Skip to main content
Glama
Firefly III MCP Server

Firefly III MCP Server

by edmondxie779

Search Transactions

search_transactions
Read-onlyIdempotent

Search Firefly III transactions with query syntax, combining type, date, amount, account, category, budget, tag, and text filters to find matching records.

Instructions

Search Firefly III transactions using Firefly III's search query syntax. Multiple terms are combined with AND. Wrap multi-word values in quotes. Useful operators: type:withdrawal|deposit|transfer, date_after:YYYY-MM-DD, date_before:YYYY-MM-DD, date_is:YYYY-MM-DD, amount_is:N, amount_more:N, amount_less:N, source_is:"Checking", destination_is:"Amazon", category_is:"Food", budget_is:"Groceries", tag_is:"trip", description_contains:"coffee", notes_contain:"reimburse", has_any_category:false, reconciled:true. Prefix any filter with '-' to negate.

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": {
      "query": "<query>"
    },
    "name": "search_transactions"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number.
limitNoResults per page.
queryYesFirefly III search query string, e.g. 'type:withdrawal category_is:"Dining" date_after:2026-11-01'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds query-engine behavior (implicit AND, negation semantics) but says nothing about result ordering, whether the search is case-sensitive, pagination or rate limits.

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 purpose and syntax in the first two sentences, then a compact operator inventory. The long inline operator list is dense but each entry is a usable filter, though a structured list would scan better.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter read tool with no output schema, the query DSL is covered well, but the description never indicates what comes back — whether results are paginated, whether pagination metadata exists alongside page/limit — leaving a real gap for an agent planning calls.

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 goes substantially beyond the schema by documenting a long list of filter operators and the combination/quoting rules for the free-text query parameter. It stops short of being exhaustive (e.g. no operator for multiple tags or amounts ranges combined) and says nothing about page/limit semantics.

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 ('Search Firefly III transactions') plus the query dialect used, so the agent knows exactly what the tool does. It does not distinguish itself from siblings such as list_transactions or search_accounts, so an agent must infer that this is the filtered/free-text path.

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 description gives strong operational guidance on how to build a query (AND combination, quoting multi-word values, '-' negation), which implies filtering use. However, it never states when to prefer this tool over list_transactions or list_account_transactions, and offers no exclusions or prerequisites.

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