Sovant Claude Code MCP
S

Sovant Claude Code MCP

Sovant MCP is a local adapter designed for Claude Code, providing independent long - term memory storage services for each code repository through explicit tool calls. Memories are stored in the cloud and can be managed.
2 points
8.1K

What is Sovant Claude Code MCP?

Sovant MCP is an intelligent memory assistant specifically designed for Claude Code (Anthropic's code editor). It enables the AI assistant to remember important information in your different projects, such as technical decisions, coding specifications, database configurations, etc. Each Git repository has an independent memory space to ensure that information is not confused.

How to use Sovant MCP?

After installation, you can directly use specific memory commands when chatting with the AI in Claude Code. For example, tell the AI "Remember: We use PostgreSQL 16". Then, at any time, when you ask "What database do we use?", the AI can answer accurately. All memories are stored in the Sovant cloud and can be managed through the web dashboard.

Applicable scenarios

It is very suitable for scenarios such as team collaborative development, long-term project maintenance, and parallel development of multiple projects. When you need to ensure the consistency of technical decisions, avoid repeated explanations of project specifications, or maintain context continuity between different sessions, Sovant MCP can be very helpful.

Main features

Explicit memory
All memories need your explicit instruction to save. There is no automatic capture or background listening, and it is completely under your control.
Repository isolation
Each Git repository corresponds to an independent memory thread, and information from different projects will not interfere with each other.
Local operation
The MCP adapter runs locally and communicates with Claude Code through standard input and output to ensure response speed.
Cloud storage
Memories are stored in the Sovant cloud, supporting search, management, and persistent storage, and can be accessed through the web dashboard.
Privacy by default
By default, only development memories saved through Claude Code are retrieved, excluding data from other sources such as dashboards and CRMs.
Rich toolset
It provides 10 different memory tools, including complete functions such as saving, retrieving, searching, listing, editing, and deleting.
Advantages
Fully controllable: All memories need explicit instructions to save, without automatic capture.
Project isolation: Each repository has independent memory to avoid information confusion.
Persistent storage: Cloud storage ensures that memories will not be lost when the session ends.
Easy to manage: All memories can be viewed and managed through the web dashboard.
Privacy protection: By default, only development memories are retrieved to protect sensitive information.
Flexible search: Supports both in - thread search and global search modes.
Limitations
Manual saving required: It will not automatically remember the conversation content.
Network - dependent: It needs to be connected to the Sovant cloud service.
API key required: You need to register to obtain a free API key.
Only for Claude Code: Currently, it only supports Anthropic's Claude Code editor.

How to use

Installation preparation
Ensure that Claude Code and Node.js 18+ are installed, and obtain the Sovant API key.
Clone and build
Download the MCP adapter code and build it.
Register to Claude Code
Register the adapter as the MCP server of Claude Code.
Verify installation
Restart Claude Code and test the memory function.

Usage examples

Save the project technology stack
At the beginning of a new project, record the technology stack and version used in the project.
Record architectural decisions
Record important technical decisions and reasons.
Save team coding specifications
Record the team's coding conventions and best practices.
Maintain context across sessions
Maintain project context between different work sessions.

Frequently Asked Questions

Where are the memories stored? Is it safe?
Will the memories between different projects be confused?
How to delete unwanted memories?
What types of memories are supported?
Are there any limits on the number or size of memories?
Will the memories be lost after uninstallation?

Related resources

Official documentation
Complete MCP adapter usage documentation and API reference.
GitHub repository
Source code, issue feedback, and contribution guidelines.
API key management
Obtain and manage your Sovant API key.
Sovant dashboard
Web interface for online management of all memories.
Claude Code documentation
Official documentation for the Claude Code editor.
Terms of service
Terms and conditions for using the Sovant service.

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

A
Airweave
Airweave is an open - source context retrieval layer for AI agents and RAG systems. It connects and synchronizes data from various applications, tools, and databases, and provides relevant, real - time, multi - source contextual information to AI agents through a unified search interface.
Python
16.2K
5 points
V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
9.4K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
9.0K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
15.8K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
6.7K
4 points
P
Paperbanana
Python
8.9K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
10.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
8.9K
5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
39.0K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
24.8K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
80.0K
4.3 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
28.3K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
37.3K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
70.4K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
24.9K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
106.7K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase