AgentIndex icon
AgentIndex
mcp-server-elasticsearch logo
mcp-server-elasticsearch
★ 725
vs
rekal logo
rekal
★ 53

mcp-server-elasticsearch vs rekal

mcp-server-elasticsearch: The Elasticsearch MCP Server enables AI agents to query, analyze, and retrieve data from Elasticsearch indices using natural language. It supports both stdio and streamable-HTTP protocols, and can be deployed as a Docker container from AWS Marketplace. Note: This server is deprecated and superseded by the Elastic Agent Builder MCP endpoint.; rekal: rekal provides long-term memory for LLMs via an MCP server. It stores memories in a local SQLite file and retrieves them using hybrid search (BM25 keywords + vector semantics + recency decay). It works with any MCP-capable agent like Claude Code, Codex CLI, and OpenCode.

01

TL;DR

mcp-server-elasticsearch logo
mcp-server-elasticsearchRAG / Knowledge Base · ★ 725

Enable AI agents to query Elasticsearch indices using natural language

Read mcp-server-elasticsearch full review →
rekal logo
rekalRAG / Knowledge Base · ★ 53

Persistent memory for coding agents across sessions to remember user preferences and decisions

Read rekal full review →
02

Side-by-Side Comparison

Field
mcp-server-elasticsearch logomcp-server-elasticsearch
rekal logorekal
Category
RAG / Knowledge Base
RAG / Knowledge Base
Stars
★ 725
★ 53
License
Apache-2.0
MIT
Install Command
docker run -i --rm -e ES_URL -e ES_API_KEY docker.elastic.co/mcp/elasticsearch stdio
pip install rekal
Updated
1d ago
1mo ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
elasticsearch, mcp, mcp-server
llm, mcp, mcp-server
03

Features

mcp-server-elasticsearch logomcp-server-elasticsearch
01Natural language querying of Elasticsearch indices
02Supports stdio and streamable-HTTP protocols
03Docker container deployment from AWS Marketplace
04Provides tools: list_indices, get_mappings, search, esql, get_shards
05Secure credential handling via environment variables
rekal logorekal
01Local SQLite storage, no cloud or API keys
02Hybrid search combining BM25 keywords, vector semantics, and recency decay
03MCP server compatible with various coding agents
04Comprehensive tool-based memory management (store, search, update, delete, prune)
05Smart write operations with supersede and linking for knowledge evolution
04

Use Cases

mcp-server-elasticsearch logomcp-server-elasticsearch
↳Enable AI agents to query Elasticsearch indices using natural language
↳Perform advanced data analysis using ES|QL through agent conversations
↳Connect MCP-compatible clients (e.g., Claude Desktop) to Elasticsearch data
rekal logorekal
↳Persistent memory for coding agents across sessions to remember user preferences and decisions
↳Storing project-specific knowledge and conventions without external services
↳Maintaining a searchable history of agent interactions and decisions
FAQ

FAQ

What is the difference between mcp-server-elasticsearch and rekal?
Both mcp-server-elasticsearch and rekal are in the RAG / Knowledge Base category. mcp-server-elasticsearch has 725 stars, while rekal has 53 stars.
Which is better, mcp-server-elasticsearch or rekal?
The best choice depends on your use case. Choose mcp-server-elasticsearch if Enable AI agents to query Elasticsearch indices using natural language, and rekal if Persistent memory for coding agents across sessions to remember user preferences and decisions.
Is mcp-server-elasticsearch free or open source?
Yes, mcp-server-elasticsearch is open source on GitHub (Apache-2.0).
Is rekal free or open source?
Yes, rekal is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to mcp-server-elasticsearch →Alternatives to rekal →mcp-server-elasticsearch details →rekal details →