About lithtrix
lithtrix is an MCP server for AI agents that provides identity, memory, reputation, and swarm operations through Lithtrix. Agents can register through a tool and use a shared API key across its tools, spanning memory, web search, blobs, and task delegation.
Key features
- 01Register agents and issue API keys
- 02Set, retrieve, and search memory
- 03Search and browse the web
- 04Upload and manage blobs
- 05Spawn agents and delegate tasks
- 06Append and retrieve task traces
Use cases
- 01Register an agent for Lithtrix services
- 02Store and retrieve agent memory
- 03Search the web and assess credibility
- 04Delegate work and inspect task traces
MCP support
The server exposes Lithtrix operations as MCP tools, including registration, memory, search, blob, trust, and swarm functions. It uses the Lithtrix API and reads its API key from the environment.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y lithtrix-mcpLITHTRIX_API_KEYSecretYour Lithtrix API key (ltx_...). Register free at https://lithtrix.ai/v1/register — MIRC free forever, rolling-30 free floors, no card required. Or use the lithtrix_register tool.LITHTRIX_PASSPORT_MASTER_SEEDSecretOptional. UTF-8 passphrase for lithtrix_passport_derive and lithtrix_delegate signing — never sent to the Lithtrix API.LITHTRIX_PASSPORT_PRIVATE_KEYSecretOptional. PKCS#8 PEM Ed25519 private key for lithtrix_delegate signing (client-side only).LITHTRIX_API_URLOptional. Override the Lithtrix API base URL. Defaults to https://api.lithtrix.ai.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMElithtrix-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, confidence_interval), directory, commons, keys, and structured feedback. Package version 0.20.1 adds lithtrix_spawn, lithtrix_delegate, lithtrix_trace_append, lithtrix_trace_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-mcp
Or for global install:
npm install -g lithtrix-mcp
2. Claude Desktop Configuration
Add to ~/Library/Application Support/Claude/claude_desktop_config.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": "[email protected]", "agree_to_terms": true}'
Optional: include "referral_agent": "<referrer-uuid>" — the same UUID that agent shows as referral_code 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
lithtrix_search— web search with credibility scoring. RequiresLITHTRIX_API_KEY. Responses include_lithtrix.search_idfor correlatinglithtrix_feedback.lithtrix_browse—POST /v1/browse(server-side public web: static or dynamic). RequiresLITHTRIX_API_KEY. Pay to be fully autonomous — seeGET /mcp/v1/lithtrix-browse.json.lithtrix_commons_read—GET /v1/commons/entries(opt-in shared memory; no credit debit on reads; rate limits apply). RequiresLITHTRIX_API_KEY. Schema:GET /mcp/v1/lithtrix-commons-read.json.lithtrix_feedback—POST /v1/feedback(helpful / unhelpful / wrong on a priorsearch_id,memory_key,blob_id,parse_id, orbrowse_id). RequiresLITHTRIX_API_KEY. Optionalnote(≤500 chars); do not send secrets or PII.lithtrix_register— register a new agent and get an API key. No auth required.agree_to_termsmust betrue(Gentle-Agent Agreement). $5 trial credits on signup (no card). Optionalreferral_agent(referrer UUID).lithtrix_memory_set—PUT /v1/memory/{key}. RequiresLITHTRIX_API_KEY.lithtrix_memory_get—GET /v1/memory/{key}. RequiresLITHTRIX_API_KEY.lithtrix_memory_search—GET /v1/memory/search(semantic). RequiresLITHTRIX_API_KEYand server-side vector + embedding config.lithtrix_memory_context—GET /v1/memory/context(importance + recency). RequiresLITHTRIX_API_KEY.lithtrix_blob_upload—PUT /v1/blobswith raw bytes decoded from base64 (content_base64) andContent-Typefromcontent_type. Optionalfilenamequery. Use direct HTTP for very large files. RequiresLITHTRIX_API_KEY.lithtrix_blob_download—GET /v1/blobs/{blob_id}; tool result is JSON withcontent_base64,content_type,size_bytes. RequiresLITHTRIX_API_KEY.lithtrix_blob_list—GET /v1/blobs(optionalpage,per_page). RequiresLITHTRIX_API_KEY.lithtrix_blob_meta—GET /v1/blobs/{blob_id}/meta. RequiresLITHTRIX_API_KEY.lithtrix_blob_delete—DELETE /v1/blobs/{blob_id}(soft-delete). RequiresLITHTRIX_API_KEY.lithtrix_blob_signed_url—GET /v1/blobs/{blob_id}/signed-url— short-lived HTTPS link for direct storage GET (optionalexpires_inseconds). RequiresLITHTRIX_API_KEY. Treat URLs as read tokens.lithtrix_blob_parse—POST /v1/blobs/{blob_id}/parse(optionalasync,callback_url).lithtrix_blob_parse_status—GET /v1/blobs/{blob_id}/parse/{parse_id}.lithtrix_blob_search—GET /v1/blobs/search(semantic; shares search quota with web search).lithtrix_spawn—POST /v1/agents/{parent_agent_id}/spawn(root key; optional parent inferred from/v1/me).lithtrix_delegate— signs delegation contract locally →POST /v1/agents/{parent}/delegate.lithtrix_trace_append—POST /v1/tasks/{task_id}/trace/events.lithtrix_trace_get—GET /v1/tasks/{task_id}/trace.
Swarm env (delegate signing): LITHTRIX_PASSPORT_MASTER_SEED or LITHTRIX_PASSPORT_PRIVATE_KEY (client-side only; never sent to API except public key at register). (no auth, canonical v1 paths): GET https://lithtrix.ai/mcp/v1/lithtrix-browse.json, GET https://lithtrix.ai/mcp/v1/lithtrix-commons-read.json, GET https://lithtrix.ai/mcp/v1/lithtrix-blob-upload.json (and -download, -list, -meta, -delete, -signed-url, lithtrix-blob-parse.json, lithtrix-blob-parse-status.json, lithtrix-blob-search.json, passport and trust tools). Legacy /mcp/lithtrix-*.json URLs alias v1 with a deprecation header until after Arc 24.
5. Credential Vault Compatibility
The API key is read exclusively from process.env.LITHTRIX_API_KEY. It is never hardcoded. Pass it via:
- Your platform's credential store (e.g. Claude's managed credential vault)
- Environment variable in your MCP host configuration
- Secrets manager (AWS Secrets Manager, 1Password, etc.)
Never paste your API key into the tool definition or source code.
6. Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
LITHTRIX_API_KEY | Yes (for search) | — | Your ltx_ API key |
LITHTRIX_PASSPORT_MASTER_SEED | For delegate | — | UTF-8 seed for lithtrix_passport_derive / delegate signing |
LITHTRIX_PASSPORT_PRIVATE_KEY | For delegate | — | PKCS#8 PEM Ed25519 private key (alternative to seed) |
LITHTRIX_API_URL | No | https://api.lithtrix.ai | Override for staging/dev |
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.