Model Context Protocol (MCP)

Enable AI assistants like Claude to query your Scrapalot knowledge base directly. MCP integration lets you ask questions about your documents during AI conversations.

What is MCP?

Model Context Protocol allows AI assistants to access external context sources, including your Scrapalot documents.

Benefits:

Ask Claude to search your documents during conversations
Get answers with citations from your knowledge base
Seamless integration with AI development tools
Real-time document access

Use Cases

Development with Claude

Scenario: Working with Claude Desktop on a coding project

With MCP:

Ask Claude: "Search my Scrapalot docs for the authentication setup"
Claude queries your knowledge base
Gets relevant context and citations
Provides answer based on your documents

Without MCP:

Manually search your documents
Copy relevant sections
Paste into Claude conversation
Ask question again

Documentation Research

Scenario: Researching across multiple document sets

With MCP:

"Find all mentions of deployment in my technical docs"
"What does my security policy say about data retention?"
"Search my meeting notes for decisions about the new feature"

Setup Guide

Prerequisites

Scrapalot running on http://localhost:8090 or your server
Documents uploaded to at least one collection
MCP-compatible client (Claude Desktop recommended)

Configuration

For Claude Desktop:

Edit your Claude Desktop config file:

macOS:

bash

~/Library/Application Support/Claude/claude_desktop_config.json

Windows:

bash

%APPDATA%\Claude\claude_desktop_config.json

Add Scrapalot MCP server:

json

{
  "mcpServers": {
    "scrapalot": {
      "command": "scrapalot-mcp",
      "args": ["--api-url", "http://localhost:8090"],
      "env": {
        "SCRAPALOT_API_KEY": "your-api-key-here"
      }
    }
  }
}

Getting Your API Key

Log into Scrapalot
Go to Settings → API Keys
Create new API key
Copy key to configuration
Restart Claude Desktop

Using MCP with Claude

Basic Queries

Ask Claude to search your docs:

Can you search my Scrapalot documents for information about deployment?

Specify a collection:

Search the "Technical Docs" collection for authentication setup

Get specific information:

Find the deployment checklist in my documents

Advanced Queries

Multi-collection search:

Search both "API Docs" and "User Guides" for rate limiting information

Semantic search:

Find documents related to security best practices

Follow-up questions:

Based on what you found, what's the recommended approach?

Available Operations

Search Documents

Query your knowledge base

Parameters:

Query text (required)
Collection ID (optional)
Max results (optional, default: 5)

Returns:

Relevant document chunks
Source document names
Relevance scores
Citations

List Collections

See available document collections

Parameters: None

Returns:

Collection names and IDs
Document counts
Creation dates

Troubleshooting

MCP Server Not Responding

Check Scrapalot is running:

bash

curl http://localhost:8090/health

Verify MCP endpoint:

bash

curl http://localhost:8090/mcp/collections

Review Claude Desktop logs:

macOS: ~/Library/Logs/Claude/mcp.log
Windows: %APPDATA%\Claude\Logs\mcp.log

Authentication Errors

Verify API key:

Check key in config is correct
Ensure key hasn't expired
Test key with direct API call:

bash

curl -H "Authorization: Bearer YOUR_KEY" \
     http://localhost:8090/api/v1/collections

If key invalid:

Generate new API key in Scrapalot
Update config file
Restart Claude Desktop

No Results Returned

Common causes:

Collection has no documents
Query doesn't match content
API key lacks collection access
Max results set too low

Solutions:

Verify documents in collection
Try broader search terms
Check permissions
Increase max_results parameter

Connection Refused

Check firewall:

Ensure port 8090 accessible
Allow localhost connections
Check network settings

Verify Scrapalot running:

bash

# Check process
ps aux | grep scrapalot

# Check port
lsof -i :8090

Best Practices

Query Formulation

Be specific:

Good: "Find the API rate limit configuration"
Poor: "Tell me about limits"

Use collection names:

"Search the Security Policies collection for..."
"In the API Documentation, find..."

Iterate:

Start broad, then narrow down
Ask follow-up questions
Request clarification

Organization

Organize collections meaningfully:

Separate by topic or project
Use descriptive collection names
Keep related documents together

Maintain document quality:

Clear, descriptive filenames
Well-structured content
Regular updates

Security

Protect your API key:

Store in config only
Don't commit to version control
Rotate periodically
Use separate keys for different purposes

Control access:

Use read-only API keys for MCP
Limit collection access if needed
Monitor usage logs

Integration Examples

Research Workflow

Research new technology:

Upload relevant documentation to Scrapalot
During Claude conversation, search docs for specific topics
Get contextual answers with citations
Dive deeper into specific areas

Documentation Writing

Create documentation with Claude:

Store existing docs in Scrapalot
Ask Claude to search for related information
Get consistent terminology and approach
Reference existing content

Code Review

Review code with context:

Store architectural docs in Scrapalot
During code review, ask Claude to check against standards
Get design pattern references
Ensure consistency with existing code

Advanced Configuration

Custom MCP Client

Build your own integration:

python

import requests

def query_scrapalot(query: str, api_key: str, collection_id: str = None):
    """Query Scrapalot via MCP endpoint"""
    response = requests.post(
        "http://localhost:8090/mcp/query",
        json={
            "query": query,
            "collection_id": collection_id,
            "max_results": 5
        },
        headers={"Authorization": f"Bearer {api_key}"}
    )
    return response.json()["results"]

Multiple Scrapalot Instances

Connect to multiple Scrapalot servers:

json

{
  "mcpServers": {
    "scrapalot-prod": {
      "command": "scrapalot-mcp",
      "args": ["--api-url", "https://prod.scrapalot.com"],
      "env": {"SCRAPALOT_API_KEY": "prod-key"}
    },
    "scrapalot-dev": {
      "command": "scrapalot-mcp",
      "args": ["--api-url", "http://localhost:8090"],
      "env": {"SCRAPALOT_API_KEY": "dev-key"}
    }
  }
}

API Reference - REST API endpoints
Security - Authentication and access control
RAG Strategy - How search works
User Guide - Using Scrapalot features

MCP integration brings your Scrapalot knowledge base directly into your AI conversations. Set it up once and search your documents naturally during any Claude conversation.

Model Context Protocol (MCP) ​

What is MCP? ​

Use Cases ​

Development with Claude ​

Documentation Research ​

Setup Guide ​

Prerequisites ​

Configuration ​

Getting Your API Key ​

Using MCP with Claude ​

Basic Queries ​

Advanced Queries ​

Available Operations ​

Search Documents ​

List Collections ​

Troubleshooting ​

MCP Server Not Responding ​

Authentication Errors ​

No Results Returned ​

Connection Refused ​

Best Practices ​

Query Formulation ​

Organization ​

Security ​

Integration Examples ​

Research Workflow ​

Documentation Writing ​

Code Review ​

Advanced Configuration ​

Custom MCP Client ​

Multiple Scrapalot Instances ​

Related Documentation ​

Model Context Protocol (MCP)

What is MCP?

Use Cases

Development with Claude

Documentation Research

Setup Guide

Prerequisites

Configuration

Getting Your API Key

Using MCP with Claude

Basic Queries

Advanced Queries

Available Operations

Search Documents

List Collections

Troubleshooting

MCP Server Not Responding

Authentication Errors

No Results Returned

Connection Refused

Best Practices

Query Formulation

Organization

Security

Integration Examples

Research Workflow

Documentation Writing

Code Review

Advanced Configuration

Custom MCP Client

Multiple Scrapalot Instances

Related Documentation