fynsight: MCP server for DATEV

query_kpis

Read-only

Calculate KPI values for a given period. Returns each KPI with value, previous-period value, and month-over-month change. Use for KPI-specific questions.

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": {
      "period": "<period>"
    },
    "name": "query_kpis"
  }
}

Input Schema

Name	Required	Description
`period`	Yes	Accounting period in YYYY-MM format (e.g. '2025-03')
`kpi_ids`	No	Optional list of KPI IDs to filter. Omit for all active KPIs.
`include_previous`	No	Include previous-period comparison (default true)

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful output context (each KPI returned with current, previous-period, and MoM change), but says nothing about how results change when include_previous is false or what happens for KPIs with no prior-period data.

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?

Three short sentences, front-loaded with the action followed by the return shape and then the usage cue. Little waste, though the final sentence is thin filler relative to what could have been a real disambiguation note.

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?

Read-only, three fully documented flat parameters, and the return fields are described in prose despite no output schema. What is missing for full completeness is the boundary against sibling trend/aggregate tools.

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%, including the YYYY-MM period format, the optional kpi_ids filter, and the include_previous default, so the schema carries the parameter burden. The description's mention of previous-period comparison loosely reinforces include_previous but adds no semantics beyond the schema.

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 ('Calculate KPI values for a given period') and previews the return shape (value, previous-period value, month-over-month change). It does not name or distinguish itself from the closest siblings (get_metric_trend, compute_aggregates), so an agent must infer the boundary from the 'KPI-specific' phrasing.

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?

'Use for KPI-specific questions' gives a positive trigger but no exclusions, prerequisites, or guidance versus get_metric_trend or get_periodic_summaries. The reader is left to infer when a KPI query is the wrong choice.

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

All fynsight: MCP server for DATEV 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.

Resources

Need Help?