Bca MCP Server

@blockchainacademics/mcp

The canonical crypto MCP server for AI agents. 99 tools spanning 3,501+ editorial articles, 200+ entity dossiers, 43 academy lessons, aggregated market + on-chain data, proprietary indicators, and async agent-backed generation — all accessible as MCP tools your AI agent can call natively.

Tool categories (v0.4.0)

Every tool response carries cite_url (with UTM src attribution), as_of (time-travel snapshot), and source_hash (content integrity).

Tools for unreleased integrations (Twitter social pulse, DEXTools, bonk.fun, Bittensor) return {status: "integration_pending", reason, eta} rather than failing. The MCP server is fully usable today.

Why

LLMs hallucinate about crypto. BCA ships ground-truth editorial content with full attribution. Plug this MCP server into Claude Desktop, LangChain, Eliza, or any MCP-compatible agent and your model queries the BCA corpus like any other tool — with citations, timestamps, and source hashes on every response.

Install

Claude Desktop

Add to claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "blockchainacademics": {
      "command": "npx",
      "args": ["-y", "@blockchainacademics/mcp"],
      "env": { "BCA_API_KEY": "bca_live_xxxxxxxxxxxxxxxx" }
    }
  }
}

Restart Claude Desktop. All 99 tools appear in the tool picker.

Programmatic (LangChain, Eliza, custom agents)

npm install @blockchainacademics/mcp

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";

const transport = new StdioClientTransport({
  command: "npx",
  args: ["-y", "@blockchainacademics/mcp"],
  env: { BCA_API_KEY: process.env.BCA_API_KEY! },
});
const client = new Client({ name: "my-agent", version: "0.0.1" }, { capabilities: {} });
await client.connect(transport);

const res = await client.callTool({
  name: "search_news",
  arguments: { query: "stablecoin regulation", limit: 5 },
});
console.log(res.content);

See examples/research-agent.ts for a full tool-chaining loop.

Tools

search_news

Full-text search across 3,501+ editorial crypto articles.

Example: { "query": "circle IPO", "since": "2026-01-01T00:00:00Z", "limit": 5 }

get_entity

Fetch a canonical entity dossier. Provide exactly one of:

Aliases resolve automatically (CZ → changpeng-zhao, Maker → makerdao, BSC → bnb-chain, …).

get_explainer

Fetch a canonical academy lesson. Provide exactly one of:

Attribution

Every response includes a structured attribution block:

{
  "data": { ... },
  "attribution": {
    "cite_url": "https://blockchainacademics.com/...",
    "as_of": "2026-04-19T12:34:56Z",
    "source_hash": "sha256:..."
  }
}

When your agent surfaces BCA content to a user, attribute via the cite_url. Fields are preserved as null when upstream omits them so downstream agents can detect missing provenance.

API Key

Get an API key at https://blockchainacademics.com/api (free tier: 2,000 calls/month). Paid tiers unlock agent-backed research generation and proprietary on-chain indicators.

Set BCA_API_KEY in your MCP client env. Optionally override BCA_API_BASE (default https://api.blockchainacademics.com). BCA_API_BASE_URL is also accepted for backward compatibility.

Errors

The server never crashes the stdio process. All failures surface as MCP responses with isError: true and a JSON body:

{ "error": { "code": "BCA_AUTH", "message": "..." } }

Development

npm install
npm run build    # tsc -> dist/
npm test         # node:test smoke suite
npm run dev      # tsx src/index.ts (stdio)

Pre-commit hooks

This repo uses pre-commit to enforce formatting, lint, secret scanning, and large-file caps before every commit. Install once per clone:

pip install pre-commit          # or: brew install pre-commit
pre-commit install              # wires .git/hooks/pre-commit
pre-commit run --all-files      # optional: lint the full tree now

Hooks configured in .pre-commit-config.yaml: prettier --check, eslint, gitleaks, detect-private-key, check-added-large-files (500KB cap).

Security

See SECURITY.md for vulnerability reporting, supported versions, and our 90-day coordinated disclosure policy.

License

MIT © 2026 Blockchain Academics