Skip to main content
Glama
wakapi-mcp

wakapi-mcp

by si-essence

wakapi_summaries

Read-only

Retrieve Wakapi coding-time summaries: all-time totals, stats, WakaTime summaries, summary, and statusbar. Query by date, project, or language, optionally as CSV.

Instructions

wakapi_summaries covers the summaries toolset (5 operations). Calls go to WAKAPI_URL with the /api prefix. Authenticated routes send Authorization Basic base64 of the API key. The key is never placed in the URL. Health and shields badges send no key. action help with target returns one action's parameters. Pass query format csv for a CSV table of dimension, key, total_seconds, and text. That format value is not sent to Wakapi. Actions: all_time, stats, wakatime_summaries, summary, statusbar.

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": {
      "action": "<action>"
    },
    "name": "wakapi_summaries"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoJSON object or JSON array. Secrets are redacted in output.
queryNoQuery parameters, such as from, to, project, language, and date. Summaries accept format csv.
actionYesWakapi operation to call, or help.
paramsNoPath parameters, such as user, range, interval, filter, and id.
targetNoWith action help, the action whose parameters to describe.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety bar is lower, yet the description still adds real operational context: requests go to WAKAPI_URL with the /api prefix, authenticated routes use Authorization Basic base64 of the API key, the key is never placed in the URL, and health/shield badge routes send no key. The note that the csv format value is not forwarded upstream is a non-obvious client-side behavior that an agent could otherwise misjudge when debugging.

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?

Roughly a hundred words with no filler — every sentence carries a distinct fact (endpoint, auth, key handling, help mode, CSV, action list). The ordering is the weak point: transport and auth boilerplate precede the statement of what the tool does and the action list, which is the single most decision-relevant piece, arrives last.

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?

There is no output schema, so the description carries the return-value burden, and it partially does so by specifying the CSV columns. It omits what the non-CSV JSON responses look like for the five actions and gives no pagination or date-range semantics for a multipurpose dispatcher, which is the main remaining gap.

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 description coverage is 100%, so the baseline is 3, and the description goes beyond it by explaining the `target` parameter's help-mode pairing, naming the CSV output columns (dimension, key, total_seconds, text) for `format=csv`, and clarifying that the format value is consumed locally. It does not characterize `body` at all, which is the one parameter with no added color beyond its schema text.

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

Purpose3/5

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

The description frames the tool as covering "the summaries toolset (5 operations)" and enumerates the actions (all_time, stats, wakatime_summaries, summary, statusbar), but never states in plain terms what a summary is or returns (aggregated coding-time statistics over a date range). An agent can infer purpose from the action names and the CSV column list, but the definition is closer to a router spec than a purpose statement, and nothing distinguishes it from sibling wakapi_heartbeats / wakapi_projects.

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?

"action help with target returns one action's parameters" is genuine, actionable discovery guidance that tells an agent how to self-serve on unknown actions. However, there is no guidance on choosing among the five actions, nor on when to use summaries versus the sibling heartbeats or projects tools. Usage is implied rather than directed.

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