Persistent reasoning memory for AI agents via typed cognitive nodes and supersedes edges.
Understanding MCP server exists for a simple reason — assistants are far more useful when they can act on Understanding directly instead of describing what you should do. Persistent reasoning memory for AI agents via typed cognitive nodes and supersedes edges.
Understanding Graph is an MCP server that gives AI agents structured, persistent memory. Unlike knowledge bases that store facts, it stores the reasoning process -- tensions, surprises, decisions, and how beliefs evolved over time. Multiple agents coordinate through the graph itself: each agent reads what others have written, builds on it, and leaves traces for the next -- stigmergy.
The server ships on npm as understanding-graph, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Once Understanding is connected, these are the calls the assistant has available:
Documents — Structured content (notes, papers, code) with thinking nodes interleaved -- capturing comprehension as it happensProjects — Isolated graphs for different contexts. Each project has its own SQLite databaseYou will need 2 environment variables: PROJECT_DIR, ANTHROPIC_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Understanding's toolset — Documents, Projects — is a fair guide to whether it matches your workflow. It is maintained by emergent-wisdom; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Understanding's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Documents | Structured content (notes, papers, code) with thinking nodes interleaved -- capturing comprehension as it happens. |
| Projects | Isolated graphs for different contexts. Each project has its own SQLite database. |
{
"mcpServers": {
"understanding-graph": {
"command": "npx",
"args": ["-y", "understanding-graph"],
"env": {
"PROJECT_DIR": "your-value",
"ANTHROPIC_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| PROJECT_DIR | Filesystem location the server is allowed to use. | Optional |
| ANTHROPIC_API_KEY | Credential the server authenticates with. | Yes |
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.