AIbase
EN
Explore
FEGIS (Schema Driven Memory)
F

FEGIS (Schema Driven Memory)

FEGIS is a structured cognitive framework based on the Anthropic model context protocol, supporting the definition of cognitive tools through patterns and the persistent storage of cognitive products.
Knowledge management and memoryDeveloper tools#Cognitive Framework#Thinking Tool#Semantic Storage.Python
2.5 points
26

What is the MCP server?

The MCP server is a framework that allows you to define, register, and invoke the cognitive patterns of language models. It enables efficient knowledge management and retrieval through vectorized storage and semantic context.

How to use the MCP server?

Through simple configuration and instructions, you can easily enable the MCP server to enhance the cognitive ability of language models.

Applicable Scenarios

The MCP server is suitable for application scenarios that require efficient knowledge management, cognitive tool integration, and cross - model compatibility, such as knowledge - intensive tasks and complex problem - solving.

Main Features

Dynamic RegistrationSupports dynamic registration of new cognitive patterns at runtime.
Persistent StorageSaves cognitive results in a structured form, supporting long - term access and reuse.
Semantic RetrievalQuickly finds relevant information through content similarity.
Model AgnosticismEnsures seamless migration of your cognitive data between different models.

Advantages and Limitations

Advantages
Enhance the cognitive ability of language models.
Support persistent storage and an efficient retrieval mechanism.
Cross - model compatibility, no need to worry about data loss caused by model switching.
High flexibility and strong customizability.
Limitations
Requires a certain technical background for setup and maintenance.
Some advanced features may require additional computing resources.
The initial configuration may be relatively complex.

How to Use

Install Dependencies
First, ensure that the necessary tools and dependencies are installed, such as the Python package manager and Docker.
Start the Qdrant Database
Run the Qdrant database to support vector storage.
Configure Claude Desktop
Edit the configuration file to integrate the MCP server.

Usage Examples

Case 1: Knowledge RetrievalSearch for relevant content in the history records by keywords.
Case 2: Reuse of Cognitive ResultsObtain previously stored cognitive results through the UUID.

Frequently Asked Questions

Does the MCP server support multiple languages?
How to ensure data security?
What should I do if I encounter technical problems?

Related Resources

Official Documentation
Detailed usage guides and technical documentation.
GitHub Code Repository
Open - source code and example projects.
Community Forum
A communication platform with other users.
Installation
Copy the following command to your Client for configuration
{
  "mcpServers": {
    "mcp-fegis-server": {
      "command": "uv",
      "args": [
        "--directory",
        "<FEGIS_PATH>",
        "run",
        "fegis"
      ],
      "env": {
        "QDRANT_URL": "http://localhost:6333",
        "QDRANT_API_KEY": "",
        "COLLECTION_NAME": "cognitive_archive",
        "FAST_EMBED_MODEL": "nomic-ai/nomic-embed-text-v1.5",
        "CONFIG_PATH": "<FEGIS_PATH>/archetypes/example.yaml"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
S
Search1api
The Search1API MCP Server is a server based on the Model Context Protocol (MCP), providing search and crawling functions, and supporting multiple search services and tools.
TypeScript
355
4 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
845
4.3 points
A
Apple Notes MCP
A server that provides local Apple Notes database access for the Claude desktop client, supporting reading and searching of note content.
Python
220
4.3 points
M
MCP Alchemy
Certified
MCP Alchemy is a tool that connects Claude Desktop to multiple databases, supporting SQL queries, database structure analysis, and data report generation.
Python
341
4.2 points
P
Postgresql MCP
A PostgreSQL database MCP service based on the FastMCP library, providing CRUD operations, schema inspection, and custom SQL query functions for specified tables.
Python
125
4 points
M
MCP Scan
MCP-Scan is a security scanning tool for MCP servers, used to detect common security vulnerabilities such as prompt injection, tool poisoning, and cross-domain escalation.
Python
632
5 points
A
Agentic Radar
Agentic Radar is a security scanning tool for analyzing and assessing agentic systems, helping developers, researchers, and security experts understand the workflows of agentic systems and identify potential vulnerabilities.
Python
569
5 points
C
Cloudflare
Changesets is a build tool for managing versions and releases in multi - package or single - package repositories.
TypeScript
1.5K
5 points
Featured MCP Services
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
1.7K
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
160
4.5 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
108
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
845
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#
581
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
6.7K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
768
4.8 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
297
4.5 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2025AIbase