About Nia
Nia is an MCP server published by nozomio-labs in the Developer Tools category: nia is a context-augmentation layer for agents, primarily designed for coding agents. It provides them with an up-to-date knowledge base and improves their performance by 27%. It has been installed 0 times through Conduid.
The repository has 43 stars and 5 forks, with the last commit 7 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues (0) before depending on it in production.
Install
npx niaThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
Ask AI about Nia
Powered by Claude · Grounded in docs
Security checks
- ·README presentNot checked yet.
- ·License declaredNot checked yet.
- ·Tests presentNot checked yet.
- ·Dependencies pinnedNot checked yet.
- ·No dynamic code executionNot checked yet.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
README
Nia - Index Anything. Search It with AI.
Index docs, repos, PDFs, and datasets -- then search them with AI. Backed by Y Combinator ($6.2M raised)
Nia lets you index docs, repos, PDFs, datasets, spreadsheets, Slack, Google Drive, and more -- then gives your AI agent a search API to query them. Your agent gets real answers instead of hallucinations.
What is Nia?
Nia is an API layer that gives agents up-to-date, continuously monitored context across repositories, documentation, PDFs, datasets, Slack, Google Drive, and local knowledge sources. It handles indexing, search, reading, research, and handoffs so agents can work from real source material instead of guesswork.
You can use it with agents like Cursor or Claude Code as an MCP server, or build your own applications with the Nia API.
Core Capabilities:
- Universal Indexing - Index GitHub repos, documentation sites, PDFs, arXiv papers, HuggingFace datasets, spreadsheets, and local folders
- Universal Search - Sub-5s semantic search across all indexed sources
- Package Search - Search 150M+ pre-indexed documents from PyPI, NPM, Crates.io, and Go modules -- no indexing required
- Document Agent - Deploy an autonomous AI agent into any indexed PDF or document for deep research with cited answers
- Data Extraction - Extract structured data from PDFs into JSON using custom schemas
- Tracer - Search GitHub code without indexing using specialized sub-agents (Fast mode with Haiku, Deep mode with Opus)
- Oracle Research Agent - Autonomous deep research across codebases and documentation
- Context Sharing - Save plans, discoveries, and conversation state between different agents
- Connectors - Integrate Notion, Confluence, and other external sources via OAuth/API key
- Google Drive Integration - Browse, select, index, and keep Drive content synced
- Slack Search - Index Slack workspaces and search conversations semantically
- E2E Encryption - Zero-knowledge sync for iMessage, WhatsApp, Apple Notes, Contacts, and more
- Local Sync - Sync local folders, databases, and chat history with continuous monitoring
- Scoped MCP - Create task-specific MCP surfaces for focused workflows
- Auto-Sync - Sources are continuously monitored and updated automatically
- API & MCP - Available as an API or MCP server for any agent
Example: Using Nia in Cursor with Package and Documentation Search
Quick Start
One-Command Install (Under 1 minute)
npx nia-wizard@latest
This wizard handles everything:
- Creates your account or logs you in
- Generates your API key automatically
- Auto-detects and configures your IDE
- Works for Cursor, VS Code, Claude Code, Windsurf, and 30+ other agents
Alternative methods:
pnpx nia-wizard@latest # pnpm
bunx nia-wizard@latest # bun (fastest)
yarn dlx nia-wizard@latest # yarn
Supported Agents
Nia works with 30+ agents including:
| Agent | Agent | Agent |
|---|---|---|
| Cursor | VS Code | Claude Code |
| Windsurf | Cline | Continue.dev |
| Claude Desktop | Zed | JetBrains AI |
| OpenAI Codex | Copilot CLI | Gemini CLI |
| Amazon Q | Roo Code | Kilo Code |
| Qwen Coder | Mistral Vibe | And many more... |
See our full setup guide for all supported agents.
Source Types
Nia can index and search across a wide range of knowledge sources:
| Source Type | How to Index | Notes |
|---|---|---|
| Code & Repositories | index or Tracer |
Grep, semantic search, file trees |
| Documentation Sites | index on any URL |
llms.txt aware, supports crawl filters |
| PDFs & Research Papers | index on PDF/arXiv URL |
Section-aware retrieval, Document Agent |
| HuggingFace Datasets | index on dataset URL |
Row-level search, schema discovery |
| Google Drive | OAuth integration | Docs, Sheets, Slides, PDFs with incremental sync |
| Spreadsheets | index CSV/TSV/XLSX/XLS |
Row-aware, header-aware indexing |
| Slack | Workspace integration | Real-time sync via Events API |
| X (Twitter) | Account indexing | Semantic search over posts and threads |
| Local Folders | index(folder_path=...) |
Continuous sync available |
| Connectors | Notion, Confluence, etc. | OAuth and API key auth with scheduled sync |
| E2E Encrypted | TypeScript SDK | iMessage, WhatsApp, Notes, Contacts, Reminders |
Key Features
Document Agent
Deploy an autonomous AI agent into any indexed PDF or document. It plans its own research strategy, navigates document structure, and produces answers with section-aware citations. Supports structured JSON output and streaming.
Data Extraction
Extract structured records from PDFs -- financial filings, invoices, spec sheets, engineering drawings. Three modes: table extraction, visual element detection, and engineering extraction.
Tracer
Search GitHub code without indexing. Tracer delegates tasks to specialized sub-agents operating in parallel. Fast mode (Haiku) for quick lookups, Deep mode (Opus 1M context) for thorough investigations.
Package Search (No Indexing Required)
Search 150M+ pre-indexed documents from PyPI, NPM, Crates.io, and Go modules. Regex and semantic search across public package source code.
Oracle Research Agent
Autonomous deep research across codebases and documentation. Chains multiple searches and builds dynamic knowledge trees for complex questions.
Context Sharing
Save plans, discoveries, edited files, and conversation state so another agent can pick up where you left off. Supports scratchpad, episodic, fact, and procedural memory types.
Connectors
Integrate external data sources through a unified framework. Supports Notion, Confluence, and more with OAuth/API key authentication, scheduled syncing, and status monitoring.
E2E Encryption
Zero-knowledge sync for personal data -- iMessage, WhatsApp, Apple Notes, Contacts, Reminders, Stickies, and Screenshots. Plaintext never leaves your device.
Use Cases
Developers are building diverse applications with Nia's API:
- Community forum search (Cursor Forum Search -- 5,000+ pages indexed)
- Knowledge base Q&A (Paul Graham Essays, Naval Wisdom)
- Document archives (Epstein Archive, legal research)
- Blog search (Simon Willison's Weblog -- 4,500+ posts)
- Dataset exploration (HuggingFace datasets)
- Code review agents that fetch up-to-date documentation on demand
- Law research agents indexing legal PDFs
- PDF book agents for students and researchers
- Custom search engines for any content
See trynia.ai/use-cases for featured projects.
Enterprise Ready
- SOC-2 Compliance for enterprise customers
- SLA Guarantees with dedicated support
- Self-hosted deployment for complete data sovereignty
- No AI training -- your data is never used to train external models
- E2E encryption and advanced data handling
- Custom infrastructure and security options
Community & Support
Report Issues
Found a bug or have a feature request? We'd love to hear from you!
Resources
- Documentation - Complete setup guides, capabilities, and API reference
- Get API Key - Start using Nia today
- Discord Community - Join our community
- API Reference - Build custom agents with Nia API
Enterprise Contact
Need enterprise features, custom deployment, or have questions about SOC-2 compliance?
Contact Founders: founders@nozomio.com
Privacy & Security
- SOC-2 Compliance for enterprise customers
- No AI training - Your data is never used to train external AI models
- E2E encryption available for sensitive personal data
- Data opt-out from AI providers (Anthropic, OpenAI, Gemini) -- they do not store or train on your data
- 350+ exclusion patterns protect sensitive files from being synced
Pricing
| Feature | Free | Builder | Team | Business | Enterprise |
|---|---|---|---|---|---|
| Price | $0 | $15/month | $50/seat/month | $99/seat/month | Custom |
| Queries | 50/month | 1,000/month | 5,000/month | Unlimited | Unlimited |
| Web Searches | 20/month | 200/month | 1,000/month | Unlimited | Unlimited |
| Package Search | 50/month | Unlimited | Unlimited | Unlimited | Unlimited |
| Contexts | 5 | 100 | 1,000 | Unlimited | Unlimited |
| Deep Research | Credits only | 30/month | 200/month | Unlimited | Unlimited |
| Oracle | Credits only | 30/month | 200/month | Unlimited | Unlimited |
| Tracer | Credits only | 30/month (3 concurrent) | 200/month (10 concurrent) | Unlimited (50 concurrent) | Unlimited (100 concurrent) |
| Indexing | 3 lifetime | 50/month | 500/month | Unlimited | Unlimited |
| Concurrent Indexes | 1 | 5 | 50 | Unlimited | Unlimited |
| SOC 2 | - | - | - | - | Yes |
| SLA | - | - | - | - | Yes |
| Dedicated Support | - | - | - | Yes | Yes |
Credit Packs - Need more? Buy credits on-demand. Credits never expire.
| Pack | Credits | Price | Per Credit |
|---|---|---|---|
| Starter | 100 | $3 | $0.030 |
| Plus | 300 | $7 | $0.023 |
| Developer | 1,000 | $18 | $0.018 |
| Growth | 5,000 | $50 | $0.010 |
| Scale | 30,000 | $149 | $0.005 |
| Max | 100,000 | $499 | $0.005 |
Credit Costs per Operation:
| Operation | Credits |
|---|---|
| Search & Context | 1 |
| Indexing & Sync | 10 |
| Deep Research | 10 |
| Oracle | 15 |
| Tracer | 15 |
See full pricing details for more information.
Made with care by Nozomio Labs in San Francisco
README mirrored from the source repository 3 months ago. The original is authoritative.