How it works

Context Master turns your workspace into a graph your agent can follow — so it finds the right code faster, plans safer changes, and wastes fewer tokens.

01
Initialize
On activation, Context Master builds a local index so your assistant can navigate reliably.
02
Build the graph
After that, it builds a real Semantic Code Graph using VS Code’s symbol and reference APIs.
03
Rank Symbols
Surface the few symbols that matter most so your agent can orient quickly.
04
Ask for the right context
Connect your assistant and request the exact context for the task.

Why it's a good idea

Most agents rely on regex and naive file reading. Context Master uses VSCode’s language providers to expose the same kind of structure developers rely on: symbols, references, and relationships across files.

Language Server Protocol

We don’t parse text; we traverse the VSCode symbol tree for each file and connect those nodes across files into a symbolic graph.

Local-First Indexing

Indexing happens in your editor. No data ever leaves your machine. You remain in control of how you access and use the provided MCP server.

Automated Context Management

Stop hand-curating context. Agents can request the right symbols for the task as they work.

Token Efficiency

Use fewer tokens by letting your agent read code by symbol instead of by file.

Fuzzy Symbol Search

Recover from agent mistakes: if it asks for the wrong symbol, Context Master suggests likely matches.

Graph Centrality

We calculate graph metrics to identify architectural pillars versus utility scripts and give the agent a heatmap of importance.

Large Repository Support #1

Work in large repos: first-time indexing can take time, however, exclusions help keep it fast. We're working hard to improve indexing speed.

Large Repository Support #2

Stay useful under tight budgets: we rank and prune context to fit a configurable token budget.

Grounded & Traceable

Outputs are anchored to real VSCode locations (uri + range), reducing hallucinations by letting the agent navigate directly to references without having to rely on regex pattern matching.

Deterministic Symbol IDs

Symbols are addressed by stable identifiers which carry semantic meaning. This helps the agent differentiate between symbols with the same name in different files.

Multi-Root Workspaces Support (Early)

We provide preliminary support for multi-root workspaces. Indexing is scoped to individual workspace folders. We're working on being able to resolve references across repository borders.

What to expect

Context Master is designed to make agents more reliable by grounding exploration in editor-resolved symbols and references. Here’s what that means in practice.

What you can rely on

Every returned symbol is anchored to a real VSCode location (uri + range).
Outputs are grounded in data returned by VS Code language providers (symbols + references), not regex scans.
Index updates incrementally as you work so context stays fresh.
Full control over indexing process through inclusions and exclusions.

What to keep in mind

The proper language extensions must be installed in VS Code for a language to be indexed.
If VSCode can’t resolve symbols/references for a language, results may be limited.
Large repos can take time to index the first time; exclusions help keep it fast.
An agent can still make incorrect decisions — Context Master reduces blind spots, it doesn’t replace review.

How it works

Initialize

Build the graph

Rank Symbols

Ask for the right context

Why it's a good idea

What to expect

Keep exploring