idea into your project:
Terminal window
```
nrepo pull 42 --to ./my-project
```
This creates a markdown file with the idea title, body, tags, and related ideas.
Build with context. Claude Code can read the pulled file and use it as a specification for implementation.
Update status. When you start building, update the idea:
Terminal window
```
nrepo move 42 building
```
Ship and close. When deployed, mark it done:
Terminal window
```
nrepo move 42 shipped
```

Example Conversation

You: Search my NeuralRepo for ideas about a REST API rate limiter

Claude Code: [calls search_ideas with query "REST API rate limiter"]
I found 2 relevant ideas:
  - #38: "Token bucket rate limiter for API" (exploring)
  - #41: "Sliding window rate limit with Redis" (captured)

You: Pull idea 38 into this project

Claude Code: [runs: nrepo pull 38 --to ./]
Done. Created ./idea-38-token-bucket-rate-limiter.md

You: Read that file and implement the rate limiter based on the spec

Claude Code: [reads the file, implements the rate limiter]
I've implemented a token bucket rate limiter based on your idea spec...

You: Update idea 38 to building status

Claude Code: [calls update_idea with id=38, status="building"]
Updated idea #38 to "building" status.

The /neuralrepo Skill

If the /neuralrepo slash command is available in your Claude Code environment, it provides a shortcut for common operations. Type /neuralrepo followed by your request:

/neuralrepo search authentication ideas
/neuralrepo pull 42
/neuralrepo status 42 shipped

This invokes the appropriate MCP tool or CLI command automatically.

Next Steps

MCP Server Reference Full documentation for all 8 MCP tools with parameter tables and examples.

Idea to Project Workflow End-to-end guide for turning a captured idea into a shipped project.