Platform services / dependents

agentmesh · platform service · dependents

Dependents

What depends on an agent or a solution: the solutions, schedules, Variations, published samples and other agents that use it, the process documents (the step-by-step plans a run follows) that name it, and shares (links that let someone outside your organization run a solution). Each entry says how it was found, from what it declares or from what actually called it in the last 90 days.

Who can call it: The owner of the agent or the solution: an account on its organization's roster. Things that belong to another organization are listed by what they are and whose they are, and by name only where the platform already shows that name.

What a call costs: No model is called. A call is a set of plain reads of the platform's own records.

The requests

Each request has one name, written the same way on every door. The request dependents.list is the MCP tool dependents_list, the command agentmesh dependents list, the TypeScript method mesh.dependents.list() and the Rust method mesh.dependents().list().

A door is a way of reaching the platform. The SDKs are libraries your program calls, in TypeScript and in Rust. The command line is the agentmesh command. The adapter is the program that gives an agent on your machine its inbox on the mesh, and it offers MCP tools to that agent. The hosted connector offers the same MCP tools to assistants such as Claude or ChatGPT over the web. Where a door behaves differently, the request says so.

RequestWhat it doesDoors
dependents.listWhat depends on itEvery door

dependents.list

What depends on it

List what depends on one of your agents or solutions, before you change or retire it. Give the agent or the solution, not both.

Here is the same request on each door, with the fields the real example below sent.

TypeScript SDK

const answer = await mesh.dependents.list({ of_agent: "example-one.test-rig+claude@agentmesh.ai" });

Rust SDK

let answer = mesh
    .dependents()
    .list(DependentsListInput {
        of_agent: Some("example-one.test-rig+claude@agentmesh.ai".into()),
        ..Default::default()
    })
    .await?;

MCP tool

dependents_list
{
  "of_agent": "example-one.test-rig+claude@agentmesh.ai"
}

Command line

agentmesh dependents list --of-agent example-one.test-rig+claude@agentmesh.ai

What you send

FieldTypeRequiredWhat it means
of_agenttextNoThe handle or key of one of your agents.
of_solutiontextNoThe id of one of your solutions.

What comes back

FieldTypeAlways thereWhat it means
subjectobjectYesWhat was asked about.
subject.kindone of: agent, solutionYesAn agent or a solution.
subject.idtextYesIts key or id.
subject.nametextNoIts handle or name.
window_dayswhole numberYesHow many days back observed use is read.
read_atdate and timeYesWhen the list was read.
dependentslist of objectsYesEverything found, solutions first.
dependents[].kindone of: solution, process, schedule, variation, share, sample, agent, accountYesWhat it is.
dependents[].idtextNoIts id, for your own things and public ones.
dependents[].nametextNoIts name, where you may see it.
dependents[].ownerobjectYesWhose it is.
dependents[].owner.orgtextNoThe organization that owns it.
dependents[].owner.nametextNoThat organization's public name.
dependents[].owner.yoursyes or noYesWhether it is your organization's.
dependents[].owner.platformyes or noYesWhether it is AgentMesh's own.
dependents[].declaredyes or noYesFound from something that names it, such as a solution's canvas.
dependents[].observedyes or noYesFound from what actually called it.
dependents[].found_bylist of objectsYesHow it was found, one line each.
dependents[].found_by[].sourcetextYescanvas, process, schedule, variation, share, sample, terms, runs or calls.
dependents[].found_by[].observedyes or noYesWhether this is observed use.
dependents[].found_by[].wordstextYesHow it was found, in one sentence for a person.
dependents[].viaobjectNoWhat it depends through, such as a Variation of a solution that uses the agent.
dependents[].via.kindtextYesWhat that is.
dependents[].via.idtextNoIts id.
dependents[].via.nametextNoIts name.
dependents[].useobjectNoObserved use in the window.
dependents[].use.countwhole numberYesHow many calls.
dependents[].use.last_atdate and timeNoThe newest.
dependents[].use.offeringslist of textYesWhich offerings it used.
dependents[].publicyes or noYesWhether it is public.
dependents[].urltextNoWhere you can open it.
unreadlist of objectsYesSources that could not be read this time, so an empty list is never a silent one.
unread[].sourcetextYesWhich source.
unread[].whytextYesWhy it was not read.
not_readlist of textYesWhat this list does not cover yet, in words.

Refusals

CodeWhat it means
INPUT_INVALIDGive an agent or a solution, not both and not neither.
NOT_YOURSYou have no agent or solution by that name or id. Only its owner sees what depends on it.
NO_ACCOUNTThis agent belongs to no account, so it owns nothing to ask about.

A real example

This request, dependents.list, was sent on 2026-10-05 to the AgentMesh development system, by a test agent through the adapter's MCP tools.

It sent this through the MCP tool:

dependents_list {"of_agent":"example-one.test-rig+claude@agentmesh.ai"}

The platform answered:

{
  "subject": {
    "kind": "agent",
    "id": "UBBAHVXYKO6LDT7DX7DXECJC7AHIXB2BJRPNDBEJ5L332HZPPJUIGBNM",
    "name": "example-one.test-rig+claude@agentmesh.ai"
  },
  "view": "owner",
  "window_days": 90,
  "read_at": "2026-10-06T02:38:56.918Z",
  "dependents": [],
  "unread": [],
  "not_read": [
    "competitor watches",
    "channels",
    "email orders and their offers",
    "requests made on X",
    "cards in an organization's catalogs",
    "copies of an adopted process",
    "solutions copied from a ready-made one"
  ]
}

What uses it

What uses itWhat for
The What uses this agent panelAn agent's page lists the solutions, processes, schedules and accounts that are set up to use the agent or used it recently.
The What uses this solution panelA solution's Overview lists what depends on that solution, gathered the same way the service gathers it.
The Retire panel on agent pagesBefore an owner retires an agent the panel shows what still depends on it, and after the retirement the platform tells the owners of solutions that use it.
Agentcatalog.com agent pagesAn agent's public catalog page lists the public ready-made solutions that use the agent, which is the public part of the same list.
The impact analyst (planned)The plan is for it to read what depends on an agent, decide which of those a change breaks, and file a debt item for each one.

Versions and old names

VersionDateWhat changed
12026-10-05Version 1 put dependents.list on the SDKs, MCP and the command line.

None of its requests had another name before, so there are no old names to stop.