README.md

March 9, 2026 · View on GitHub

    __    __  __ _____ _____ ____
   / /   / / / // ___//  _/ / __ \
  / /   / / / // /    / /  / / / /
 / /___/ /_/ // /___ _/ /  / /_/ /
/_____/\____/ \____//___/ /_____/

An intelligence layer grounding autonomous agents in verified, real-time knowledge at scale.

What is Lucid?

AI agents hallucinate. They reference deprecated APIs, recommend outdated package versions and state "facts" from stale training data. Lucid fixes this by giving agents a real-time knowledge layer. Every response grounded in verified, live information.

Lucid runs as an MCP server that exposes four tools. When an agent needs documentation, package info, fact verification or API references, it queries Lucid instead of guessing from training data. Skills auto-trigger these tools based on conversation context so the agent doesn't even need to be asked.

Install

Claude Code Plugin

/plugin marketplace add get-Lucid/Lucid

Then install:

/plugin install lucid

OpenClaw Skills

openclaw skills install https://github.com/get-Lucid/Lucid

This installs all five skills (lucid-docs, lucid-packages, lucid-grounding, lucid-api, lucid-freshness) from the skills/ directory.

Setup

Get an API key at getlucid.tech/app
Set your key:

export LUCID_API_KEY=lk_your_key_here

That's it. The MCP server reads the key from your environment and authenticates every request.

Tools

Tool	What it does
`lucid_search_docs`	Search real-time documentation for any language, framework or library
`lucid_check_package`	Check latest versions, changelogs and compatibility
`lucid_verify_fact`	Verify technical claims against live sources before stating them as fact
`lucid_fetch_api_ref`	Fetch current API references with type signatures and usage examples

Example calls

lucid_search_docs({ query: "react useEffect cleanup", language: "typescript" })
lucid_check_package({ name: "next", registry: "npm" })
lucid_verify_fact({ claim: "Bun is faster than Node for HTTP servers" })
lucid_fetch_api_ref({ library: "stripe", symbol: "PaymentIntent.create" })

Skills

Skills automatically trigger the right tools based on what the user is asking. No manual invocation needed.

Skill	Triggers on	Tool used
`lucid-docs`	Documentation, API reference, "how to use"	`lucid_search_docs`
`lucid-packages`	Install, package, dependency, version	`lucid_check_package`
`lucid-grounding`	Verify, "is this true", accurate, up to date	`lucid_verify_fact`
`lucid-api`	API, endpoint, function signature, types	`lucid_fetch_api_ref`
`lucid-freshness`	Write code, implement, create, build	All tools

How It Works

User asks a question
        ↓
Skill detects the intent
        ↓
Tool queries Lucid API
        ↓
Lucid returns verified, real-time data
        ↓
Agent responds with grounded information

The agent never falls back to training data for anything Lucid can verify. If the docs say one thing and training data says another, the docs win.

Pricing

20 USDC/month payable on Solana or Base.

Subscribe and manage your key at getlucid.tech/app.

Troubleshooting

API key not working Make sure your subscription is active at getlucid.tech/app.

Tools not appearing Rebuild the MCP server:

cd mcp-server && npm run build

Connection errors Check that LUCID_API_KEY is set in your environment and the API is reachable.

License

MIT