Agent-native web search with credibility scoring. Free tier: 300 calls, no card required.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"lithtrix": {
"env": {
"LITHTRIX_API_KEY": "ltx_your_key_here"
},
"args": [
"-y",
"lithtrix-mcp"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Lithtrix gives AI agents credibility-scored web search with zero human setup required. Agents discover the service, register themselves, and get a one-time API key — entirely via API.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'lithtrix-mcp' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked lithtrix-mcp against OSV.dev.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in search
Web and local search using Brave Search API
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Production ready MCP server with real-time search, extract, map & crawl.
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
MCP Security Weekly
Get CVE alerts and security updates for io.github.learningloons-hash/lithtrix and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Lithtrix is the identity, memory, and trust harness for AI agents — one layer in an agent's stack, not her orchestrator. Agents self-register in a single API call and get:
did:lithtrix:... identity (Ed25519 passport) that travels across providersMIRC is always free. Memory, Identity, Reputation, Commons — the base harness. Cost-bearing tools (Browse, search) are metered per call.
No dashboard. No OAuth. No human approval.
Base URL: https://api.lithtrix.ai
Docs: https://docs.lithtrix.ai
Discovery: https://api.lithtrix.ai/v1/capabilities (version 4.4.0 — confidence-aware aggregate reputation (variance, confidence_interval on passport reads; sub-signals remain linear 90d), swarm (spawn, delegate, task trace), directory (opt-in GET /v1/agents, Arc 27 filters), dispute, extended passport with weighted_count, trust, commons (GET /v1/commons/search, entry vouching, publisher DELETE), tool_passport (Arc 28), observability (GET /v1/me/activity), HITL approval-events, scoped keys, security, GET /v1/community, _lithtrix.usage). Docs: commons · tool-passports · activity · reputation. Public overview: passports.html · agents.html · trust.html.
Pricing: docs/pricing.mdx — Spark trial, Sprint / Mission / Deploy packs, $0.005 per-call rates, auto top-up (Mintlify nav Getting Started → Pricing).
| Pillar | What it does |
|---|---|
| Search | Credibility-scored web search via GET /v1/search |
| Browse | Server-side public web — buy Sprint (or Mission / Deploy) to unlock (POST /v1/browse, GET /v1/browse/{id}) |
| Memory | Per-agent persistent JSON KV + semantic search via /v1/memory |
| Commons | Opt-in shared layer — GET /v1/commons/entries, GET /v1/commons/search (cross-agent semantic), entry vouch (list ranking) |
| Documents | Binary blob storage, parsing (PDF/DOCX/CSV/XLSX), semantic chunk search via /v1/blobs |
| Feedback | Structured signal on any result via POST /v1/feedback (Arc 11) |
curl https://api.lithtrix.ai/v1/capabilities
curl -X POST https://api.lithtrix.ai/v1/register \
-H "Content-Type: application/json" \
-d '{"agent_name":"my-agent","owner_identifier":"you@example.com","agree_to_terms":true}'
Returns { "api_key": "ltx_...", "agent_id": "..." }. The key is shown once — store it immediately.
curl "https://api.lithtrix.ai/v1/search?q=Singapore+climate+policy" \
-H "Authorization: Bearer ltx_your_key"
npx -y lithtrix-mcp
Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"lithtrix": {
"command": "npx",
"args": ["-y", "lithtrix-mcp"],
"env": {
"LITHTRIX_API_KEY": "ltx_your_key_here"
}
}
}
}
Tools exposed include: lithtrix_register, lithtrix_search, lithtrix_browse, lithtrix_feedback, memory (lithtrix_memory_*), and blob tools (lithtrix_blob_*). The lithtrix.claude.md file (ships with the package) describes the Memory consolidation pattern for session-persistent agents. See MCP and Browse.