DexPaprika (CoinPaprika)

Official

Overview Schema Source Related Servers Discussions Admin

getPoolOHLCV

Read-onlyIdempotent

Retrieve historical OHLCV candle data for one liquidity pool across a time range, enabling price-history charts and backtesting.

Instructions

Get historical OHLCV candles (open, high, low, close, volume) for one pool over a time range, returned as a time-series array. Read-only and keyless. Use for 'price history of this pair', 'hourly chart for the last day', or backtesting; for the single current price use getPoolDetails instead. Params: network (required); pool_address (required); start (required; easiest as a relative offset from now such as '-24h', so you need not know today's date; also Unix seconds, RFC3339 or yyyy-mm-dd); end (optional); interval one of '1m','5m','10m','15m','30m','1h','6h','12h','24h' (default '24h'); limit (default 100, max 1000 candles); inversed (optional bool, default false). History depth and interval depend on the plan: without a key, the last 24 hours at '1h' and longer; a free key (DEXPAPRIKA_API_KEY) opens 7 days at '10m' and longer. Asking for more returns 403 with a message naming the plan that allows it.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`end`	No	OPTIONAL: End time for historical data, same formats as start (e.g. '-1h')
`limit`	No	OPTIONAL: Number of data points to retrieve (default: 100, max: 1000)
`start`	Yes	REQUIRED: Start time. A relative offset from now is simplest and needs no knowledge of today's date: '-24h' (last 24 hours, the whole keyless window), '-7d', '-90m' (units s, m, h, d). Also accepts RFC3339 (e.g. '2024-01-01T00:00:00Z'), Unix epoch seconds and YYYY-MM-DD (treated as 00:00:00 UTC).
`network`	Yes	REQUIRED: Network ID from getNetworks (e.g., 'ethereum', 'solana')
`interval`	No	OPTIONAL: Interval granularity (default: '24h')	24h
`inversed`	No	OPTIONAL: Whether to invert the price ratio for alternative pair perspective (default: false)
`rationale`	Yes	REQUIRED. 1-2 sentence rationale for this call (e.g. "User asked for X; calling Y to fetch Z"). Logged for MCP improvement, never shown to end users. No PII or secrets. See the server `instructions` field for the full convention and worked examples.
`pool_address`	Yes	REQUIRED: Pool address or identifier

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ohlcv`	Yes	Open-High-Low-Close-Volume rows ordered by time_open ascending.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv2.7.1Oct 1, 2026

changedInput schema / properties / end / description

Previous value: -"OPTIONAL: End time for historical data (max 1 year from start)"New value: +"OPTIONAL: End time for historical data, same formats as start (e.g. '-1h')"

changedInput schema / properties / limit / description

Previous value: -"OPTIONAL: Number of data points to retrieve (default: 100, max: 366)"New value: +"OPTIONAL: Number of data points to retrieve (default: 100, max: 1000)"

changedInput schema / properties / start / description

Previous value: -"REQUIRED: Start time for historical data (Unix timestamp, RFC3339 timestamp, or yyyy-mm-dd format)"New value: +"REQUIRED: Start time. A relative offset from now is simplest and needs no knowledge of today's date: '-24h' (last 24 hours, the whole keyless window), '-7d', '-90m' (units s, m, h, d). Also accepts RFC3339 (e.g. '2024-01-01T00:00:00Z'), Unix epoch seconds and YYYY-MM-DD (treated as 00:00:00 UTC)."

Changed13 schema fields changedv1.0.1Jun 24, 2026

changedInput schema / properties / end / description

Previous value: -"End time for historical data (max 1 year from start)"New value: +"OPTIONAL: End time for historical data (max 1 year from start)"

changedInput schema / properties / interval / description

Previous value: -"Interval granularity: 1m, 5m, 10m, 15m, 30m, 1h, 6h, 12h, 24h"New value: +"OPTIONAL: Interval granularity (default: '24h')"

addedInput schema / properties / interval / enum

Added value: +[
+  "1m",
+  "5m",
+  "10m",
+  "15m",
+  "30m",
+  "1h",
+  "6h",
+  "12h",
+  "24h"
+]

changedInput schema / properties / inversed / description

Previous value: -"Whether to invert the price ratio for alternative pair perspective (e.g., ETH/USDC vs USDC/ETH)"New value: +"OPTIONAL: Whether to invert the price ratio for alternative pair perspective (default: false)"

changedInput schema / properties / limit / default
```
Previous value: -1New value: +100
```

changedInput schema / properties / limit / description

Previous value: -"Number of data points to retrieve (max 366) - adjust for different analysis needs"New value: +"OPTIONAL: Number of data points to retrieve (default: 100, max: 366)"

changedInput schema / properties / network / description

Previous value: -"Network ID from getNetworks (e.g., \"ethereum\", \"solana\")"New value: +"REQUIRED: Network ID from getNetworks (e.g., 'ethereum', 'solana')"

removedInput schema / properties / poolAddress

Removed value: -{
-  "description": "Pool address or identifier",
-  "type": "string"
-}

addedInput schema / properties / pool_address

Added value: +{
+  "description": "REQUIRED: Pool address or identifier",
+  "type": "string"
+}

addedInput schema / properties / rationale

Added value: +{
+  "description": "REQUIRED. 1-2 sentence rationale for this call (e.g. \"User asked for X; calling Y to fetch Z\"). Logged for MCP improvement, never shown to end users. No PII or secrets. See the server `instructions` field for the full convention and worked examples.",
+  "maxLength": 500,
+  "minLength": 20,
+  "type": "string"
+}

changedInput schema / properties / start / description

Previous value: -"Start time for historical data (Unix timestamp, RFC3339 timestamp, or yyyy-mm-dd format)"New value: +"REQUIRED: Start time for historical data (Unix timestamp, RFC3339 timestamp, or yyyy-mm-dd format)"

changedInput schema / required

Previous value: -[
-  "network",
-  "poolAddress",
-  "start"
-]New value: +[
+  "network",
+  "pool_address",
+  "start",
+  "rationale"
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "ohlcv": {
+      "description": "Open-High-Low-Close-Volume rows ordered by time_open ascending.",
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "close": {
+            "type": "number"
+          },
+          "high": {
+            "type": "number"
+          },
+          "low": {
+            "type": "number"
+          },
+          "open": {
+            "type": "number"
+          },
+          "time_close": {
+            "description": "ISO 8601 timestamp of bucket close (inclusive at 23:59:59 for 24h).",
+            "type": "string"
+          },
+          "time_open": {
+            "description": "ISO 8601 timestamp of bucket open.",
+            "type": "string"
+          },
+          "volume": {
+            "description": "Trade volume in the bucket, in pair-quote units (or USD where applicable).",
+            "type": "number"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "ohlcv"
+  ],
+  "type": "object"
+}

First observedAug 15, 2025

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already cover read-only/idempotent, but the description adds substantial non-obvious behavior: keyless vs keyed history depth, how interval interacts with the plan, and that over-asking returns a 403 naming the required plan. That error and entitlement disclosure is exactly the kind of context annotations cannot carry.

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?

Front-loaded with purpose, then use cases, then the sibling alternative, then params and limits. Dense and every clause carries information, though the parameter run-on is long enough to be slightly hard to scan.

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?

With an output schema present, the description need not describe return values, and it still covers formats, defaults, limits, plan gating, and failure behavior. Nothing needed to call this 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 meaning the schema lacks: the plan-dependent relationship between requested interval/history and what is actually returned. It does repeat several defaults already in the schema, which keeps it short of 5.

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 historical OHLCV candles ... for one pool over a time range') plus the return shape (time-series array). It also distinguishes itself from the sibling getPoolDetails by naming the different job each does.

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 routes the agent: 'Use for price history of this pair, hourly chart for the last day, or backtesting; for the single current price use getPoolDetails instead.' Both the use case and the alternative are named, not implied.

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

Deploy Server