
KPI Depot MCP server
Which MCP servers are KPI Depot's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-17
- Registry namecom.kpidepot/kpi-depotverified in the MCP registry
The registry name sits under kpidepot.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-17
- Tools3
- Server calls itselfkpi-depot
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-17 the server answered initialize and tools/list without a sign-in. First answer in 282 ms.
- Its tools do none of the product's use cases we checked: choose which KPIs to track for a function; set benchmark-based targets for a KPI; export a balanced scorecard as a CSV template.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score72 of 100answers 100 · does the job 0 · definitions 100 · context 100 · connects 100
- What an agent can do with it0 of 3 use cases
- Answered100% of days8 of 8 daily checks
- Median first answer291 ms
- Space in an agent's context≈ 667 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- cannot · choose which KPIs to track for a function
- cannot · set benchmark-based targets for a KPI
- cannot · export a balanced scorecard as a CSV template
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_kpisSearch KPI Depot's library of 20,000+ corporate KPIs by keyword, with optional corporate-function and industry filters. Returns up to 10 relevance-ranked matches, each with a one-line definition, its benchmark count, and the KPI's page…
get_kpiFull intelligence for a single KPI: definition, standard formula, common pitfalls, improvement levers, related KPIs, the KPI groups it belongs to, and metadata about its available benchmarks (benchmark values themselves come from…
get_benchmarksBenchmark data for a single KPI (one kpi_id per call): benchmark values with descriptive metadata (industry, geography, time period, sample size) and full source attribution (source name, URL, excerpt, and comments). Each response…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"kpi-depot": {
"type": "http",
"url": "https://kpidepot.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http kpidepot https://kpidepot.com/mcpclaude.ai, ChatGPT and other clients: add https://kpidepot.com/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.