Reports each server: installed, running or not, its endpoint and the models it serves.

GET

/v1/m/agenttools/model-servers

curl --request GET \
  --url https://example.com/v1/m/agenttools/model-servers \
  --header 'Authorization: Bearer <token>'

• this engine

Reports each server: installed, running or not, its endpoint and the models it serves.

Authorizations

• bearerAuth
• browserSession

Responses

200

Each local OpenAI-compatible model server (llama.cpp, vLLM): installed, running or not, its endpoint and the models it serves

Media type application/json

object

servers

required

Array<object>

object

endpoint

string

installed

required

boolean

kind

required

string

Allowed values: llama-cpp vllm

message

string

model

string

models

required

Array<string>

name

required

string

state

required

string

Allowed values: stopped starting running failed

Example

{
  "servers": [
    {
      "kind": "llama-cpp",
      "state": "stopped"
    }
  ]
}

400

Bad request

Media type application/json

object

Example ^generated

{}

401

Unauthenticated

Media type application/json

object

Example ^generated

{}

403

Forbidden / step-up required

Media type application/json

object

Example ^generated

{}

404

Not found

Media type application/json

object

Example ^generated

{}

409

Conflict

Media type application/json

object

Example ^generated

{}

503

Required evidence or store unavailable

Media type application/json

object

Example ^generated

{}