# Pyth Pro MCP Server (remote · mcp.pyth.network)

Real-time and historical price feeds for 500+ crypto, equities, FX, and commodities assets.

- Trust score: 78/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.pyth.network`: 78/100 (this document), [markdown](https://verifymcp.io/servers/pyth-network-mcp/mcp.md), [page](https://verifymcp.io/servers/pyth-network-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.pyth.network/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1507 tokens (~115/item across 13 items; 5 tools + 8 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http pyth-network-mcp https://mcp.pyth.network/mcp
```

### Codex

```toml
[mcp_servers.pyth-network-mcp]
url = "https://mcp.pyth.network/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pyth-network-mcp": {
      "type": "remote",
      "url": "https://mcp.pyth.network/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pyth-network-mcp --url https://mcp.pyth.network/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  pyth-network-mcp:
    url: "https://mcp.pyth.network/mcp"
```

### Other

```json
{
  "mcpServers": {
    "pyth-network-mcp": {
      "type": "http",
      "url": "https://mcp.pyth.network/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 76, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 74, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 72, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 71)

First indexed and scored.

## MCP tools (5)

### `get_symbols` (~174 tokens)

List Pyth Price Feeds

List available Pyth Pro price feeds. Use this FIRST to discover what feeds exist before calling get_latest_price, get_historical_price, or get_candlestick_data. Filter by asset_type (crypto, equity, fx, metal, rates, commodity, funding-rate) or search by name/symbol. Returns feed metadata including pyth_lazer_id (needed for get_historical_price), symbol, asset_type, and exponent.

Input parameters:

- `asset_type` (string): Filter by asset type: crypto, fx, equity, metal, rates, commodity, funding-rate
- `limit` (integer): Results per page (default 50, max 200)
- `offset` (integer): Pagination offset (default 0)
- `query` (string): Text filter (e.g. 'BTC', 'gold', 'AAPL')

### `convert_date_to_timestamp` (~170 tokens)

Convert Date to Timestamp

Convert a date string to Unix timestamp for use with get_historical_price and get_candlestick_data. Use this tool when you need to compute timestamps — do not calculate Unix timestamps manually. Accepts ISO 8601 dates (e.g. '2026-01-01', '2026-01-01T12:00:00Z'). Returns seconds, microseconds, ISO 8601, and whether the date is within the available data range (April 2025 onward).

Input parameters:

- `date_string` (string, required): Date to convert. Must be ISO 8601 / RFC 3339 with timezone (e.g. '2026-01-01T00:00:00Z', '2026-01-01'). Bare dates without timezone are interpreted as UTC.

### `get_candlestick_data` (~407 tokens)

Get Candlestick Data

Fetch OHLC candlestick data for a symbol. Pass your Pyth Pro `access_token` to authenticate the request. Use for charting, technical analysis, backtesting. IMPORTANT: The symbol must be the full name from get_symbols including the asset type prefix (e.g. 'Crypto.BTC/USD', 'Equity.US.AAPL', 'FX.EUR/USD') — never use bare names like 'BTC/USD'. Historical data is available from April 2025 onward — do not request timestamps before that. Resolutions: 1/5/15/30/60 minutes, 120/240/360/720 (multi-hour), D (daily), W (weekly), M (monthly). Timestamps are Unix seconds.

Timestamp reference (Unix seconds):
  2025-04-01 (earliest available) = 1743465600
  2026-01-01 = 1767225600
  2026-06-01 = 1780272000
Always double-check your timestamp math — year-boundary errors are common.

Input parameters:

- `access_token` (string): Pyth Pro access token used to authenticate the request. Get one at https://docs.pyth.network/price-feeds/pro/acquire-access-token
- `channel` (string): Override default channel (e.g. fixed_rate@200ms, real_time, fixed_rate@50ms, fixed_rate@1000ms)
- `from` (integer, required): Start time (Unix seconds)
- `resolution` (string, required): Candle size: 1, 5, 15, 30, 60 (minutes), 120, 240, 360, 720 (hours), D (daily), W (weekly), M (monthly)
- `symbol` (string, required): Full symbol from get_symbols including asset type prefix (e.g. 'Crypto.BTC/USD', not 'BTC/USD')
- `to` (integer, required): End time (Unix seconds)

### `get_historical_price` (~380 tokens)

Get Historical Price

Get price data for specific feeds at a historical timestamp. Pass your Pyth Pro `access_token` to authenticate the request. Use get_symbols first to find feed IDs or symbols. If both price_feed_ids and symbols are provided, only price_feed_ids are used. Accepts Unix seconds, milliseconds, or microseconds (auto-detected). Historical data is available from April 2025 onward — do not request timestamps before that. The timestamp is internally converted to microseconds and aligned (rounded down) to the channel rate — e.g. for fixed_rate@200ms, it must be divisible by 200,000μs. Prices are integers with an exponent field — human-readable price = price * 10^exponent. Pre-computed display_price fields are included for convenience.

Timestamp reference:
  2025-04-01 (earliest available) = 1743465600
  2026-01-01 = 1767225600
  2026-06-01 = 1780272000
Always double-check your timestamp math — year-boundary errors are common.

Input parameters:

- `access_token` (string): Pyth Pro access token used to authenticate the request. Get one at https://docs.pyth.network/price-feeds/pro/acquire-access-token
- `channel` (string): Override default channel (e.g. fixed_rate@200ms, real_time, fixed_rate@50ms, fixed_rate@1000ms)
- `price_feed_ids` (array): Numeric feed IDs from get_symbols
- `symbols` (array): Full symbol names from get_symbols including asset type prefix (e.g. ['Crypto.BTC/USD', 'Equity.US.AAPL/USD'])
- `timestamp` (number, required): Unix timestamp — accepts seconds, milliseconds, or microseconds (auto-detected by magnitude)

### `get_latest_price` (~272 tokens)

Get Latest Price

Get the most recent real-time price for one or more feeds. Requires an `access_token` parameter (get one at https://docs.pyth.network/price-feeds/pro/acquire-access-token). Use get_symbols first to find symbols or feed IDs. IMPORTANT: symbols must be the full name including asset type prefix (e.g. 'Crypto.BTC/USD', not 'BTC/USD'). If both price_feed_ids and symbols are provided, only price_feed_ids are used. Prices are integers with an exponent field — human-readable price = price * 10^exponent. Pre-computed display_price fields are included for convenience.

Input parameters:

- `access_token` (string, required): Pyth Pro access token. Get one at https://pyth.network/pricing
- `channel` (string): Override default channel (e.g. fixed_rate@200ms, real_time, fixed_rate@50ms, fixed_rate@1000ms)
- `price_feed_ids` (array): Numeric feed IDs from get_symbols
- `properties` (array): Properties to return. Default: price, bestBidPrice, bestAskPrice, confidence, exponent, publisherCount
- `symbols` (array): Full symbol names from get_symbols including asset type prefix (e.g. ['Crypto.BTC/USD', 'Equity.US.AAPL/USD'])

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/pyth-network-mcp/mcp#diagnostics

## Score history

- 2026-08-03: 78
- 2026-08-02: 77
- 2026-08-01: 77
- 2026-07-31: 76
- 2026-07-30: 74
- 2026-07-29: 73
- 2026-07-28: 72
- 2026-07-27: 72
- 2026-07-26: 71

## Links

- Remote endpoint: https://mcp.pyth.network/mcp
- Repository: https://github.com/pyth-network/pyth-crosschain
- Website: https://docs.pyth.network/price-feeds/pro
- Changelog RSS feed: https://verifymcp.io/servers/pyth-network-mcp/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/pyth-network-mcp/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/pyth-network-mcp/mcp