kite-connect-mcp

Search mutual fund schemes

search_mf_instruments

Read-onlyIdempotent

Search mutual fund schemes by name, ISIN, AMC, plan, or scheme type to find matches and retrieve ISINs, NAV, purchase/redemption rules, and minimum amounts.

Instructions

Find mutual fund schemes on Zerodha Coin in Kite's daily mutual fund list (cached locally). Returns a list, best match first, each with tradingsymbol (the scheme's ISIN, which the MF tools take), amc, name, purchase_allowed, redemption_allowed, minimum_purchase_amount and purchase_amount_multiplier (INR), minimum_additional_purchase_amount, minimum_redemption_quantity and redemption_quantity_multiplier (units), dividend_type (growth / payout), scheme_type, plan (direct / regular), settlement_type, last_price (the latest NAV, INR) and last_price_date.

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": "search_mf_instruments"
  }
}

Input Schema

Name	Required	Description
`amc`	No	part of the fund house code, e.g. "AXIS" (codes look like AXISMUTUALFUND_MF)
`plan`	No	direct or regular
`limit`	No	most results to return
`query`	No	part of the fund name or its ISIN, case-insensitive; every word must match (e.g. "axis bluechip", "INF846K01DP8"). May be empty when a filter is given
`scheme_type`	No	equity, debt, elss ...

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?

Beyond the annotations (readOnly/idempotent/non-destructive), the description contributes material facts: results come from a locally cached copy of Kite's daily MF list (so data can be stale) and are returned 'best match first'. It also enumerates every returned field with units and semantics, which the annotations cannot convey.

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 purpose is front-loaded in the opening clause, followed by a justification for the long tail: since there is no output schema, enumerating return fields earns its place. The single run-on sentence is dense but not padded with filler.

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?

With no output schema, the description compensates well by fully enumerating return fields, their units, and the ordering guarantee. Remaining gaps are minor for a read-only search: no statement of result-count behavior or tie to the refresh_instruments sibling for cache freshness.

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%, so all five parameters (amc, plan, limit, query, scheme_type) are already documented in the schema, including matching rules and the empty-query-with-filter case. The description adds no parameter-level guidance beyond what the schema states, so the baseline of 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 and resource — 'Find mutual fund schemes on Zerodha Coin' — scoped to Kite's daily mutual fund list. The domain qualifier ('mutual fund schemes') implicitly separates it from the generic search_instruments sibling, and the note that tradingsymbol is the ISIN 'which the MF tools take' clarifies its role in the MF workflow chain.

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?

Usage is only implied: the description makes clear this is the lookup step for MF schemes, and the ISIN remark hints that its output feeds other MF tools. There is no explicit when-to-use vs. search_instruments guidance, and no mention of when to call refresh_instruments if the local cache is stale.

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