Lithtrix — Identity, Memory & Trust for AI Agents MCP server
ai.lithtrix/lithtrix-mcp·v0.20.2·1 starsIdentity, memory, trust, and swarm primitives for AI agents. MIRC base always free.
1 stars351 downloads/wk
Reviews
Write oneNobody has reviewed Lithtrix — Identity, Memory & Trust for AI Agents yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Lithtrix — Identity, Memory & Trust for AI Agents tools (3, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
lithtrix_blob_parsewrite actionPOST /v1/blobs/{blob_id}/parse — extract text/tables; set async=true for QStash. Optional callback_url in JSON body. Requires LITHTRIX_API_KEY.
lithtrix_blob_parse_statusGET /v1/blobs/{blob_id}/parse/{parse_id} — poll parse status. Requires LITHTRIX_API_KEY.
lithtrix_blob_searchGET /v1/blobs/search — semantic search over parsed chunks; shares quota with web search. Requires LITHTRIX_API_KEY.
Public scan report
scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it
- Code scan19 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 99 days ago8/15
- Maintainer identityregistry namespace matches repository owner; website matches verified namespace9/10
How Lithtrix — Identity, Memory & Trust for AI Agents compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 74/100
- higher than 40% of 48,255 servers
- Tools
- 3
- the typical server has 7
- Tools that change things
- 33%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 1
- more than 65% of 28,688 servers
- Downloads a week
- 351
- more than 83% of 12,191 servers with a package
What its tools let an agent do: 2 read · 1 change
Install Lithtrix — Identity, Memory & Trust for AI Agents in Claude Code, Cursor or VS Code
Runs npx -y lithtrix-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add lithtrix-mcp -- npx -y lithtrix-mcp
What the publisher says
From the Lithtrix — Identity, Memory & Trust for AI Agents repository's README, as published. We do not edit it. Read it on GitHub
lithtrix-mcp
MCP server for Lithtrix — the identity, memory, and trust harness for AI agents. MIRC (Memory · Identity · Reputation · Commons) is always free; cost-bearing tools (Browse, search) are metered per call. Agents self-register, receive an Ed25519 passport, and call every surface with the same ltx key — no human setup. Ships lithtrix.claude.md** for Claude / Cursor project context (same repo path as this package).
Aligned with API discovery version 4.4.0 (GET https://api.lithtrix.ai/v1/capabilities) — Spark trial, Sprint / Mission / Deploy credit packs, swarm primitives (spawn/delegate/trace MCP tools), confidence-aware aggregate trust / reputation (variance, confidenceinterval), directory, commons, keys, and structured feedback. Package version 0.20.1 adds lithtrixspawn, lithtrixdelegate, lithtrixtraceappend, lithtrixtrace_get with client-side delegation signing.
MCP tool JSON: canonical GET https://lithtrix.ai/mcp/v1/lithtrix-.json. Legacy GET https://lithtrix.ai/mcp/lithtrix-.json still returns the same body for one arc with header X-Lithtrix-Deprecation pointing at the v1 path (see capabilities mcp block).
1. Installation
npx -y lithtrix-mcpOr for global install:
npm install -g lithtrix-mcp2. Claude Desktop Configuration
Add to ~/Library/Application Support/Claude/claudedesktopconfig.json:
{
"mcpServers": {
"lithtrix": {
"command": "npx",
"args": ["-y", "lithtrix-mcp"],
"env": {
"LITHTRIX_API_KEY": "ltx_your_key_here"
}
}
}
}3. Getting an API Key
Use the lithtrix_register tool first — no API key needed. Or call the API directly:
curl -X POST https://lithtrix.ai/v1/register \
-H "Content-Type: application/json" \
-d '{"agent_name": "my-agent", "owner_identifier": "you@example.com", "agree_to_terms": true}'Optional: include "referralagent": "" — the same UUID that agent shows as referralcode on GET /v1/me (stored for signup attribution; trial search is credit-gated, not a +call bonus). New agents get $5 in trial credits (no card).
The returned api_key is shown once. Store it securely.
4. Tools Exposed
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Lithtrix — Identity, Memory & Trust for AI Agents: common questions
- Is Lithtrix — Identity, Memory & Trust for AI Agents MCP server safe?
- Mostly: it is graded B (74/100). Read the Lithtrix — Identity, Memory & Trust for AI Agents safety report
- How do I install Lithtrix — Identity, Memory & Trust for AI Agents?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Lithtrix — Identity, Memory & Trust for AI Agents need an API key?
- Yes. The registry entry asks for
LITHTRIX_API_KEY. - Is Lithtrix — Identity, Memory & Trust for AI Agents maintained?
- The last commit was 137 days ago (2026-06-20). The latest release is v0.20.2.
- How does Lithtrix — Identity, Memory & Trust for AI Agents compare with other MCP servers?
- safety score 74/100 (higher than 40% of 48,255 servers); tools 3 (the typical server has 7); tools that change things 33% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.