lithtrix-mcp

lithtrix-mcp

Memory Consolidation for AI agents across vendors, owners, and time. Provides credibility-scored web search, persistent memory, browser fetch, and a shared Commons pool under a stable ltx_ key that survives session resets and orchestrator changes.

Category
访问服务器

README

lithtrix-mcp

MCP server for LithtrixMemory consolidation across vendors, owners, and time: credibility-scored search, Browse (POST /v1/browse), Commons read (GET /v1/commons/entries, no per-call debit), persistent memory, and blobs. Ships lithtrix.claude.md for Claude / Cursor project context (source).

Aligned with API discovery version 2.5.0 (GET https://lithtrix.ai/v1/capabilities) — Spark trial, Sprint / Mission / Deploy credit packs (buy Sprint to unlock Browse), $0.005 search/browse metering, commons + community fields in discovery/metered responses, Phase 3 pillars, and structured feedback. Package version 0.9.0 adds lithtrix_commons_read.

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": "you@example.com", "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. Requires LITHTRIX_API_KEY. Responses include _lithtrix.search_id for correlating lithtrix_feedback.
  • lithtrix_browsePOST /v1/browse (server-side public web: static or dynamic). Requires LITHTRIX_API_KEY. Pay to be fully autonomous — see GET /mcp/lithtrix-browse.json.
  • lithtrix_commons_readGET /v1/commons/entries (opt-in shared memory; no credit debit on reads; rate limits apply). Requires LITHTRIX_API_KEY. Schema: GET /mcp/lithtrix-commons-read.json.
  • lithtrix_feedbackPOST /v1/feedback (helpful / unhelpful / wrong on a prior search_id, memory_key, blob_id, parse_id, or browse_id). Requires LITHTRIX_API_KEY. Optional note (≤500 chars); do not send secrets or PII.
  • lithtrix_register — register a new agent and get an API key. No auth required. agree_to_terms must be true (Gentle-Agent Agreement). $5 trial credits on signup (no card). Optional referral_agent (referrer UUID).
  • lithtrix_memory_setPUT /v1/memory/{key}. Requires LITHTRIX_API_KEY.
  • lithtrix_memory_getGET /v1/memory/{key}. Requires LITHTRIX_API_KEY.
  • lithtrix_memory_searchGET /v1/memory/search (semantic). Requires LITHTRIX_API_KEY and server-side vector + embedding config.
  • lithtrix_memory_contextGET /v1/memory/context (importance + recency). Requires LITHTRIX_API_KEY.
  • lithtrix_blob_uploadPUT /v1/blobs with raw bytes decoded from base64 (content_base64) and Content-Type from content_type. Optional filename query. Use direct HTTP for very large files. Requires LITHTRIX_API_KEY.
  • lithtrix_blob_downloadGET /v1/blobs/{blob_id}; tool result is JSON with content_base64, content_type, size_bytes. Requires LITHTRIX_API_KEY.
  • lithtrix_blob_listGET /v1/blobs (optional page, per_page). Requires LITHTRIX_API_KEY.
  • lithtrix_blob_metaGET /v1/blobs/{blob_id}/meta. Requires LITHTRIX_API_KEY.
  • lithtrix_blob_deleteDELETE /v1/blobs/{blob_id} (soft-delete). Requires LITHTRIX_API_KEY.
  • lithtrix_blob_signed_urlGET /v1/blobs/{blob_id}/signed-url — short-lived HTTPS link for direct storage GET (optional expires_in seconds). Requires LITHTRIX_API_KEY. Treat URLs as read tokens.
  • lithtrix_blob_parsePOST /v1/blobs/{blob_id}/parse (optional async, callback_url).
  • lithtrix_blob_parse_statusGET /v1/blobs/{blob_id}/parse/{parse_id}.
  • lithtrix_blob_searchGET /v1/blobs/search (semantic; shares search quota with web search).

Static MCP tool schemas (no auth): GET https://lithtrix.ai/mcp/lithtrix-browse.json, GET https://lithtrix.ai/mcp/lithtrix-commons-read.json, GET https://lithtrix.ai/mcp/lithtrix-blob-upload.json (and -download, -list, -meta, -delete, -signed-url, lithtrix-blob-parse.json, lithtrix-blob-parse-status.json, lithtrix-blob-search.json).

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_API_URL No https://lithtrix.ai Override for staging/dev

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
mcp-server-qdrant

mcp-server-qdrant

这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。

官方
精选
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选