SiteCheck Crypto & Finance

Pyth Network oracle prices with confidence bands, read

crypto_pyth_network_oracles

Read-only

Pyth Network oracle prices with confidence bands, read on-chain from Pyth's Solana push feeds: price, confidence interval (absolute and %), EMA price and EMA confidence, publish time and age in seconds, feed id and account, for up to 20 symbols (BTCUSD, ETHUSD, SOLUSD, gold XAUUSD, stablecoins, LST rates; ~65 feeds). Call with list=true for every available symbol. Related tools on this server, for a different need: crypto_tao_network when you need Bittensor network fundamentals: block height, total issued. Price: $0.002 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "crypto_pyth_network_oracles"
  }
}

Input Schema

Name	Required	Description	Default
`list`	No	true to list the available symbols instead
`symbols`	No	Comma-separated Pyth symbols, e.g. BTCUSD,ETHUSD (1 to 20)

Output Schema

Name	Required	Description	Default
`count`	No
`prices`	No
`source`	No
`checkedAt`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond readOnlyHint and openWorldHint, the description discloses the cost model ($0.002 USDC per successful call, paid via x402 on Base, Solana or Arc, with failed calls not charged) and the source and mechanics (on-chain Solana push feeds, ~65 feeds, 20-symbol cap). These are exactly the operational facts an agent needs before spending money on a call and that no annotation or schema field carries.

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?

Purpose and data fields are front-loaded, then the list=true escape hatch, then the sibling routing and the price. It is dense but nearly every clause carries information; the long comma-delimited field enumeration makes it a heavier read than it needs to be, which is the only thing keeping it off a 5.

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

Completeness5/5

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

An output schema exists, yet the description still summarizes the returned fields, and it adds the payment, feed-count, and symbol-limit constraints. For a two-parameter read tool with full schema coverage and declared annotations, nothing material an agent needs to call it correctly is missing.

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 100%, so the baseline is 3, but the description adds real meaning on top: it explains that list=true returns every available symbol (not just a flag toggle), caps symbols at 20, and supplies concrete symbol formats and coverage categories (BTCUSD, ETHUSD, SOLUSD, XAUUSD, stablecoins, LST rates). The only gap is that it does not state the behavior when symbols is omitted while list is also absent.

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?

The description opens with a specific verb and resource ('Pyth Network oracle prices with confidence bands, read on-chain from Pyth's Solana push feeds') and then enumerates exactly what is returned: price, confidence interval in absolute and percent terms, EMA price and confidence, publish time and age, feed id and account. It also distinguishes itself from the sibling it names (crypto_tao_network, for Bittensor network fundamentals) and signals its scope (up to 20 symbols, ~65 feeds).

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

Usage Guidelines4/5

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

It gives a concrete usage rule: pass list=true to enumerate every available symbol, and it routes the agent away to crypto_tao_network when Bittensor fundamentals are the actual need. What it does not do is disambiguate against the many other price/oracle siblings on the server, such as crypto_chainlink_price_feeds or finance_dia_crypto_oracle, so the when-to-use-this-instead-of-that guidance is clear but incomplete.

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

All SiteCheck Crypto & Finance 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.

Resources

Need Help?