GitHub Workflow Fix-and-Retry MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GH_REPO | Yes | Repository to monitor, owner/repo | |
| DATA_DIR | No | Where DB and worktrees live | /var/lib/gh-workflow-fix |
| GH_TOKEN | Yes | GitHub PAT with repo scope (rerun, issues, read workflow YAML) | |
| GH_OC_AUTO | Yes | Automatically run OpenCode fixes (true/false) | |
| GH_API_BASE | No | GitHub API base URL (for GHES) | https://api.github.com |
| OPENCODE_BIN | No | Path to the opencode binary | opencode |
| WEBHOOK_HOST | No | Bind address of the daemon | 0.0.0.0 |
| WEBHOOK_PORT | No | Bind port of the daemon | 18080 |
| FIX_TIMEOUT_S | No | Timeout for a single OpenCode fix run | 1800 |
| OPENCODE_MODEL | No | Model to pass to opencode run --model | |
| WEBHOOK_SECRET | Yes | Secret for HMAC verification (same value as the GitHub webhook) | |
| RETRY_DELAYS_MIN | No | Comma-separated delays (minutes) before attempts 1, 2, 3… | 15,30,60 |
| SCHEDULER_TICK_S | No | Scheduler tick interval in seconds | 60 |
| SELF_HEAL_MARKER | No | Marker comment that opts a workflow into self-healing | # self-heal: true |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_chainsB | List fix-and-retry chains, optionally filtered by state. |
| get_chainA | Get a single chain by ID, or error if not found. |
| retry_nowC | Schedule a chain for immediate retry. |
| pause_chainA | Pause a chain (only if running, waiting, or fix_error). |
| resume_chainB | Resume a paused chain. |
| create_issue_nowB | Create a GitHub issue for a chain (requires GitHub client). |
| set_configA | Set a configuration override (gh_oc_auto or retry_delays_min). |
| healthA | Health check with DB status and chain counts. |
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 8 tools
Each tool targets a distinct action or resource: listing/getting chains, retrying, pausing/resuming, creating issues, config, and health. There is minor potential confusion between retry_now and resume_chain since both make a chain active again, but the descriptions clarify the difference. Overall, boundaries are clear.
Most tools follow a verb_noun pattern: list_chains, get_chain, pause_chain, resume_chain, set_config. Minor deviations include health (bare noun) and create_issue_now (verb_noun_adverb), but these are still readable and do not break the overall convention.
Eight tools is a well-scoped set for a fix-and-retry workflow server. Each tool covers a necessary operational aspect: inspection, state changes, issue creation, configuration, and health monitoring. No tool feels redundant or extraneous.
The tool surface covers the core lifecycle of chains: list, get, retry, pause, resume, plus config and health. A delete/cancel operation is missing, but it may not be needed for this domain. Minor gap, but agents can generally operate without dead ends.