Manticore Search
Provides access to Manticore Search, an open-source database for real-time, full-text search.
Manticore Search MCP Server
A Model Context Protocol (MCP) server that provides access to Manticore Search functionality through MCP-compatible clients like Claude Code, Cursor, and other AI development tools.
Features
- Full-text search with advanced query options
- Table/index management operations
- Document insertion and manipulation
- Cluster status monitoring
- Boolean queries with highlighting and fuzzy search
- Configurable result limits and pagination
Installation
Prerequisites
- Go 1.22 or later
- Manticore Search server running and accessible
Build
git clone https://github.com/krajcik/manticore-mcp-server.git
cd manticore-mcp-server
go build -o manticore-mcp-server
Configuration
Configure using environment variables:
export MANTICORE_URL="http://localhost:9308"
export MAX_RESULTS_PER_QUERY="100"
export REQUEST_TIMEOUT="30s"
export DEBUG="false"
Or command-line flags:
./manticore-mcp-server --manticore-url="http://localhost:9308" --max-results=100
MCP Client Integration
Add to your MCP client configuration (e.g., ~/.claude.json for Claude Code):
{
"mcpServers": {
"manticore-search": {
"command": "/path/to/manticore-mcp-server",
"args": [],
"env": {
"MANTICORE_URL": "http://localhost:9308",
"MAX_RESULTS_PER_QUERY": "50"
}
}
}
}
Available Tools
The MCP protocol automatically exposes these tools to clients:
search
Full-text search in Manticore indexes.
Key Parameters:
table(required): Table namequery: Search textlimit: Max resultshighlight: Enable result highlightingbool_query: Complex boolean queries
show_tables
List available tables/indexes.
describe_table
Get table schema information.
Parameters:
table(required): Table name
insert_document
Insert document into index.
Parameters:
table(required): Table namedocument(required): Document data
update_document
Update an existing document by id (attributes) with optional additional condition.
Parameters:
table(required)id(required)document(required): fields to updatecondition(optional)
delete_document
Delete documents by id or condition.
Parameters:
table(required)idorcondition(one required)
show_cluster_status
Display cluster health status.
create_cluster / join_cluster / alter_cluster / delete_cluster / set_cluster
Cluster management operations (use with caution in production).
Response Format
All tools return structured JSON:
{
"success": true,
"data": { /* results */ },
"meta": {
"total": 42,
"count": 10,
"operation": "search"
}
}
API Discovery
MCP clients automatically discover available tools and their schemas through the protocol. No manual configuration required.
Troubleshooting
Connection Issues:
- Verify Manticore is running:
curl http://localhost:9308 - Check server path in MCP configuration
- Use
--debugfor verbose logging - For complex boolean queries, ensure HTTP JSON API is reachable (POST to
/search).
Performance:
- Adjust
MAX_RESULTS_PER_QUERYfor your needs - Increase
REQUEST_TIMEOUTfor complex queries
License
MIT License
Server Terkait
MCP SOP Server
An MCP server for accessing and searching Standard Operating Procedures (SOPs) with Italian language support.
Marginalia Search
A search engine for non-commercial content and hidden gems of the internet.
Genji MCP Server
Search and analyze classical Japanese literature using the Genji API, with advanced normalization features.
Perplexity
An MCP server that connects to Perplexity's Sonar API, enabling real-time web-wide research in conversational AI.
Agntic AI for Research Papers
Search and extract information about research papers from arXiv.
RateMySupervisor MCP
Query supervisor evaluation data with fuzzy matching for Chinese and Pinyin names.
microCMS
A search server for the microCMS headless CMS, compatible with the Model Context Protocol (MCP).
Splunk
Interact with Splunk Enterprise/Cloud using natural language queries.
MCP Gemini Grounded Search
A Go-based MCP server providing grounded search functionality using Google's Gemini API.
BGPT MCP
Search scientific papers with structured experimental data extracted from full-text studies. Returns 25+ fields per paper including methods, results, sample sizes, limitations, and quality scores.