FEGIS

Fegis

Fegis does 3 things:

Easy to write tools - Write prompts in YAML format. Tool schemas use flexible natural language instructions.
Structured data from tool calls saved in a vector database - Every tool use is automatically stored in Qdrant with full context.
Search - AI can search through all previous tool usage using semantic similarity, filters, or direct lookup.

Quick Start

# Install uv
# Windows
winget install --id=astral-sh.uv -e

# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Clone
git clone https://github.com/p-funk/fegis.git

# Start Qdrant
docker run -d --name qdrant -p 6333:6333 -p 6334:6334 qdrant/qdrant:latest

Configure Claude Desktop

Update claude_desktop_config.json:

{
  "mcpServers": {
    "fegis": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/fegis",
        "run",
        "fegis"
      ],
      "env": {
        "QDRANT_URL": "http://localhost:6333",
        "QDRANT_API_KEY": "",
        "COLLECTION_NAME": "fegis_memory",
        "EMBEDDING_MODEL": "BAAI/bge-small-en",
        "ARCHETYPE_PATH": "/absolute/path/to/fegis-wip/archetypes/default.yaml",
        "AGENT_ID": "claude_desktop"
      }
    }
  }
}

Restart Claude Desktop. You'll have 7 new tools available including SearchMemory.

How It Works

1. Tools from YAML

parameters:
  BiasScope:
    description: "Range of bias detection to apply"
    examples: [confirmation, availability, anchoring, systematic, comprehensive]
  
  IntrospectionDepth:
    description: "How deeply to examine internal reasoning processes"
    examples: [surface, moderate, deep, exhaustive, meta_recursive]
    
tools:
  BiasDetector:
    description: "Identify reasoning blind spots, cognitive biases, and systematic errors in AI thinking patterns through structured self-examination"
    parameters:
      BiasScope:
      IntrospectionDepth:
    frames:
      identified_biases:
        type: List
        required: true
      reasoning_patterns:
        type: List
        required: true
      alternative_perspectives:
        type: List
        required: true

2. Automatic Memory Storage

Every tool invocation gets stored with:

Tool name and parameters used
Complete input and output
Timestamp and session context
Vector embeddings for semantic search

3. SearchMemory Tool

"Use SearchMemory and find my analysis of privacy concerns"
"Use SearchMemory and what creative ideas did I generate last week?"  
"Use SearchMemory and show me all UncertaintyNavigator results"
"Use SearchMemory and search for memories about decision-making"

Available Archetypes

archetypes/default.yaml - Cognitive analysis tools (UncertaintyNavigator, BiasDetector, etc.)
archetypes/simple_example.yaml - Basic example tools
archetypes/emoji_mind.yaml - Symbolic reasoning with emojis
archetypes/slime_mold.yaml - Network optimization tools
archetypes/vibe_surfer.yaml - Web exploration tools

Configuration

Required environment variables:

ARCHETYPE_PATH - Path to YAML archetype file
QDRANT_URL - Qdrant database URL (default: http://localhost:6333)

Optional environment variables:

COLLECTION_NAME - Qdrant collection name (default: fegis_memory)
AGENT_ID - Identifier for this agent (default: default-agent)
EMBEDDING_MODEL - Dense embedding model (default: BAAI/bge-small-en)
QDRANT_API_KEY - API key for remote Qdrant (default: empty)

Requirements

Python 3.13+
uv package manager
Docker (for Qdrant)
MCP-compatible client

License

MIT License - see LICENSE file for details.

This server cannot be installed

security - not tested

license - permissive license

quality - not tested

How are these scores calculated?

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

FEGIS is a Model Context Protocol server that gives LLMs structured, persistent and portable memory through customizable cognitive tools defined in schema.

Related MCP Servers

mcp-figma
smithery-ai
A
security
F
license
A
quality
A Model Context Protocol server that provides access to Figma API functionality, allowing AI assistants like Claude to interact with Figma files, comments, components, and team resources.
Last updated -
18
62
2
Figma MCP Server
mohammeduvaiz
-
security
F
license
-
quality
A Model Context Protocol server that connects AI tools and LLMs to Figma designs, enabling them to extract design data, analyze design systems, and generate development documentation.
Last updated -
144
1
TypeScript
FogBugz MCP Server
akari2600
-
security
F
license
-
quality
A Model Context Protocol server that enables Language Learning Models to interact with FogBugz, allowing operations like creating and updating issues, assigning cases, listing open cases, and searching through natural language.
Last updated -
JavaScript
Lark MCP
cv-cat
-
security
F
license
-
quality
A Model Context Protocol server that enables AI models to perform function calls through Feishu/Lark messaging platform, using your personal account (no bot configuration needed) to create a full-featured AI assistant.
Last updated -
110
Python

View all related MCP servers

FEGIS

Fegis

Quick Start

Configure Claude Desktop

How It Works

1. Tools from YAML

2. Automatic Memory Storage

3. SearchMemory Tool

Available Archetypes

Configuration

Requirements

License

Related MCP Servers

mcp-figma

Figma MCP Server

FogBugz MCP Server

Lark MCP

Appeared in Searches

MCP directory API