Alexandria

Alexandria

A Model Context Protocol (MCP) server for querying, reading, and ingesting texts from 61 public digital libraries. Works with any MCP-compatible client (Claude Desktop, Cursor, VS Code Copilot, etc.).

Tools

library_ask is the primary entry point. library_search is for targeted queries against a known source. library_index / library_ingest are for building a vector knowledge base from retrieved texts.

Sources (61)

Public Domain Literature (29)

Academic & Science (11)

Government, Law & International (5)

Specialized Corpora (3)

Research Aggregators (8)

Institutional Repositories (4)

Software Documentation (1)

Credentials

Most tools query external library APIs directly and need no credentials at all. The two optional dependencies are scoped to specific tools:

OpenAI — optional (platform.openai.com)

Required by two tools only:

• library_ask — uses gpt-4o-mini to route your natural language query to the right sources and generate optimized per-source search terms. Without this key, use library_search to query sources directly.
• library_ingest — uses text-embedding-3-small to embed chunked text before writing to the vector store.

library_list_sources, library_search, library_read, library_index, and library_recommend all work without an OpenAI key.

Supabase — optional (supabase.com)

Required by one tool only:

• library_ingest — writes chunked, embedded text into a pgvector table for semantic search. Without this, retrieved texts stay in-context and are not persisted anywhere.

Everything else — searching, reading, browsing, getting recommendations — queries external sources in real time and needs no database.

Source-specific keys

Some sources require their own API key. These are free registrations. Sources without a key listed here work without any credentials.

Setup

git clone https://github.com/suavecito585/alexandria-mcp
cd alexandria-mcp
npm install
npm run build

Copy .env.example to .env. Minimum configuration to run with no credentials (search and read only):

TRANSPORT=stdio

To enable library_ask:

TRANSPORT=stdio
OPENAI_API_KEY=sk-...

To enable library_ingest:

TRANSPORT=stdio
OPENAI_API_KEY=sk-...
SUPABASE_URL=https://your-project.supabase.co
SUPABASE_SERVICE_ROLE_KEY=eyJ...

Supabase Schema

Required only if using library_ingest:

create table if not exists knowledge_chunks (
  id bigserial primary key,
  content text not null,
  embedding vector(1536),
  mcp_name text,
  metadata jsonb,
  created_at timestamptz default now()
);

create table if not exists source_docs (
  id bigserial primary key,
  source_url text not null,
  mcp_name text not null,
  title text,
  source text,
  chunk_count int,
  indexed_at timestamptz,
  unique (source_url, mcp_name)
);

create index if not exists knowledge_chunks_embedding_idx
  on knowledge_chunks using ivfflat (embedding vector_cosine_ops)
  with (lists = 100);

Claude Desktop (stdio)

Minimum config (search and read only):

{
  "mcpServers": {
    "library": {
      "command": "node",
      "args": ["/path/to/alexandria-mcp/dist/index.js"],
      "env": {
        "TRANSPORT": "stdio"
      }
    }
  }
}

With library_ask and library_ingest enabled:

{
  "mcpServers": {
    "library": {
      "command": "node",
      "args": ["/path/to/alexandria-mcp/dist/index.js"],
      "env": {
        "TRANSPORT": "stdio",
        "OPENAI_API_KEY": "sk-...",
        "SUPABASE_URL": "https://your-project.supabase.co",
        "SUPABASE_SERVICE_ROLE_KEY": "eyJ..."
      }
    }
  }
}

Railway (HTTP)

Set env vars in the Railway dashboard and deploy:

railway up

Register in Claude Desktop:

{
  "mcpServers": {
    "library": {
      "url": "https://your-service.up.railway.app/mcp"
    }
  }
}

Health check: GET /health returns { status: "ok", sources: 61 }.

Adding Custom Providers

The pipeline is provider-agnostic. To add a new embedding model or vector store:

1. Implement EmbeddingProvider or VectorStoreProvider from src/types.ts
2. Add your implementation to src/pipeline/providers/
3. Register it in src/pipeline/providers/index.ts
4. Set EMBEDDING_PROVIDER or VECTOR_STORE_PROVIDER in your env

// Example: Ollama embedding provider
import type { EmbeddingProvider } from '../../types.js';

export class OllamaEmbeddingProvider implements EmbeddingProvider {
  readonly dimensions = 768;

  async embed(texts: string[]): Promise<number[][]> {
    // your implementation
  }
}