Local-first AI code intelligence. Indexes your codebase, returns minimal context bundles for LLMs. 50-70% token reduction. MCP + VS Code + CLI.
Your AI reads 10,000 lines to find 1 function. Indexa gives it exactly what it needs.
A context engine for AI coding tools. Sits between your codebase and your AI assistant — returns symbols, dependencies, and execution flows instead of full files.
Index once. Query forever. 50-70% fewer tokens.
Website | npm | GitHub | VS Code Extension
Every AI coding tool — Copilot, Claude, ChatGPT — has the same bottleneck: context. They open full files, skim hundreds of lines, burn thousands of tokens, and still miss dependencies across files.
Without Indexa:
Open file (800 lines) → find 1 function → repeat x7 files
= 10,000+ tokens burned. 30+ seconds. Missed dependencies.
Indexa indexes your codebase once, then answers any question with only the relevant symbols, their dependencies, and connections — packed within a token budget.
With Indexa:
"explain the auth flow" → 5 symbols + deps + connections
= 3,000 tokens. 2 seconds. Nothing missed.
Proven: 51% average token reduction on production codebases.
npx indexa-mcp setup
One command. Under 60 seconds. Indexes your code, configures MCP for Claude Code, runs a test query.
Indexa Setup
✓ Project: my-app (typescript / react)
✓ Indexed 87 chunks in 5.3s
✓ MCP configured
✓ Test query: found 3 results
Indexa ready!
Restart Claude Code. Ask anything:
You: "how does the theme system work"
Indexa: 3 symbols + connections = 1,789 tokens
[component] ThemeSwitcher — UI picker (4 themes)
[function] ThemeApplier — sets data-theme on <html>
[export] Theme — type definition
Connections:
ThemeSwitcher → calls → useUIStore
ThemeApplier → calls → useUIStore
Without Indexa: Read 3 full files (400+ lines, 5,000 tokens). With Indexa: 1,789 tokens. Same understanding.
You: "trace VendorAuthGuard"
Indexa: 9 steps across 5 files, 2 seconds
1. VendorAuthGuard → calls VendorFlowGuard, StaffFlowGuard
2. VendorFlowGuard → calls verifyPkceSession, setAuth
3. verifyPkceSession → calls getAppSessionCookie, isRealJwt
4. getAppSessionCookie → reads document.cookie
5. useVcAuthStore → Zustand store (sessionStorage)
This normally takes 10-15 minutes of manual file-by-file tracing.
You: "what breaks if I change UserService"
Indexa: 12 direct references, 23 transitive, 8 files affected
Direct:
[controller] UserController — src/controllers/user.ts:15
[service] AuthService — src/services/auth.ts:42
[component] UserProfile — src/components/UserProfile.tsx:8
... +9 more
Transitive impact (depth 3):
AuthService → LoginPage → App → 3 more files
You: "find dead code"
Indexa: 7 unreferenced symbols across 4 files
src/utils/legacy.ts
[function] formatOldDate (L12-28) — Unused function
[function] parseLegacyToken (L30-45) — Unused function
src/helpers/deprecated.ts
[function] oldValidate (L5-18) — Unused function
You: "find circular dependencies"
Indexa: 2 cycles detected
Cycle 1: src/auth/guard.ts → src/auth/session.ts → src/auth/guard.ts
Cycle 2: src/store/user.ts → src/store/ui.ts → src/store/user.ts
You: "find duplicate code"
Indexa: 3 pairs above 92% similarity
Pair 1 — 96.2% similar:
[function] validateUserInput — src/validators/user.ts:12-35
[function] validateAdminInput — src/validators/admin.ts:8-31
You: "review this PR"
Indexa: 4 changed files, 12 symbols, blast radius mapped
src/services/auth.ts (3 symbols)
[method] validateToken — impact: 5 direct refs, 12 files affected
[method] refreshSession — impact: 3 direct refs, 8 files affected
Key connections:
validateToken → calls → decodeJWT → verifySignature
refreshSession → calls → validateToken → updateStore
# Export to markdown — paste into ChatGPT, Claude, or any LLM
indexa export "auth flow" -o context.md
# Export as JSON — pipe to scripts, CI/CD
indexa export "payment logic" -f json | your-tool
# Copy to clipboard with structured prompt
# (VS Code: Ctrl+Shift+P → "Indexa: Copy for AI")
indexa watch
# Indexa Watch Mode — monitoring ./src
# [10:30:15] 2 files → 8 chunks indexed (total: 142)
# [10:31:02] 1 files → 3 chunks indexed (total: 145)
VS Code auto-indexes on save — no manual step needed.
| Metric | Without Indexa | With Indexa | Improvement |
|---|---|---|---|
| Tokens per question | 5,000-15,000 | 1,500-3,000 | 50-70% reduction |
| Time to understand a feature | 10-15 min | 2 seconds | 300x faster |
| Files opened to trace a flow | 5-10 files | 0 files (one query) | Zero manual work |
| Finding dead code | Hours (manual audit) | 1 command | Instant |
| Blast radius before refactor | Guess and pray | Full impact map | 100% visibility |
| PR review context gathering | 15-30 min | 1 command | 30x faster |
| Keeping index fresh | Manual re-run | Auto on save | Zero friction |
| Circular dependency detection | External tool / manual | Built in | Free |
| Duplicate code detection | External tool ($$$) | Built in | Free |
Your Code → Parser (AST) → Chunker → Embedder → .indexa/
↓
AI Query → Intent Router → Hybrid Search → Bundle → Response
↓
Semantic (35%) + BM25 (25%)
+ Name match (15%) + Path (25%)
.indexa/ per project..bak| Tool | What it does |
|---|---|
indexa_context_bundle | Start here. Code + deps + connections within token budget |
indexa_flow | Trace execution: what calls what, across files |
indexa_explain | Human-readable explanation from actual code |
indexa_search | Smart search — auto-routes by query type |
indexa_symbol | Instant lookup by name or ID |
indexa_file | All symbols in a file |
indexa_references | Find usages + blast radius |
indexa_dead_code | Unreferenced functions, methods, classes |
indexa_blast_radius | What breaks if you change a symbol |
indexa_impact_chain | Full transitive impact (deeper than blast radius) |
indexa_circular_deps | Circular dependencies between files |
indexa_unused_exports | Exports nobody imports |
indexa_duplicates | Near-duplicate code via embedding similarity |
indexa_importers | Who imports from a given file |
indexa_review_pr | Context-aware PR review |
indexa_security_scan | Deep scan grouped by OWASP domains |
indexa_index | Index or re-index a directory |
indexa_stats | Index health and stats |
Auto-configured by indexa setup. No manual .mcp.json editing.
# Setup
indexa setup # One-command setup
indexa doctor # Health check
# Search & Context
indexa search "auth middleware" # Hybrid search
indexa bundle "payment flow" # Context bundle for LLMs
indexa flow "handleLogin" # Execution flow
indexa explain "pricing system" # Code explanation
# Code Analysis
indexa dead-code # Unreferenced symbols
indexa blast-radius UserService # What breaks
indexa impact-chain UserService # Full transitive impact
indexa circular-deps # Import cycles
indexa unused-exports # Dead exports
indexa duplicates # Near-duplicate code
indexa duplicates -t 0.85 # Custom threshold
# Export & Live
indexa export "auth" -o context.md # Export context to file
indexa export "auth" -f json # Export as JSON
indexa watch # Live re-index on save
# Index Management
indexa index ./src # Full index
indexa update # Incremental via git diff
indexa clean # Remove junk chunks
indexa reindex ./src # Full clean re-index
indexa serve # REST API on :3000
Install globally: npm i -g indexa-mcp
Start with indexa serve:
| Method | Endpoint | Description |
|---|---|---|
| POST | /api/context-bundle | Symbols + deps + connections |
| POST | /api/flow | Execution flow tracing |
| POST | /api/explain | Code explanation |
| POST | /api/search | Smart search |
| GET | /api/symbol?name= | Symbol lookup |
| GET | /api/references?name= | References + blast radius |
| GET | /api/blast-radius?name= | Impact analysis |
| GET | /api/impact-chain?name=&depth= | Full transitive impact |
| GET | /api/dead-code | Unreferenced symbols |
| GET | /api/circular-deps | Circular dependencies |
| GET | /api/unused-exports | Dead exports |
| GET | /api/duplicates?threshold= | Near-duplicate code |
| GET | /api/importers?path= | File importers |
| GET | /api/file?path= | File symbols |
| GET | /api/outline?path= | File outline (no code) |
| GET | /api/symbol/:id | Symbol by ID |
| POST | /api/update | Incremental re-index |
| GET | /api/stats | Index statistics |
| GET | /api/health | Health check |
import { createIndexa } from 'indexa-mcp/sdk';
const indexa = createIndexa({ dataDir: '.indexa' });
// Search
const results = await indexa.searchCode('auth middleware');
// Context bundle for LLMs
const bundle = await indexa.contextBundle('login flow', 3000);
// Code analysis
const dead = indexa.findDeadCode();
const cycles = indexa.findCircularDependencies();
const dupes = indexa.findDuplicates(0.90);
const impact = indexa.getFullImpactChain('UserService', 5);
// Flow tracing
const flow = await indexa.traceFlow('handleLogin', 5);
Search "Indexa Code Intelligence" in VS Code, or install from VS Code Marketplace.
| Feature | What it does |
|---|---|
Ask Indexa (Ctrl+Shift+I) | Query from sidebar |
| Show Flow | Trace execution from selection |
| Find References | Usages + blast radius |
| Copy for AI | Export context to clipboard with structured prompt |
| Open for Copilot | Open relevant files so Copilot has context |
| Auto-index on save | Re-indexes automatically when you save |
| Health Check | Verify connection and index status |
Auto-starts the Indexa server. No manual terminal needed.
| Copilot | ChatGPT | Cursor | Grep | Indexa | |
|---|---|---|---|---|---|
| Understands code structure | No | No | Partial | No | Yes (AST) |
| Traces execution across files | No | No | No | No | Yes |
| Blast radius / impact analysis | No | No | No | No | Yes |
| Dead code / circular deps | No | No | No | No | Yes |
| Duplicate detection | No | No | No | No | Yes |
| Token efficient | Poor | Poor | Medium | N/A | 50-70% reduction |
| Runs 100% locally | No | No | No | Yes | Yes |
| Free forever | No | No | No | Yes | Yes |
| Works with any LLM | No | No | No | N/A | Yes (MCP/API/CLI) |
Each project gets its own isolated index. No shared state.
my-project/
.indexa/ <- index data (auto-gitignored)
embeddings.json
embeddings.json.bak <- auto-backup for recovery
metadata.json
.mcp.json <- MCP config (auto-created)
Indexa auto-classifies your query and adjusts search weights:
| You ask | Indexa detects | Search strategy |
|---|---|---|
| "how does auth work" | flow | Boost semantic |
| "explain vendor pricing" | explain | Balanced |
| "where is UserService used" | references | Boost name matching |
| "fix login bug on token" | debug | Boost semantic + path |
| "VendorAuthGuard" | symbol lookup | Direct O(1) name match |
| "payment logic" | search | Default hybrid weights |
No configuration needed.
| Guide | What you'll learn |
|---|---|
| Quick Start | Setup to first query in 60 seconds |
| Architecture | How the system works under the hood |
| CLI Reference | Every command and option |
| API Reference | REST endpoints with curl examples |
| MCP Integration | Claude Code setup and CLAUDE.md template |
| Configuration | Exclude patterns, embeddings, tuning |
| Re-indexing | Keeping the index fresh |
| Troubleshooting | Common issues and fixes |
18 MCP tools
21 CLI commands
21 API endpoints
1 SDK (programmatic API)
1 VS Code extension (auto-index, AI bridge)
23 integration tests
0 API keys required
0 cloud dependencies
MIT — free forever, no API keys, runs 100% offline.
Built by Prashant Singh.
FAQs
Local-first AI code intelligence. Indexes your codebase, returns minimal context bundles for LLMs. 50-70% token reduction. MCP + VS Code + CLI.
The npm package indexa-mcp receives a total of 7 weekly downloads. As such, indexa-mcp popularity was classified as not popular.
We found that indexa-mcp demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
NIST disclosed an unreleased AI tool called V-etalon and opened a broad inquiry into NVD modernization after years of automation plans produced no public enrichment system.
Security News
In his AI Council 2026 talk, Feross Aboukhadijeh covers recent package compromises, vulnerability discovery, and a more automated security model.
Security News
A new federal program will let vetted U.S. cybersecurity firms help investigate and disrupt foreign cybercrime groups under government direction.