OpenFinance — Easy Trading: Crypto, Stocks, Perps & Prediction Markets

onchain_get_address_holdings

Get a wallet's on-chain holdings ON ONE CHAIN. includeNfts=true returns the FULL portfolio (native currency + all fungibles + NFT collection) — heavier. includeNfts=false (default) returns only native + fungibles, paginated via cursor — lighter and the right call when you only need token holdings (e.g. before placing a trade or computing USD totals). includePrice attaches USD values; includeMetadata attaches name/symbol/logo/decimals.

IMPORTANT — chainId takes exactly ONE chain (comma-separated values are rejected), so an open-ended "what do I hold?" / "what's my balance?" needs ONE CALL PER CHAIN, and any chain you skip is simply absent from the answer. Unless the user named a chain, cover at least: 1 (Ethereum), 8453 (Base), 42161 (Arbitrum), 137 (Polygon), 4663 (Robinhood Chain) and "solana". 4663 is the one most often missed — every Pons, wrapper and OpenFinance V4 launch lives there, along with USDG, so omitting it reports an empty wallet to a user who holds plenty. Say which chains you checked, so a real zero is distinguishable from a chain you didn't look at.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "chainId": "<chainId>",
      "walletAddress": "<walletAddress>"
    },
    "name": "onchain_get_address_holdings"
  }
}

Input Schema

Name	Required	Description
`cursor`	No	Pagination cursor (only meaningful when includeNfts=false)
`chainId`	Yes	ONE chain identifier — "1" Ethereum, "8453" Base, "42161" Arbitrum, "137" Polygon, "4663" Robinhood Chain (OpenFinance launches + USDG), "solana". Not comma-separated: call once per chain.
`provider`	No	Force provider: Alchemy / GoldRush / Moralis / Tatum / BlockDaemon / Shyft
`includeRaw`	No
`includeNfts`	No	Include NFTs (default false)
`includePrice`	No	Attach USD values
`walletAddress`	Yes	Wallet address to query
`includeMetadata`	No	Attach token metadata

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations at all, the description carries the full burden, and it does well: it discloses the weight trade-off of includeNfts, cursor-based pagination only applying when includeNfts=false, the one-chain-per-call restriction, and that skipped chains are silently absent. It stops short of any rate-limit, caching, auth, or provider-fallback behavior, and says nothing about the return shape beyond field attachments.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Long but front-loaded: the one-line summary and the includeNfts trade-off come first, with the multi-chain warning after. The bolded emphasis on the commonly missed chain is justified by the stated failure mode, though the tone is at the edge of over-verbose for a tool definition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter tool with no annotations and no output schema, the description covers the consequential parameters, the pagination model, and the critical multi-chain usage pattern. The gaps are provider selection and includeRaw, neither of which the description or schema meaningfully explains.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 88% (baseline 3), and the description goes further by explaining the consequences of each flag: what includeNfts=true adds and why it is heavier, that cursor pagination only applies with includeNfts=false, and what includePrice/includeMetadata attach. It adds little for provider and includeRaw, which remain semantics-light.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Get a wallet's on-chain holdings') and immediately scopes it ('ON ONE CHAIN'), which cleanly separates it from siblings like get_wallet_addresses, onchain_get_token_metadata, and onchain_get_token_usd_price.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly prescribes when to use each mode: includeNfts=true for full portfolio, includeNfts=false for token-only needs 'e.g. before placing a trade or computing USD totals'. It also gives a hard when-to-use rule for the one-chain constraint, naming the exact chains to cover when the user didn't specify, and telling the agent to report which chains were checked.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All OpenFinance — Easy Trading: Crypto, Stocks, Perps & Prediction Markets tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.