AI & Machine Learning
heyanon.ai
MCP server for Hey Anon that exposes on-chain AI agent and crypto research tools such as wallet listing, API key setup, and querying Anon and Gemma assistants.
ENDPOINT 1
https://api.heyanon.ai/mcp
MCP server metadata
- Name
- heyanon-mcp
- Version
- 1.0.0
API key: it must be set as the X-API-Key (or Authorization: Bearer) header in the MCP connection config; ping and get_api_key_setup_url need no key. Never ask the user to paste the key into the chat. If a tool fails with "API key not set": call get_api_key_setup_url and show the user the URL and the config snippet; the user creates a key, puts it into the MCP connection config as the X-API-Key header and reconnects. ask_anon is asynchronous: it returns a background task ID; poll background_task with that ID until status is no longer "pending"; on "completed" read the reply from result, any other status means the request did not finish. Anon keeps no conversation context: every ask_anon message starts from a clean slate and must be self-contained. ask_anon refuses to send while Anon is still processing the previous request. ask_anon needs at least one wallet address and at most one per wallet type (evm, solana, ton); get addresses from wallet_list.
Known tools 21
get_api_key_setup_urlGet the URL of the Hey Anon page where the user logs in and creates an API key, plus the MCP config snippet where the key goes (X-API-Key header).
Inferred read-onlywallet_listList the user wallets registered in Hey Anon: display name, type (evm, solana, ton, etc.
Inferred read-onlyask_anonSend a message to Anon, the Hey Anon on-chain AI agent (balances, swaps, bridging, lending, staking, CEX, scheduled automations, research).
Potential side effectsask_gemmaAsk Gemma, the Hey Anon crypto research assistant: protocol analysis, community and social insights, market data, news, token analytics by contract address.
Inferred read-onlyprojectsList the protocols and integrations Anon can operate (swaps, lending, staking, bridges, CEX, etc.
Inferred read-onlyscheduled_task_listList the user scheduled tasks: automations created through Anon that run at a given time or when a price condition is met.
Inferred read-onlyportfolio_tokensToken balances for every user wallet (addresses taken from wallet_list) across all supported networks.
Inferred read-onlyportfolio_transactionsRecent transactions for every user wallet (addresses taken from wallet_list).
Inferred read-onlyportfolio_cexBalances and positions from the exchange accounts linked to Hey Anon (e.
Inferred read-onlybackground_task_listList the user Anon background tasks (one per ask_anon message): id, prompt, status, result (Anon reply when completed), logs, createdAt, updatedAt.
Potential side effectstransfer_assetSend a token (ERC-20 / SPL / jetton) from one of the user wallets to another address.
Potential side effectsaddress_book_listList the user saved recipient addresses (address book): name, networks and address.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.heyanon-mcp]
url = "https://api.heyanon.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"heyanon-mcp": {
"type": "http",
"url": "https://api.heyanon.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: heyanon-mcp
Remote MCP URL: https://api.heyanon.ai/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"heyanon-mcp": {
"url": "https://api.heyanon.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"heyanon-mcp": {
"type": "http",
"url": "https://api.heyanon.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "heyanon-mcp",
"transport": "streamable-http",
"url": "https://api.heyanon.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.