
StackPick MCP server
Which MCP servers are StackPick'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 2026-11-01
- Registry nameapp.stackpick/directoryverified in the MCP registry
The registry name sits under stackpick.app. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-11-01
- Tools6
- Server calls itselfstackpick
- Server version1.0.0
- Protocol version2025-06-18
On 2026-11-01 the server answered initialize and tools/list without a sign-in. First answer in 114 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Once connected
- For "Find the best-ranked tool for each development need", the likely first call is list_categories.
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 scoreafter a weeka score needs 7 daily checks: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer1324 ms
- Space in an agent's context≈ 555 tokensthe definitions of all its tools (6), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · Choose an AI dev stack for a project
- not sure · Compare AI coding tools by the job they do
- can do · Find the best-ranked tool for each development need
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 →
list_categoriesList StackPick jobs and the tool slugs ranked in each one. Order matches the category pages. Rankings are never paid.
get_best_toolsRanked tools for one category slug, highest score first. Scores and order match the category page. Rankings are never paid.
get_toolOne StackPick tool by slug, including its category rank, score, website, and last reviewed date. Rankings are never paid.
compare_toolsSide-by-side scores and ranks for two or more tool slugs. Each rank is within that tool's category. Rankings are never paid.
search_toolsSearch StackPick tools by name, former name, tagline, description, category, or tag. Results use the same score order as the site search.
latest_releasesNewest StackPick release notes, the same records as the changelog, newest first.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"directory": {
"type": "http",
"url": "https://stackpick.app/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http stackpick https://stackpick.app/mcpclaude.ai, ChatGPT and other clients: add https://stackpick.app/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.