
Marketcaper MCP server
Which MCP servers are Marketcaper'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 2026-10-21
- Registry namecom.marketcaper/mcpverified in the MCP registry
The registry name sits under marketcaper.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-21
- Tools4
- Server calls itselfmarketcaper-mcp
- Server version1.4.0
- Protocol version2025-06-18
On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 514 ms.
- Its tools do every use case we checked: compare market caps of two assets side by side; view relative size of stocks, crypto, funds, and GDP.
Once connected
- For "compare market caps of two assets side by side", the likely first call is compare_assets.
- For "view relative size of stocks, crypto, funds, and GDP", the likely first call is compare_assets.
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 score100 of 100answers 100 · does the job 100 · definitions 100 · context 100 · connects 100
- What an agent can do with it2 of 2 use cases
- Answered100% of days13 of 13 daily checks
- Median first answer535 ms
- Space in an agent's context≈ 1,098 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- can do · compare market caps of two assets side by side
- can do · view relative size of stocks, crypto, funds, and GDP
- not sure · check hypothetical prices for supported price-based comparisons
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 →
get_asset_snapshotResolve one Marketcaper asset and return its reported size snapshot. Check the input observation time and always cite the returned source_url when using the data.
compare_assetsCompare two Marketcaper assets and return relative size or a supported hypothetical price-at-size scenario, the canonical pair URL, and an optional hosted image URL. Hosted images are PNG, generated on demand, share a 10 images/day/IP…
compare_assets_packCompare two Marketcaper assets and return the same cited comparison data plus a draft short post for review and share payload with the hosted comparison image URL. Always cite the returned source_url when using the data.
get_stock_heatmapReturn a Marketcaper stock heatmap summary with reported observation and update times, plus a hosted dark-theme PNG image URL. Supports US or global universes, classic or bubble views, optional sector/category filtering, and capped…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"marketcaper": {
"type": "http",
"url": "https://marketcaper.com/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http marketcaper https://marketcaper.com/api/mcpclaude.ai, ChatGPT and other clients: add https://marketcaper.com/api/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.