Agent Router MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KEV_MODEL | No | Kev model name. Defaults to 'kev-latest'. | kev-latest |
| KEV_BASE_URL | No | Base URL for the local Kev server. Optional. | |
| KEV_TIMEOUT_MS | No | Timeout in milliseconds for Kev requests, between 1,000 and 120,000. Defaults to 30,000. | 30000 |
| ROUTER_DECISION_BACKEND | No | Selects the decision backend. Defaults to 'laya'. Set to 'kev' to use the local Kev server. | laya |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| route_next_stageA | Let the configured decision backend pick the best-fitting worker model for one substantial Herdr stage from the whole Claude and Codex catalog. Leave compare_providers=true and omit client; the selected choice is returned even when uncertain. Pass client only with compare_providers=false. The returned client determines the worker kind. Supply a compact task, progress and acceptance summary. |
| advise_next_actionA | Advisory choice among 2-4 explicit, bounded development actions when the next step is uncertain. Supply evidence and constraints. Low confidence calls for more evidence; approval remains with the user. |
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 2 tools
Both tools are decision/routing helpers that pick among options for the 'next step,' which creates real overlap in intent. The descriptions do distinguish them (route_next_stage selects a worker model/backend for a Herdr stage, while advise_next_action recommends among bounded development actions), but an agent could plausibly reach for the wrong one when unsure what to do next.
Both names follow the same verb_noun pattern (route_next_stage, advise_next_action) with snake_case throughout. The convention is predictable and readable.
Two tools is thin for a routing/decision server, sitting at the borderline where a set feels underdeveloped. It is not extreme, but there is little surface to work with.
The domain (decision routing over model catalogs and next actions) implies supporting operations like inspecting the catalog, configuring the backend, or querying available workers, none of which exist. The surface is a narrow slice with notable gaps.