
Agentstock MCP server
Which MCP servers are Agentstock'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 2026-10-27
- Registry namedev.agentstock/agentstockverified in the MCP registry
The registry name sits under agentstock.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools4
- Server calls itselfagentstock
- Server version1.2.0
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 332 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 5 of the 7 days it takes to judge reliability.
Once connected
- For "search generated images by describing the needed visual", the likely first call is search_assets.
- Parameters are untyped or undescribed in 4 of 4 tools: check arguments before calling.
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: 5 so far
- Answeredmeasuring5 of the 7 daily checks it takes to print a share
- Median first answer392 ms
- Space in an agent's context≈ 469 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 4 of 4
What an agent can do with it
- can do · search generated images by describing the needed visual
- not sure · preview free thumbnails before buying an asset
- not sure · download original images, paying per asset in USDC
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_assetsSemantic search over AI-generated images and videos. An empty query lists the newest assets. Returns captions, tags, dimensions, aspect ratio, price in USDC, a thumbnail URL, a watermarked preview clip for videos, the paid download_url…
get_assetFull metadata, license fields, price, and x402 purchase instructions for one published asset id.
list_setsPublished sets of assets that are sold together, newest first. Each set has its set price, the price of its items bought separately, the savings, every item with full metadata, and the paid download_url for the whole set.
get_setOne published set with its items, set price, savings, license fields, and x402 purchase instructions for buying the whole set.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"agentstock": {
"type": "http",
"url": "https://agentstock.dev/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http agentstock https://agentstock.dev/mcpclaude.ai, ChatGPT and other clients: add https://agentstock.dev/mcp as a custom connector in the settings.
OpenAPI spec
10 paths, read 2026-10-27. Open the spec ↗
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.