ai-context-nas
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PGID | Yes | The GID of the intended non-root NAS folder owner. | |
| PUID | Yes | The UID of the intended non-root NAS folder owner. | |
| DATA_ROOT | Yes | The data root path for the NAS deployment. Relative ./runtime means local storage beside compose.yaml; an absolute path must be a verified NAS Linux path. | |
| HTTPS_PORT | Yes | The HTTPS port for Caddy to serve the MCP endpoint. | |
| BACKUP_KEEP | Yes | The number of newest backup archives to retain. | |
| BIND_ADDRESS | No | The bind address for the gateway. Default is loopback; set to the NAS's private IP after checking ports and firewall rules. | loopback |
| CONTEXT_HOST | Yes | The private DNS/hostname for the MCP server (e.g., context.nas.internal). | |
| CONTEXT_VARIANT | No | Set to standard to run the standard gateway; defaults to slim. | slim |
| MAX_CONTEXT_TOKENS | Yes | The configured token budget used as a byte ceiling for serialized results. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| query_graphB | Search the knowledge graph using BFS or DFS. Returns relevant nodes and edges as text context. |
| get_nodeC | Get full details for a specific node by label or ID. |
| get_neighborsC | Get all direct neighbors of a node with edge details. |
| get_communityB | Get all nodes in a community by community ID. |
| god_nodesC | Return the most connected nodes - the core abstractions of the knowledge graph. |
| graph_statsA | Return summary statistics: node count, edge count, communities, confidence breakdown. |
| shortest_pathA | Find the shortest path between two concepts in the knowledge graph. Follows stored edge direction by default; set undirected=true to ignore it. |
| list_prsA | List open GitHub PRs with CI status, review state, and graph impact (which communities each PR touches, blast radius). Use this before starting work to check if a PR already covers the area you're about to change. |
| get_pr_impactA | Get detailed graph impact for a specific PR: which files it changes, which knowledge-graph communities are affected, and how many nodes are touched. Use this to assess merge risk or check for overlap with your current work. |
| triage_prsA | Return all actionable open PRs (correct base, not stale) with full graph impact data so you can reason about review priority, merge order, and conflict risk. Call this when the user asks 'what PRs should I review?' or 'what's ready to merge?' |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Graph Report | Full GRAPH_REPORT.md |
| Graph Stats | Node/edge/community counts and confidence breakdown |
| God Nodes | Top 10 most-connected nodes |
| Surprising Connections | Cross-community surprising connections |
| Confidence Audit | EXTRACTED/INFERRED/AMBIGUOUS edge breakdown |
| Suggested Questions | Suggested questions for this codebase |
TDQS
Scored across 10 tools
Most tools have clearly distinct graph or PR purposes, such as get_node vs get_neighbors vs shortest_path. The main overlap is between list_prs and triage_prs, both listing PRs, though triage_prs is narrower and adds priority-oriented impact data. get_pr_impact is distinct by targeting a specific PR.
All names use snake_case, but conventions are mixed: some are verb_noun (query_graph, get_node, list_prs), while others are noun phrases or specialized labels (god_nodes, graph_stats, shortest_path). The pattern is readable but not consistently action-first.
Ten tools is well-scoped for a read-only knowledge-graph context and PR triage server. Each tool covers a distinct query or inspection need without excessive surface area.
The surface covers graph search, node details, neighbors, communities, statistics, paths, and PR impact/triage well. A minor gap is the lack of a list_communities operation, making community IDs less discoverable before calling get_community.