kite-connect-mcp

Order updates and broker messages

ticker_order_updates

Read-onlyIdempotent

Retrieves live order updates and broker messages from WebSocket or postback streams, letting you check recent order status changes or page forward from a given time.

Instructions

Order updates and broker messages received by this server: the WebSocket stream (live updates for orders placed anywhere on the account: web, mobile or API) and, when KITE_MCP_POSTBACK_PATH is set, Kite postbacks sent to the HTTP endpoint. Each item has seq, received_at, source ("ticker" or "postback"), type ("order"; "error" or "message" for Kite's own text) and data. For orders, data has order_id, status (COMPLETE, REJECTED, CANCELLED, UPDATE...), status_message, exchange, tradingsymbol, transaction_type, order_type, product, variety, quantity, filled_quantity, pending_quantity, price, trigger_price, average_price and timestamps.

Only the last 500 items are kept, in memory, and items arrive only while the WebSocket is open (ticker_subscribe, even with an empty list, opens it) or the postback endpoint is receiving. Without since: the latest items, oldest first. With since: the first items after it, so you can page forward (more=true means there are further ones). These are notifications, not the book of record: a postback is authenticated only by a checksum over order_id and order_timestamp, so confirm what matters with get_order_history.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ticker_order_updates"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No	at most this many items
`since`	No	ISO 8601 time (IST if no offset): only items received after it, oldest first

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the readOnly/idempotent annotations: discloses a 500-item in-memory cap, the precondition that the WebSocket must be open, that postbacks are authenticated only by a checksum over order_id and order_timestamp, and that these are notifications rather than authoritative records. It also explains the more=true paging flag.

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 the resource and delivery channels, then item shape, then paging rules, then the reliability caveat. It is long and the enumerated field list is dense, but nearly every sentence carries decision-relevant information.

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 no output schema, the description fully compensates by specifying each item's seq/received_at/source/type/data fields and the order payload contents. Combined with the paging, retention and reliability notes, an agent has everything needed to call and interpret it.

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 both parameters are already documented. The description nonetheless adds behavior the schema omits: without since you get the latest items oldest-first, with since you get the first items after it enabling forward paging, and more=true signals further pages.

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 the specific resource (order updates and Kite broker messages received by this server) and the two delivery channels (WebSocket stream, postback HTTP endpoint), plus the exact item shape. This clearly separates it from get_orders/get_order_history, which are the book of record rather than a notification feed.

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?

Gives explicit conditions: items only arrive while the WebSocket is open (ticker_subscribe, even with an empty list) or when the postback endpoint is configured, and directs the agent to get_order_history for authoritative confirmation. The only gap is no direct differentiation from the sibling ticker_get_ticks/ticker_status tools.

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