Twelvedata

Indices

indices

Read-onlyIdempotent

Twelve Data reference list of supported market index symbols with exchange metadata — about 1,300 NON-US indices (e.g. N225 Nikkei 225, 000001 SSE Composite, NSEI Nifty 50), paged, default 200 rows. Filter by country (e.g. "Japan", "India", "China"), exchange or symbol. US indices (SPX, DJI, IXIC, NDX, VIX) are NOT in Twelve Data's reference list and quoting them requires a Grow-or-higher Twelve Data key via _apiKey — a US filter here returns that refusal, not an empty list. Use to discover or validate index tickers before querying time_series.

Input Schema

TableJSON Schema

Name	Required	Description
`page`	No	Page of the reference list (default 1). `count` in the response is the TOTAL matched; `data` is this page.
`symbol`	No	Optional index symbol filter (e.g. "N225", "NSEI", "000001"). US symbols such as SPX/DJI/IXIC are not in this list — see the tool description.
`country`	No	Optional country filter, full name or alpha code (e.g. "Japan", "India", "China", "Germany"). "United States" returns a plan refusal, not rows.
`exchange`	No	Optional exchange filter (e.g. "NASDAQ", "NYSE", "Binance").
`mic_code`	No	Optional ISO 10383 market identifier code filter (e.g. "XNAS", "XLON").
`outputsize`	No	Rows per page (default 200, max 5000). The unfiltered ETF list is 64,000+ rows, so narrow with symbol / country / exchange rather than raising this.

Output Schema

TableJSON Schema

Name	Required	Description
`code`	No	Response code
`status`	No	Response status
`message`	No	Response message

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedSep 20, 2026

changedInput schema / examples

Previous value: -[
-  {}
-]New value: +[
+  {
+    "country": "Japan"
+  },
+  {
+    "country": "India",
+    "outputsize": 20
+  }
+]

changedInput schema / properties / country / description

Previous value: -"Optional country filter (e.g. \"United States\")."New value: +"Optional country filter, full name or alpha code (e.g. \"Japan\", \"India\", \"China\", \"Germany\"). \"United States\" returns a plan refusal, not rows."

addedInput schema / properties / exchange

Added value: +{
+  "description": "Optional exchange filter (e.g. \"NASDAQ\", \"NYSE\", \"Binance\").",
+  "type": "string"
+}

addedInput schema / properties / mic_code

Added value: +{
+  "description": "Optional ISO 10383 market identifier code filter (e.g. \"XNAS\", \"XLON\").",
+  "type": "string"
+}

addedInput schema / properties / outputsize

Added value: +{
+  "description": "Rows per page (default 200, max 5000). The unfiltered ETF list is 64,000+ rows, so narrow with symbol / country / exchange rather than raising this.",
+  "type": "number"
+}

addedInput schema / properties / page

Added value: +{
+  "description": "Page of the reference list (default 1). `count` in the response is the TOTAL matched; `data` is this page.",
+  "type": "number"
+}

changedInput schema / properties / symbol / description

Previous value: -"Optional index filter (e.g. \"IXIC\")."New value: +"Optional index symbol filter (e.g. \"N225\", \"NSEI\", \"000001\"). US symbols such as SPX/DJI/IXIC are not in this list — see the tool description."

Changed2 schema fields changedJun 24, 2026

addedInput schema / properties / country

Added value: +{
+  "description": "Optional country filter (e.g. \"United States\").",
+  "type": "string"
+}

addedInput schema / properties / symbol

Added value: +{
+  "description": "Optional index filter (e.g. \"IXIC\").",
+  "type": "string"
+}

Changed1 schema field changedMay 24, 2026
- removedInput schema / additionalProperties
```
Removed value: -true
```

Changed2 schema fields changedMay 22, 2026

addedInput schema / examples
```
Added value: +[
+  {}
+]
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "code": {
+      "description": "Response code",
+      "type": "number"
+    },
+    "message": {
+      "description": "Response message",
+      "type": "string"
+    },
+    "status": {
+      "description": "Response status",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

First observedMay 20, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint, idempotentHint), the description discloses pagination behavior (default 200 rows, outputsize max 5000), the presence of `count` as total matches vs `data` as the page, and the specific refusal behavior for US indices. This adds meaningful operational context that is not present in structured fields.

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 a compact paragraph that front-loads purpose and scope, then covers filters and the US caveat. It is efficient overall, though the reference to an 'unfiltered ETF list' appears possibly mis-copied from another tool and slightly distracts from the index focus, but this does not undermine the structure.

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?

Given the presence of an output schema, the description focuses on behavior not otherwise specified. It covers key operational aspects: default page size, filter options, US refusal, and the use case. Minor omissions like rate limits are acceptable given the tool's read-only nature and existing annotation coverage.

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?

The input schema already provides detailed descriptions for all six parameters (100% coverage). The description adds value by clarifying semantic implications: 'United States' country yields a plan refusal, outputsize defaults to 200 with a max of 5000, and page interacts with count/data. This supplements rather than duplicates the schema.

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 states a specific purpose: a reference list of supported market index symbols with exchange metadata, explicitly scoped to non-US indices (~1,300) and illustrated with concrete examples (N225, 000001, NSEI). It clearly differentiates from siblings like time_series or quote by focusing on ticker discovery/validation.

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 explicitly instructs to use this tool to discover or validate index tickers before querying time_series, and warns that US filters return a plan refusal rather than an empty list, providing a clear usage boundary. It could more explicitly name alternative tools for other asset classes, but the primary use case and exclusion are clear.

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

All Twelvedata 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.