research-mcp
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 buildConfiguration
All optional, via environment variables:
Variable | Default | Purpose |
|
| Display name used in tool output |
|
| GeckoTerminal network slug |
|
| DefiLlama chain name |
| public testnet RPC | EVM JSON-RPC endpoint for on-chain reads |
| public testnet explorer | Blockscout instance for token index and holders |
| 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.jsOr 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"
}
}
}
}Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/atlas-rwa/research-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server