Server data from the Official MCP Registry
Authority-weighted memory graph for AI agents with conflict detection and semantic search.
Authority-weighted memory graph for AI agents with conflict detection and semantic search.
A well-architected memory management MCP server with proper input validation, secure dependency choices, and appropriate permission scoping. The codebase demonstrates good security practices including parameterized SQL queries, no hardcoded secrets, and thoughtful conflict resolution. Minor code quality observations exist but do not materially impact security. Supply chain analysis found 4 known vulnerabilities in dependencies (0 critical, 4 high severity). Package verification found 1 issue.
8 files analyzed · 11 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-retrorobai-mcp-memory-graph": {
"args": [
"mcp-memory-graph"
],
"command": "uvx"
}
}
}From the project's GitHub README.
A context-aware memory MCP server for Claude Code and any MCP-compatible AI agent.
Goes beyond basic vector search by adding authority weighting, conflict detection, and typed relationship edges between memories — so your agent always retrieves the right answer when sources disagree.
Inspired by the context engine architecture described in Unblocked's "How a Context Engine Actually Works".
Standard memory MCP servers store and retrieve memories by semantic similarity. That works until you have conflicting memories — an old instruction saying one thing and a new one saying another. Without authority weighting, the agent retrieves whichever is semantically closer to the query, not whichever is more trustworthy.
mcp-memory-graph solves this with three mechanisms:
| Problem | Solution |
|---|---|
| All memories treated equally | Priority tiers: high / medium / low → authority scores 1.0 / 0.6 / 0.3 |
| Stale memories persist silently | Supersession tracking: old memories marked status=superseded with typed edges |
| Duplicates accumulate over time | Conflict detection before every store; auto-resolve by authority |
pip install mcp-memory-graph
Or run directly:
git clone https://github.com/RetroRobAI/mcp-memory-graph
cd mcp-memory-graph
pip install -r requirements.txt
python server.py
Add to ~/.claude.json under mcpServers:
"mcp-memory-graph": {
"type": "stdio",
"command": "mcp-memory-graph",
"env": {
"MEMORY_GRAPH_DB_PATH": "/path/to/memories.db"
}
}
Or with the raw script:
"mcp-memory-graph": {
"type": "stdio",
"command": "python",
"args": ["/path/to/mcp-memory-graph/server.py"],
"env": {
"MEMORY_GRAPH_DB_PATH": "/path/to/memories.db"
}
}
If you have an existing memory service (mcp-memory-service, Mem0, or a markdown-based memory system), you can import your memories into mcp-memory-graph using the included migration script.
Migration is manual and opt-in — it never runs automatically. Nothing is written until you explicitly confirm.
python -m mcp_memory_graph.migrate
The script will:
mcp-memory-service SQLite databaseYour existing memory service is never modified — the script only reads from it.
All settings via environment variables:
| Variable | Default | Description |
|---|---|---|
MEMORY_GRAPH_DB_PATH | ~/.mcp-memory-graph/memories.db | SQLite database path |
MEMORY_GRAPH_MODEL | all-MiniLM-L6-v2 | sentence-transformers model |
MEMORY_GRAPH_DIM | 384 | Embedding dimensions |
MEMORY_GRAPH_CONFLICT_THRESHOLD | 0.85 | Cosine similarity above which memories are flagged as conflicting |
MEMORY_GRAPH_DEFAULT_RESULTS | 10 | Default retrieval limit |
| Tool | Description |
|---|---|
store_memory | Store with conflict detection and optional auto-resolve |
retrieve_memories | Semantic search ranked by similarity × authority |
check_conflicts | Preview conflicts before storing |
update_memory | Update content/priority with supersession tracking |
delete_memory | Soft delete (preserves history) |
add_memory_edge | Manually add typed relationship |
get_related_memories | Traverse relationship graph for a memory |
list_memories | List with filters (status, type, priority) |
priority="high" # authority_score=1.0 — explicit instructions, confirmed preferences
priority="medium" # authority_score=0.6 — inferred preferences, reference data
priority="low" # authority_score=0.3 — session summaries, historical context
Retrieval ranking: weighted_score = 1 - (distance / (authority_score + 0.001) / 10)
A high-authority memory will rank above a semantically closer low-authority one when their similarity scores are within ~3x of each other.
supersedes — this memory replaces anotherrelates_to — connected but not conflictingcontradicts — explicitly conflicting, unresolvedreferenced_by — another memory cites this oneMIT
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.