kite-connect-mcp

Last traded prices

get_ltp

Read-onlyIdempotent

Fetch the last traded price in INR for up to 1,000 instruments in one call and return missing symbols separately, so you can verify quote availability.

Instructions

Last traded price (INR) for up to 1000 instruments in one call. Returns {"quotes": {instrument: {instrument_token, last_price}}, "missing": [...]} (missing: instruments Kite has no data for). The cheapest price check. Needs the paid Kite Connect plan.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "instruments": "<instruments>"
    },
    "name": "get_ltp"
  }
}

Input Schema

Name	Required	Description	Default
`instruments`	Yes	1 to 1000 instruments, each EXCHANGE:TRADINGSYMBOL (e.g. "NSE:INFY", "NSE:NIFTY 50", "NFO:NIFTY25NOVFUT")

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive semantics, and the description adds real context beyond them: the paid Kite Connect plan prerequisite, the 1000-instrument batching limit, and the existence of a `missing` bucket for instruments Kite has no data for. It does not discuss rate limits or error behavior, but the plan requirement and partial-data handling are exactly the kind of disclosure that matters here.

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?

Four short sentences, front-loaded with what it returns and followed by the return shape, caveat, cost hint, and prerequisite. The inline JSON return sketch is slightly dense but earns its place since there is no output schema.

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?

Single-parameter read tool whose only ambiguity (instrument format) is covered by the schema; the description compensates for the missing output schema by sketching the response envelope and the `missing` list. The plan prerequisite is a genuinely important operational constraint and is included, leaving only minor gaps like partial-failure semantics on error.

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 already documents the 1–1000 range and the EXCHANGE:TRADINGSYMBOL format with examples. The description only restates the 1000 cap and adds the INR currency of the returned price, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb-less but unmistakable resource and scope: last traded price in INR for up to 1000 instruments in one call. An agent can immediately tell it returns only LTP, unlike get_ohlc or get_quotes, though those siblings are never named explicitly.

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

Usage Guidelines3/5

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

"The cheapest price check" hints that this should be chosen over richer quote tools when only the last price is needed, which is useful implied guidance. It never names the alternatives or states exclusions (e.g. when you need depth, volume, or OHLC, use get_quotes/get_ohlc instead), so the routing decision is left partly to inference.

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