research-mcp
MCP server exposing ATLAS research capabilities: live tokenized stock market data, on-chain source-of-truth reads, and published research atlases. Connects to MCP clients over stdio with no API keys required for public testnet endpoints.
README
research-mcp
MCP server that exposes ATLAS research capability to other agents: live tokenized stock data on Robinhood Chain, on-chain source-of-truth reads, and the research atlases published by the autonomous ATLAS agent. Any MCP capable client (Claude Code, Claude Desktop, custom agents) connects over stdio.
Works out of the box against the public Robinhood Chain testnet endpoints, no API keys needed.
Tools
Market data:
list_markets: the tokenized stocks on the chain, discovered by merging the Blockscout ERC-20 index (ranked by holders) with GeckoTerminal's trading pools (ranked by liquidity), each classified as equity or notget_token_market: price, 1h/24h change, market cap, liquidity, and volume for a ticker or contract address, via GeckoTerminalchain_tvl: the chain's TVL landscape from DefiLlama, with DEX venues and the RWA category called out
On-chain source of truth:
get_token_supply: ERC-20 total supply read directly from chain JSON-RPC at the current blockverify_token_contract: bytecode, on-chain name/symbol/decimals, block, and chain id for an addressget_token_holders: holder count and top-10 concentration from the Blockscout index
Published research (set ATLAS_API_URL to a running ATLAS deployment):
list_research_atlases: the agent's published research atlases, newest firstget_observation_history: the agent's recorded time series for a ticker,chain-tvl, or a contract addressget_agent_status: model, chain config, publish interval, and memory stats
Tickers resolve through discovery, so TSLA finds the tokenized Tesla contract without a hand written registry. Classification is a heuristic over symbol and name (issuer suffixes, tokenized-equity wording, and company-name corroboration for plain names like "Tesla"), so anything surprising can be verified on chain with verify_token_contract.
Setup
npm install
npm run build
Configuration
All optional, via environment variables:
| Variable | Default | Purpose |
|---|---|---|
CHAIN_NAME |
Robinhood Chain |
Display name used in tool output |
GECKOTERMINAL_NETWORK |
robinhood |
GeckoTerminal network slug |
DEFILLAMA_CHAIN |
Robinhood Chain |
DefiLlama chain name |
RPC_URL |
public testnet RPC | EVM JSON-RPC endpoint for on-chain reads |
BLOCKSCOUT_URL |
public testnet explorer | Blockscout instance for token index and holders |
ATLAS_API_URL |
unset | Base URL of an ATLAS deployment, enables research feed tools |
Connect a client
Claude Code:
claude mcp add atlas-research -- node /path/to/research-mcp/dist/index.js
Or in any MCP client config:
{
"mcpServers": {
"atlas-research": {
"command": "node",
"args": ["/path/to/research-mcp/dist/index.js"],
"env": {
"ATLAS_API_URL": "https://your-atlas-deployment"
}
}
}
}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.