Agentdrop MCP server
Which MCP servers are Agentdrop'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 namefyi.agentdrop/agentdropverified in the MCP registry
The registry name sits under agentdrop.fyi. 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 itselfagentdrop
- Server version0.3.0
- Protocol version2025-06-18
On 2026-11-01 the server answered initialize and tools/list without a sign-in. First answer in 72 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 2 of the 7 days it takes to judge reliability.
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: 2 so far
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer287 ms
- Space in an agent's context≈ 156 tokensthe definitions of all its tools (2), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
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_servicesThe AgentDrop services with their MCP endpoints, HTTP routes, prices and limits. Free.
putStore a value under a key. Costs $0.002, charged only if the payment settles; a failed payment stores nothing. Values up to 64 KB, stored unencrypted, kept for ttl_seconds (default 3600, max 604800) then deleted. Overwrites an existing…
waitBlock until a key changes, then return it. Costs $0.001 per call whether or not anything arrives (it is a long-poll, not a subscription). Returns immediately if the key's seq is already greater than since; otherwise waits up to…
getRead a key. Free, no payment or identity needed, rate limited per address. Needs the box: a box_... id from put, or a channel name. Returns value null with found false if absent or expired. A box is a namespace of keys. Omit it on a paid…
listList the keys in a box with their seq, size and expiry, newest first, without values. Free, rate limited per address. Anyone holding the box id can do this.
deleteDelete a key from a box immediately. Free, rate limited per address. Anyone holding the box id can do this; there is no undo.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"agentdrop": {
"type": "http",
"url": "https://agentdrop.fyi/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http agentdrop https://agentdrop.fyi/mcpclaude.ai, ChatGPT and other clients: add https://agentdrop.fyi/mcp as a custom connector in the settings.
- fyi.agentdrop/aianswers, 2 toolsverified in the MCP registry
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.