Memex Targeted Search Server

Performs targeted searches across Memex conversation history and project files.

A Model Context Protocol (MCP) server that provides targeted search capabilities across Memex conversation history and project files.

This MCP server enables AI agents to efficiently search through:

- Conversation History: 952+ conversation files from Memex with metadata, titles, summaries, and message content
- Project Files: 516+ project directories in the user's workspace with various file types and technologies
- search_conversations- Search conversation history by text, metadata, and filters
- get_conversation_snippet- Retrieve specific parts of conversations without context overload
- search_projects- Search project files by content, file types, and names
- get_project_overview- Get project summaries with technology detection
- find_command-NEW!Find specific commands, CLI usage, or code snippets from conversation history

- Returns targeted snippets instead of full conversations
- Limits search scope to prevent context explosion
- Supports faceted filtering (dates, projects, file types)
- Provides relevance scoring for search results

# Clone the repository git clone https://github.com/memextech/memex-targeted-search-server.git cd memex-targeted-search-server # Install dependencies npm install # Build the project npm run build

- Conversation History:~/Library/Application Support/Memex/history/
- Project Files:~/Workspace/

Add to your MCP configuration (e.g., Claude Desktop config):

{ "mcpServers": { "memex-search": { "command": "node", "args": ["/path/to/memex-targeted-search-server/dist/index.js"] } } }

"I don't remember what the command is to run the memex agent cli"

find_command({ query: "memex agent cli", command_type: "cli", limit: 5 })

find_command({ query: "npm install", command_type: "cli", limit: 5 })

{ "query": "npm install", "total_found": 3, "commands": [ { "command": "npm install -g firebase-tools", "context": "Install Firebase CLI: npm install -g firebase-tools\n- Login to Firebase: firebase login", "conversation_id": "abc123", "conversation_title": "Firebase Setup Guide", "message_index": 7, "confidence": 0.9, "type": "cli" } ] }

Find conversations about specific topics

search_conversations({ query: "3D modeling", limit: 5 })

{ "total_found": 3, "conversations": [ { "conversation_id": "a3edfc8f-0978-415e-9de8-18f4d94ea3a2", "title": "3D Interactive Solar System Model", "summary": "Design an engaging, visually appealing 3D representation of planets and celestial bodies", "created_at": "2025-05-27T17:13:26Z", "project": "Stellar 3d solar system", "message_count": 76, "relevance": "content" } ] }

search_conversations({ query: "python", project: "cad_example", date_from: "2025-01-01", date_to: "2025-03-01", limit: 3 })

Retrieve specific messages from a conversation

get_conversation_snippet({ conversation_id: "bf283daa-25d3-434f-ad7e-9adda48cdcdd", message_start: 1, message_count: 3 })

{ "conversation_id": "bf283daa-25d3-434f-ad7e-9adda48cdcdd", "title": "3D Model 3MF File Creation", "message_range": "1-3", "total_messages": 30, "messages": [ { "index": 1, "role": "user", "content": "can I create a 3D model in .3mf?" }, { "index": 2, "role": "assistant", "content": "I'll help you create a 3D model using PythonOCC and convert it to .3mf format..." } ] }

search_projects({ query: "interface", file_types: ["ts", "js"], limit: 10 })

search_projects({ query: "streamlit", limit: 5 })

{ "total_found": 3, "results": [ { "project": "ad_campaign_dashboard", "file": "ad_campaign_dashboard/app.py", "match": "import streamlit as st", "line": 1 } ] }

Analyze project structure and tech stack

get_project_overview({ project_name: "memex_targeted_search_server" })

{ "name": "memex_targeted_search_server", "path": "/Users/user/Workspace/memex_targeted_search_server", "file_count": 8, "directories": ["dist", "src"], "file_types": { "ts": 1, "js": 1, "json": 3, "md": 1 }, "main_files": ["package.json", "README.md"], "technologies": ["JavaScript/TypeScript"] }

Scenario 1: "I forgot that command..."

// User: "I don't remember what the command is to run the memex agent cli" find_command({ query: "memex agent", command_type: "cli", limit: 5 }) // User: "What was that firebase command to deploy?" find_command({ query: "firebase deploy", command_type: "cli", limit: 3 }) // Result: Finds exact commands with context from previous conversations

// Agent: "I need to find previous conversations about Blender projects" search_conversations({ query: "blender", limit: 5 }) // Result: Finds 2 conversations about 3D Manhattan cityscape and geometric skyscraper // Agent can then drill down into specific conversations for details

// Agent: "Show me Python projects that use Streamlit" search_projects({ query: "streamlit", file_types: ["py"], limit: 10 }) // Result: Finds specific Python files with Streamlit imports // Agent can then examine project structure and implementation patterns

// Agent: "Find conversations from January 2025 about 3D modeling" search_conversations({ query: "3D model", date_from: "2025-01-01", date_to: "2025-01-31", limit: 5 }) // Agent: "Now show me the related project files" get_project_overview({ project_name: "cad_example" })

- Purpose: Search conversation history with flexible filtering
- Parameters:query(required),limit,project,date_from,date_to
- Returns: Array of conversation metadata with relevance scoring

- Purpose: Retrieve specific message ranges from conversations
- Parameters:conversation_id(required),message_start,message_count
- Returns: Conversation snippet with message details

- Purpose: Search project files by content and metadata
- Parameters:query(required),file_types,limit
- Returns: Array of file matches with context

- Purpose: Analyze project structure and technology stack
- Parameters:project_name(required)
- Returns: Project summary with file counts and tech detection

- Purpose: Find specific commands, CLI usage, or code snippets from conversation history
- Parameters:query(required),command_type(cli/code/config/any),limit
- Returns: Array of commands with context, confidence scoring, and conversation references

- TypeScript- Type-safe development
- MCP SDK- Official Model Context Protocol SDK
- Node.js- Runtime environment
- File System APIs- Direct file access for performance

- Limits search scope to prevent overwhelming results
- Uses streaming JSON parsing for large files
- Implements intelligent file filtering
- Caches frequently accessed metadata
- Returns truncated content with full context available on demand

The server is designed for optimal agent interaction:

- Targeted Search: Find specific information without context overload
- Faceted Filtering: Multiple search dimensions (date, project, file type)
- Progressive Discovery: Start with summaries, drill down to details
- Context Preservation: Maintain conversation and project relationships

The server includes comprehensive error handling and graceful degradation for:

- Missing or corrupted conversation files
- Inaccessible project directories
- Invalid JSON parsing
- Large file handling

Contributions are welcome! Please feel free to submit a Pull Request.

🤖 Generated withMemex
Co-Authored-By: Memexnoreply@memex.tech

Search and discover 24,500+ MCP servers and AI agents. Semantic search, trust scores, vulnerability tracking.