Back to Home
saurabhmain icon

a-mem-mcp-server

by saurabhmain

Overview

An agentic memory system for LLM agents, enhancing research by storing, linking, and evolving knowledge based on the Zettelkasten principle, with IDE integration.

Installation

Run Command
python -m src.a_mem.main

Environment Variables

  • LLM_PROVIDER
  • OLLAMA_BASE_URL
  • OLLAMA_LLM_MODEL
  • OLLAMA_EMBEDDING_MODEL
  • OPENROUTER_API_KEY
  • OPENROUTER_BASE_URL
  • OPENROUTER_LLM_MODEL
  • OPENROUTER_EMBEDDING_MODEL
  • TCP_SERVER_ENABLED
  • TCP_SERVER_HOST
  • TCP_SERVER_PORT
  • RESEARCHER_ENABLED
  • RESEARCHER_CONFIDENCE_THRESHOLD
  • RESEARCHER_MAX_SOURCES
  • RESEARCHER_MAX_CONTENT_LENGTH
  • JINA_READER_ENABLED
  • JINA_READER_HOST
  • JINA_READER_PORT
  • UNSTRUCTURED_ENABLED
  • UNSTRUCTURED_API_URL
  • UNSTRUCTURED_API_KEY
  • UNSTRUCTURED_USE_LIBRARY
  • GOOGLE_SEARCH_ENABLED
  • GOOGLE_API_KEY
  • GOOGLE_SEARCH_ENGINE_ID
  • GRAPH_BACKEND

Security Notes

The server exposes a `/get_graph` endpoint via an `aiohttp` web server, by default on `127.0.0.1:42424`, which is read-only but exposes internal graph data. The `add_file` tool processes file paths provided by the user/agent; if a malicious actor controls this input, it could potentially be used to read arbitrary files accessible to the server process, leading to information disclosure. Additionally, public Google API keys are hardcoded as defaults, which, while likely for a public Custom Search Engine, is still poor practice and could lead to API quota exhaustion.

Similar Servers

Stats

Interest Score0
Security Score5
Cost ClassHigh
Avg Tokens2000
Stars0
Forks0
Last Update2026-01-19

Tags

Agentic MemoryKnowledge GraphLLM IntegrationZettelkastenResearch AssistantIDE IntegrationVector DatabaseGraph Database