fileman
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| jobs.listA | List current Fileman jobs from the local workspace job store. |
| jobs.getC | Get one Fileman job by id. |
| runtime.settings.getA | Read the current local runtime settings. |
| analyze.createC | Create an analyze job without mutating files. Review still happens later. |
| review_queue.getC | Get the review queue with deterministic copilot hints and collection slices. |
| manifest.getB | Get the manifest view for one job. Defaults to the resolved review view. |
| manifest.patch_rowB | Patch one manifest row through the overlay only. |
| manifest.batch_patchB | Patch multiple manifest rows through the overlay only. |
| review_rule.previewA | Preview a review rule against the current review queue without changing anything. |
| review_rule.applyC | Apply a review rule to the overlay only. This does not execute file changes. |
| apply.previewC | Create an apply job in dry-run mode only. |
| report.getA | Get one persisted report plus the review bridge metadata. |
| strategy_packs.listA | List repo-shipped strategy packs and the active local default. |
| watch_sources.listA | List local-first watch sources and their linked strategy packs. |
| inbox.scanA | Run inbox discovery only. This does not auto-start analyze or apply. |
| inbox.analyzeC | Create an analyze job from one watch source and optional discovered batch id. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| workflow-safety-boundary | Human-readable summary of the review-first and dry-run guardrails. |
| workflow-tool-matrix | Machine-readable list of MCP v1 tools and their underlying safety class. |