Context Loom
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 |
|---|---|
| hydrate_messageD | Compile a source-preserving prompt envelope for one exact user message. |
| get_contextC | Read the canonical envelope for a hydration identifier. |
| explain_selectionC | Explain selected and omitted resources with score components and fidelity gates. |
| record_usageB | Idempotently record provider-observed usage and return updated thread totals. |
| thread_statsB | Read confidence-separated lifetime token metrics for one thread. |
| workspace_statusC | Read active generation, freshness, and synchronization status. |
| resolve_resource_versionC | Resolve immutable sanitized content from an omission recovery reference. |
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 7 tools
Each tool targets a fairly distinct operation within the hydration pipeline: hydrate_message compiles an envelope, get_context reads one by id, explain_selection explains choices, record_usage writes metrics, thread_stats/workspace_status read state, and resolve_resource_version recovers omitted content. Minor overlap exists between hydrate_message and get_context (both concern envelopes) and between record_usage and thread_stats (both concern token metrics), but descriptions keep them separable.
Most tools follow a clear verb_noun pattern (hydrate_message, record_usage, get_context, explain_selection, resolve_resource_version), but thread_stats and workspace_status drop the verb and use noun_noun, breaking the otherwise consistent convention. Still readable and largely predictable.
Seven tools is well-scoped for a context-hydration and usage-tracking server, with each tool covering a distinct part of the pipeline (hydrate, read, explain, record, stats, status, resolve). No redundant or filler tools.
The surface covers the core lifecycle: hydrate, read, explain, record usage, inspect stats/status, and recover omitted resources. Gaps exist for thread deletion/forgetting, listing threads, or bulk config, but agents can work around these for the primary workflows.