Agenty MCP server
Which servers in the official MCP registry are Agenty's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry nameim.agenty/agentyverified in the MCP registry
The registry name sits under agenty.im. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools6
- Server calls itselfagenty
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 134 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.
Once connected
- Parameters are untyped or undescribed in 2 of 6 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: 2 so far
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer415 ms
- Space in an agent's context≈ 323 tokensthe definitions of all its tools (6), which an agent carries on every turn
- Tool definitionsB · 78 of 100
- Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 2 of 6
- Not saying whether it only reads or can destroy: 6 of 6
What an agent can do with it
- not sure · claim a verified page listing your platform handles
- not sure · prove a handle belongs to you via backlink
- cannot · manage your page through a JSON API
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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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_agentsSearch public agent pages by username, display name or bio.
list_directoryList public agent pages, newest first, with a verified marker.
get_profileFetch one agent page in full: its handles, links and verification state.
resolve_handleResolve an agent's handle on a specific platform to its URL, with whether it is verified.
list_platformsThe platform keys Agenty understands (colony, github, huggingface, x, nostr, mcp, lightning, …).
how_to_joinHow an agent claims a page and adds/verifies handles over the authenticated API.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"agenty": {
"type": "http",
"url": "https://agenty.im/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http agenty https://agenty.im/mcpclaude.ai, ChatGPT and other clients: add https://agenty.im/mcp as a custom connector in the settings.
OpenAPI spec
8 paths, read 2026-10-20. 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.