agent-as-model
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| chat_completeA | Generate a chat completion from an OpenAI chat-completions-shaped request. The completion is produced by the host agent's own model via MCP sampling. No API key is used or needed: the connected agent is the model. |
| messages_createA | Generate a completion from an Anthropic messages-shaped request. The completion is produced by the host agent's own model via MCP sampling. No API key is used or needed: the connected agent is the model. |
| list_modelsA | List the models this server offers. There is exactly one: agent-default, an alias for the host agent's own model. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
chat_complete and messages_create serve genuinely distinct request shapes (OpenAI vs Anthropic schemas), and the descriptions make this clear. However, both do essentially the same thing — run a completion through the host agent — so an agent without a strong schema preference could still hesitate between them.
Naming mixes conventions: 'chat_complete' is noun_verb while 'messages_create' is plural_noun_verb and 'list_models' is verb_noun. The verb position flips between first and last, and no single pattern dominates.
Three tools are a tight, well-scoped surface for a thin model shim. The count is slightly thin but each tool earns its place; list_models is arguably redundant given the single-model aliasing, keeping it just below a 5.
The server covers the two dominant completion request shapes plus discovery, so core workflows are reachable. Minor gap: no streaming or token-counting option, and no way to introspect model capabilities, but agents can work around these.