# FastMCP server for surgical queries against a vault knowledge graph (NetworkX no
**Category:** 🔒 Security
**Repository:** https://github.com/adelaidasofia/graph-query-mcp
**Views:** 1
**Installs:** 0
**Upvotes:** 0
**Directory Page:** https://allmcps.com/mcp/fastmcp-server-for-surgical-queries-against-a-vault-knowledge-graph-networkx-no
## Description
FastMCP server for surgical queries against a vault knowledge graph (NetworkX node-link JSON).…
## Claude Desktop Quick Installation
Heuristic fallback — verify the package name and runner against the repository README before running it. Uses `npx` (confidence: low):
```json
"mcpServers": {
"fastmcp-server-for-surgical-queries-against-a-vault-knowledge-graph-networkx-no": {
"command": "npx",
"args": ["-y","fastmcp-server-for-surgical-queries-against-a-vault-knowledge-graph-networkx-no"]
}
}
```
## Documentation & README
# graph-query-mcp
Surgical queries against an Obsidian / vault knowledge graph. Loads a `graph.json` (NetworkX node-link format) once at startup and answers targeted questions without making Claude read a 50K-line graph report.
Designed to pair with [`graphify`](https://github.com/mycelium-hq/ai-brain-starter) (the graph-building skill in ai-brain-starter), but the server accepts any graph in NetworkX node-link JSON. Supports up to two scopes (primary + secondary, e.g. personal + team).
## Why use this
If you've already run `graphify` on a vault, you've got a `graph.json` and a `GRAPH_REPORT.md`. Reading the full report into Claude burns thousands of tokens for every question. This MCP loads the graph once at startup, answers in <50ms, and never spills the whole graph into context.
## Tools
| Tool | What it does |
|---|---|
| `search_nodes(query, scope, limit)` | Fuzzy match against node names. Returns node IDs ranked by exact / starts-with / contains. |
| `get_neighbors(node_id, scope, max_hops, limit)` | Connected nodes within N hops, sorted by degree. |
| `find_path(source, target, scope)` | Shortest path between two concepts. Auto-fuzzy-matches both ends. |
| `get_top_nodes(scope, n)` | Highest-degree nodes (the "god nodes"). |
| `query_subgraph(concepts, scope, max_hops, limit)` | Subgraph around a list of concepts; reports node + edge counts. |
| `get_node_info(node_id, scope)` | Full metadata + top neighbors for one node. |
| `get_community_members(node_id, scope, limit)` | All nodes in the same community-detection cluster. |
Scope defaults to `personal`; pass `scope="onde"` (or whatever secondary scope name you've configured) for the second graph.
## Configuration
Two env vars, both optional:
| Env var | Default | Use for |
|---|---|---|
| `GRAPH_JSON_PATH` | `~/Documents/Vault/Meta/graphify-out/graph.json` | Primary graph (the `personal` scope) |
| `SECONDARY_GRAPH_JSON_PATH` | `~/Documents/Vault/Team/Meta/graphify-out/graph.json` | Secondary graph (the `onde` scope, historical name) |
`ONDE_GRAPH_JSON_PATH` is also accepted as a backward-compat alias for `SECONDARY_GRAPH_JSON_PATH`.
If a path doesn't exist at startup, the server logs a warning and the tools return a friendly error when that scope is queried. The server still starts — a missing secondary graph never blocks the primary.
## Install
Open Claude Code, paste:
/plugin marketplace add adelaidasofia/graph-query-mcp
/plugin install graph-query-mcp@graph-query-mcp
Legacy install
```bash
git clone https://github.com/adelaidasofia/graph-query-mcp.git ~/.claude/graph-query-mcp
cd ~/.claude/graph-query-mcp
pip3 install --break-system-packages -r requirements.txt
```
Register in your project `.mcp.json`:
```json
{
"mcpServers": {
"graph-query": {
"type": "stdio",
"command": "fastmcp",
"args": ["run", "/Users/YOU/.claude/graph-query-mcp/server.py"],
"env": {
"GRAPH_JSON_PATH": "/path/to/your/vault/Meta/graphify-out/graph.json"
}
}
}
}
```
Restart Claude Code, then `claude mcp list` should show `graph-query` connected.