vibe-pilot
Provides the same stdio MCP tools to Windsurf through its Codeium mcp_config.json, letting the agent pull a pruned repo brief, focus-ranked file lists, and dead-code/entry-point signals before exploring a codebase.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
vibe-pilot
The context optimizer for AI engineers. Prunes boilerplate, compresses the dependency tree, and generates a focused .context/ brief — before you feed your codebase to Cursor, Claude Code, or Windsurf.
300.6M raw tokens → 877k brief tokens (−99.7%) measured across 21 real reposDemos
vibe-pilot scan — what your repo costs an agent, in milliseconds:

vibe-pilot focus scanner gitignore — rank files around a topic, 1-hop neighbors included:

vibe-pilot mcp — the same engine as an MCP server over stdio:

Related MCP server: TokenLighten
The problem
Modern agents are context-limited and context-expensive. Drop a real repository into Cursor or Claude Code and you get:
token burn — lockfiles, snapshots, fixtures, and vendored code you pay for on every turn;
noise — 128k files across 21 popular repos average 14M tokens of raw text, while the task usually touches 20–50 files;
no priorities — the agent can't tell the file you edited yesterday from a 3-year-old fixture.
vibe-pilot fixes the input, not the model: it scans your repo, builds the JS/TS + Python import graph, reads git hotspots, and emits a compact .context/ package your agent reads first.
60-second quick start
npm install -g vibe-pilot
cd your-project
# 1. see what your repo costs an agent (read-only)
vibe-pilot scan
# 2. generate the .context/ briefing package
vibe-pilot context
# 3. point your agent at it — e.g. add to your prompt:
# "Read .context/PROJECT.md first, use .context/files.json as the file index."vibe-pilot init writes a vibe-pilot.config.json and adds .context/ to your .gitignore in one step.
What you get
.context/ contains exactly four files:
file | what it is | who reads it |
| AI briefing: what the project is, entry points, hot files, focus area, dead-code candidates, stats table | humans + agents (start here) |
| pruned source tree with | agents doing discovery |
| tiered machine index of every file: class, tokens, hot commits, focus score, import counts | agents doing lookups |
| generation manifest + stats (reproducibility, CI checks) | tooling |
Nothing else. No lockfiles, no fixtures, no node_modules, no generated bundles — gitignore-aware, with built-in boilerplate rules and a 512KB oversize guard.
How it works
flowchart LR
subgraph interfaces
CLI["vibe-pilot CLI"]
MCP["MCP server (stdio)"]
end
subgraph engine["core engine"]
S["scanner<br/>gitignore + 7-class<br/>file classification"]
G["import graph<br/>JS/TS + Python<br/>workspaces · tsconfig paths"]
H["hotspots<br/>git log + focus<br/>1-hop neighborhood"]
E["context builder<br/>token budget<br/>tiered index"]
end
CLI --> S
MCP --> S
S --> G --> H --> E
E --> OUT[(".context/<br/>PROJECT.md · tree.txt<br/>files.json · manifest.json")]
OUT --> AG["Cursor · Claude Code<br/>Windsurf · any LLM"]scan — walk the repo honoring
.gitignoreplus built-in boilerplate rules (node_modules/,dist/,__pycache__/, lockfiles,*.min.*, …), classify every file into 7 classes, estimate raw token cost.graph — parse JS/TS and Python imports, resolve relative paths, tsconfig path aliases, and monorepo workspace packages (
@scope/pkg), detect entry points (package.jsonmain/exports/bin, withdist/→src/fallback), then run a reachability analysis: anything unreachable is a dead-code candidate.hot —
git log --name-onlyover the last 30 days finds hotspots; a focus query boosts matches and their 1-hop import neighbors at half weight.context — assemble the four artifacts under a token budget (balanced: 60k), trimming the tree and the index from the bottom until it fits.
Full-resolution diagram: docs/assets/architecture.svg.
CLI reference
vibe-pilot scan [root] read-only cost report: classes, tokens, entries, hot, cold
vibe-pilot context [root] generate .context/ (the main command)
vibe-pilot focus <query…> rank files around a topic, incl. 1-hop neighbors
vibe-pilot init [root] write vibe-pilot.config.json + gitignore .context/
vibe-pilot mcp start the MCP server on stdio
options: --json · -p/--profile conservative|balanced|aggressive
--focus <query> · --hot-days <n> · --no-write · --out <dir>Profiles:
profile | file cap | classes kept | hot window | token budget |
| 1MB | source, test, config, docs, assets, data | 60d | 150k |
| 512KB | source, test, config, data | 30d | 60k |
| 256KB | source, test | 14d | 25k |
Use it as an MCP server
One binary, four tools (vibe_pilot_scan, get_context, focus, list_files). Results are truncated to ~24k characters so a tool call can never blow the context window, and diagnostics go to stderr — stdout stays a clean JSON-RPC stream.
Claude Code
claude mcp add vibe-pilot -- npx -y vibe-pilot mcpor in .mcp.json / claude_desktop_config.json:
{
"mcpServers": {
"vibe-pilot": {
"command": "npx",
"args": ["-y", "vibe-pilot", "mcp"]
}
}
}Cursor — ~/.cursor/mcp.json, same JSON block as above.
Windsurf — ~/.codeium/windsurf/mcp_config.json, same JSON block as above.
Then ask your agent things like "scan this repo and tell me where the dead code is" or "get the context brief for the payment module" and it will call vibe-pilot itself.
Benchmark
21 real repositories, shallow clones, balanced profile, single run on a laptop — raw text cost vs. the shipped .context/ brief. Raw data: docs/benchmark.json.
repo | files | raw tokens | brief tokens | reduction | time |
20,795 | 88.2M | 54.2k | −99.9% | 6090ms | |
7,274 | 10.8M | 49.1k | −99.5% | 764ms | |
32,149 | 27.6M | 56.9k | −99.8% | 5663ms | |
704 | 1.7M | 33.3k | −98.1% | 76ms | |
11,706 | 31.4M | 52.0k | −99.8% | 1364ms | |
8,030 | 16.1M | 51.0k | −99.7% | 1225ms | |
12,419 | 25.3M | 52.0k | −99.8% | 2050ms | |
2,980 | 4.6M | 54.1k | −98.8% | 280ms | |
5,066 | 15.9M | 54.0k | −99.7% | 436ms | |
563 | 1.5M | 27.5k | −98.2% | 55ms | |
532 | 1.3M | 20.7k | −98.4% | 34ms | |
65 | 554.2k | 3.6k | −99.3% | 9ms | |
216 | 184.0k | 10.4k | −94.3% | 14ms | |
3,081 | 7.9M | 56.1k | −99.3% | 278ms | |
6,764 | 25.0M | 56.4k | −99.8% | 1092ms | |
3,278 | 12.0M | 57.4k | −99.5% | 474ms | |
7,029 | 12.6M | 50.2k | −99.6% | 519ms | |
3,243 | 9.0M | 58.3k | −99.4% | 137ms | |
128 | 1.1M | 6.0k | −99.5% | 11ms | |
1,869 | 6.3M | 55.2k | −99.1% | 179ms | |
414 | 1.5M | 18.6k | −98.8% | 70ms | |
21 repos total | 128,305 | 300.6M | 877.1k | −99.7% | 9ms–6.1s (median 280ms) |
Token counts are bytes/4 estimates for code and bytes/3 for dense formats (JSON/YAML/lockfiles) — a deliberately conservative heuristic, not a tokenizer clone.
Development
git clone https://github.com/renniyy/vibe-pilot && cd vibe-pilot
npm install
npm test # 12 tests in 7 suites, incl. a full MCP stdio JSON-RPC handshake
npm run bench # re-run the 21-repo benchmark (clones into repos/, ~1.5GB)Roadmap
v0.2 —
--watchmode; Go and Rust import graphs; GitHub Action that commits a refreshed.context/on PRs; per-workspace profiles for monorepos.ideas — blame-weighted focus; docstring extraction into PROJECT.md;
get_contextstreaming for huge monorepos.
License
MIT © renniyy
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Code-map tools for AI agents: see a repo's structure first, then edit only what matters.
Securely search and manage workspace context files for AI agents and teams.
Repo intel for AI coding agents: overview, PRs, contributors, hot files, CI, deps. Remote MCP.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to query a codebase as a knowledge graph, providing token-budgeted context, search, and impact analysis via MCP tools.27 PyPIMIT
- FlicenseNot gradedqualityBmaintenanceLocal-first MCP toolkit that provides coding agents focused repository context via read_file, search_files, and edit_file tools, reducing token usage and task cost.2-
- AlicenseNot gradedqualityBmaintenanceEnables AI coding agents to retrieve token-budgeted project context, search code symbols, look up definitions, and access project memory and cross-project learnings through local MCP tools. It reduces redundant exploration by supplying the smallest useful context from a deterministic, local-first index.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI coding agents to retrieve repository context through stdio-based MCP tools, including ranked repo maps, context packs, and live symbol search.6 npmMIT