MCP server for enabling persistent knowledge storage for Claude through a knowledge graph with multiple storage backends
MCP server for enabling persistent knowledge storage for Claude through a knowledge graph with multiple storage backends. That is what the knowledgegraph mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
A simple way to give LLMs persistent memory across conversations. This server lets Claude or vscode remember information about you, your projects, and your preferences using a knowledge graph.
The server publishes 11 tools. What each one is for:
create_entities — The create_entities tool exposed by this servercreate_relations — The create_relations tool exposed by this serveradd_observations — The add_observations tool exposed by this serveradd_tags — The add_tags tool exposed by this serverread_graph — The read_graph tool exposed by this serversearch_knowledge — The search_knowledge tool exposed by this serveropen_nodes — The open_nodes tool exposed by this serverdelete_entities — The delete_entities tool exposed by this serverdelete_observations — The delete_observations tool exposed by this serverdelete_relations — The delete_relations tool exposed by this serverremove_tags — The remove_tags tool exposed by this serverThe server ships on npm as knowledgegraph-mcp, 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.
Configuration is passed through the environment: KNOWLEDGEGRAPH_SQLITE_PATH, KNOWLEDGEGRAPH_STORAGE_TYPE, KNOWLEDGEGRAPH_CONNECTION_STRING. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Among the file and storage access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Knowledgegraph MCP's toolset — create_entities, create_relations, add_observations and 8 more — is a fair guide to whether it matches your workflow. It is maintained by n-r-w; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Knowledgegraph MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| create_entities | The create_entities tool exposed by this server. |
| create_relations | The create_relations tool exposed by this server. |
| add_observations | The add_observations tool exposed by this server. |
| add_tags | The add_tags tool exposed by this server. |
| read_graph | The read_graph tool exposed by this server. |
| search_knowledge | The search_knowledge tool exposed by this server. |
| open_nodes | The open_nodes tool exposed by this server. |
| delete_entities | The delete_entities tool exposed by this server. |
| delete_observations | The delete_observations tool exposed by this server. |
| delete_relations | The delete_relations tool exposed by this server. |
| remove_tags | The remove_tags tool exposed by this server. |
{
"mcpServers": {
"Knowledge Graph": {
"command": "npx",
"args": ["-y", "knowledgegraph-mcp"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| KNOWLEDGEGRAPH_SQLITE_PATH | Filesystem location the server is allowed to use. | Optional |
| KNOWLEDGEGRAPH_STORAGE_TYPE | Configuration value read at startup. | Optional |
| KNOWLEDGEGRAPH_CONNECTION_STRING | Configuration value read at startup. | Optional |
Scoped local file access — read, write, search and reorganise files in directories you explicitly allow.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Model Context Protocol (MCP) tool to interact with Claude Desktop on macOS
Upload, search, transform and organise your Cloudinary media library from a chat window