open-delegate
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPEN_DELEGATE_ODE_MODELS | No | CSV list of model identifiers that should always use open-delegate (force routing) | |
| OPEN_DELEGATE_DENY_MODELS | No | CSV list of denied model identifiers | |
| OPEN_DELEGATE_ALLOW_MODELS | No | CSV list of allowed model identifiers | |
| OPEN_DELEGATE_OPENCODE_BIN | No | Full path to the opencode CLI binary if not on PATH | |
| OPEN_DELEGATE_DEFAULT_MODEL | No | Default model identifier for opencode sessions (e.g., opencode/deepseek-v4-flash-free) | |
| OPEN_DELEGATE_ODE_MODELS_FILE | No | Path to a JSON array or CSV file listing models for force routing | |
| OPEN_DELEGATE_OPENCODE_CONFIG_CONTENT | No | Full OpenCode configuration blob (advanced usage) |
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 |
|---|---|
| ode_delegateA | Starts a new OpenCode agent session to work on Model policy (cost-first):
|
| ode_awaitA | Blocks (up to a clamped timeout) until the session started by ode_delegate finishes, then returns its final status (plus a capped |
| ode_transcriptA | Fetches the conversation so far for a session started by ode_delegate, without waiting for it to finish. |
| ode_cancelA | Aborts an in-progress session started by ode_delegate. A no-op (still returns ok) if it already finished. |
| ode_diagnosticsA | Read-only snapshot of the open-delegate MCP bridge itself (not a specific session): its own pid/version/log paths, every live opencode runtime with its own pid/url/log path, recent internal events, and session counts by status. Use this to diagnose host-side "Connection stopped" / "Timed out waiting for connection" errors, or to find which opencode process/log backs a given runtimeKey. |
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 5 tools
Each of the five tools has a clearly distinct purpose: starting a session, waiting for completion, fetching transcript, canceling, and diagnostics. There is no overlap or ambiguity.
All tools share the 'ode_' prefix and mostly use imperative verbs (delegate, await, cancel), but 'transcript' is a noun, breaking the pattern slightly. Overall consistent.
Five tools are well-scoped for managing agent sessions: start, wait, fetch transcript, cancel, and diagnostics. Neither too few nor too many.
The set covers core session lifecycle (start, wait, cancel, transcript), but lacks a tool to list session IDs explicitly. Diagnostics provides session counts but not individual IDs, a minor gap.