CoinPaprika

getCoinOHLCVHistorical

Read-onlyIdempotent

Get OHLC candles (open, high, low, close, volume) for a coin. Use for 'daily chart last month', 'hourly candles since Jan 1'. For one past price use getTickersHistoricalById; for the latest candle use getCoinOHLCVLatest. Read-only. Params: coinId (required) canonical id like 'btc-bitcoin' (resolve via resolveId); start (required) and end (optional, default now) accept 'yyyy-mm-dd' or ISO 8601; interval (optional, default '24h'): one of '5m', '15m', '30m', '1h', '6h', '12h', '24h'; quote (optional, default 'usd'); limit (optional, default 50, max 250) caps candles. Requires a Starter+ plan (COINPAPRIKA_API_KEY).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`end`	No	Optional end timestamp. Same formats as start. Defaults to now if omitted.
`limit`	No	Optional. Number of candles (default 50, max 250).
`quote`	No	Optional quote currency code (default 'usd'). Examples: 'usd', 'btc', 'eth'.	usd
`start`	Yes	Required. Start timestamp. Accepts ISO 8601 ('2026-01-15T00:00:00Z') or date-only ('2026-01-15'). UTC.
`coinId`	Yes	Canonical CoinPaprika coin slug in 'symbol-name' format, e.g. 'btc-bitcoin', 'eth-ethereum', 'ada-cardano'. Do NOT pass ticker symbols ('BTC', 'AAVE') or guess the slug; it is not derivable from the symbol (e.g. AAVE resolves to 'aave-new', which you could not guess). Call search or resolveId first to resolve a symbol or name to its canonical id.
`interval`	No	Optional. Candle interval. Defaults to '24h' for daily candles.	24h
`rationale`	Yes	REQUIRED. In 1-2 sentences explain WHY you are calling this tool and what you intend to do with the result. Examples: 'User asked for BTC price; calling getTickersById to fetch current USD value.' 'Building a portfolio dashboard; need OHLCV for ETH last 7 days.' This is logged and reviewed to improve the MCP. Do not include user PII or secrets; use generic descriptions.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ohlcv`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 2, 2026

changedInput schema / properties / coinId / description

Previous value: -"Canonical CoinPaprika coin slug in 'symbol-name' format, e.g. 'btc-bitcoin', 'eth-ethereum', 'ada-cardano'. Do NOT pass ticker symbols ('BTC', 'AAVE') or guess the slug — it is not derivable from the symbol (e.g. AAVE resolves to 'aave-new', which you could not guess). Call search or resolveId first to resolve a symbol or name to its canonical id."New value: +"Canonical CoinPaprika coin slug in 'symbol-name' format, e.g. 'btc-bitcoin', 'eth-ethereum', 'ada-cardano'. Do NOT pass ticker symbols ('BTC', 'AAVE') or guess the slug; it is not derivable from the symbol (e.g. AAVE resolves to 'aave-new', which you could not guess). Call search or resolveId first to resolve a symbol or name to its canonical id."

changedInput schema / properties / rationale / description

Previous value: -"REQUIRED. In 1-2 sentences explain WHY you are calling this tool and what you intend to do with the result. Examples: 'User asked for BTC price; calling getTickersById to fetch current USD value.' 'Building a portfolio dashboard; need OHLCV for ETH last 7 days.' This is logged and reviewed to improve the MCP. Do not include user PII or secrets — use generic descriptions."New value: +"REQUIRED. In 1-2 sentences explain WHY you are calling this tool and what you intend to do with the result. Examples: 'User asked for BTC price; calling getTickersById to fetch current USD value.' 'Building a portfolio dashboard; need OHLCV for ETH last 7 days.' This is logged and reviewed to improve the MCP. Do not include user PII or secrets; use generic descriptions."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "ohlcv": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "close": {
+            "type": "number"
+          },
+          "high": {
+            "type": "number"
+          },
+          "low": {
+            "type": "number"
+          },
+          "market_cap": {
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "open": {
+            "type": "number"
+          },
+          "time_close": {
+            "description": "ISO 8601 bucket close. Often '23:59:59Z' for daily candles, inclusive.",
+            "type": "string"
+          },
+          "time_open": {
+            "description": "ISO 8601 bucket open.",
+            "type": "string"
+          },
+          "volume": {
+            "type": [
+              "number",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "ohlcv"
+  ],
+  "type": "object"
+}

First observedJul 28, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description adds meaningful context beyond them: it requires a Starter+ plan with COINPAPRIKA_API_KEY, notes that limit caps the number of candles, and warns that coinId must be resolved rather than guessed. This goes beyond the structured annotation data without contradicting it.

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?

The description is front-loaded with purpose and usage, followed by a dense but organized parameter summary. It is appropriately sized for a 7-parameter historical data tool, though the 'Read-only' phrase is slightly redundant given the annotations and the parameter summary partly repeats schema content.

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?

For a tool with rich schema coverage, detailed annotations, and an output schema, the description covers the remaining invocation-critical context: auth requirements, ID resolution, date formats, interval choices, limits, and sibling routing. Nothing essential for correct usage is missing.

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

Parameters3/5

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

Schema description coverage is 100% and the schema already provides detailed parameter descriptions, examples, enums, and defaults. The description adds a compact summary but little genuinely new semantic information beyond what the input schema supplies, so the baseline of 3 is appropriate.

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: 'Get OHLC candles (open, high, low, close, volume) for a coin.' It further distinguishes itself from siblings by explicitly stating that getTickersHistoricalById is for one past price and getCoinOHLCVLatest is for the latest candle, so an agent can select the right tool without ambiguity.

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?

It gives explicit use cases ('daily chart last month', 'hourly candles since Jan 1') and names alternatives with their conditions ('For one past price use getTickersHistoricalById; for the latest candle use getCoinOHLCVLatest'). It also instructs agents to resolve canonical IDs via resolveId, preventing a common invocation error.

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

All CoinPaprika 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?