context-archive
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CONTEXT_ARCHIVE_HOME | No | Set to an absolute alternate directory. Runtime, configuration, archive, and logs live under ~/Library/Application Support/ContextArchive/ by default. |
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 |
|---|---|
| statusC | Status; bounded read-only archive retrieval. |
| sourcesC | Sources; bounded read-only archive retrieval. |
| searchC | Search; bounded read-only archive retrieval. |
| timelineC | Timeline; bounded read-only archive retrieval. |
| get_recordB | Get record; bounded read-only archive retrieval. |
| get_blobC | Get blob; bounded read-only archive retrieval. |
| decode_blobC | Decode blob; bounded read-only archive retrieval. |
| describe_schemaC | Describe schema; bounded read-only archive retrieval. |
| queryC | Query; bounded read-only archive retrieval. |
| app_usage_summaryD | App usage summary; bounded read-only archive retrieval. |
| domain_summaryC | Domain summary; bounded read-only archive retrieval. |
| projectsA | Read explicit project rules. Rule matches are associations, not proof of work. |
| episodesC | Temporal groups within a timezone-aware window, with source lanes and evidence. Not dwell time or causal links. Narrow the window if a budget is exceeded. |
| project_timelineC | Find events associated by explicit project rules; each match explains its rule indexes and links to evidence. |
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 14 tools
Many tools share the exact same description prefix 'bounded read-only archive retrieval,' making it difficult to distinguish e.g. search from query, or timeline from episodes from project_timeline. A few tools are clearer, but the set has notable overlapping retrieval purposes.
Naming is inconsistent: single-word nouns like 'status' and 'sources' sit alongside verb-prefixed names like 'get_record' and 'decode_blob,' compound nouns like 'app_usage_summary,' and multiword names like 'project_timeline.' No consistent verb_noun or noun_noun convention is maintained.
Fourteen tools is within a reasonable range for an archive-retrieval server. The count feels slightly padded because several tools may overlap, but it is not excessive or clearly under-scoped.
The tool set covers core retrieval operations, schema introspection, blob decoding, and timeline/summary views, which is plausible for a read-only archive. However, there are gaps such as no obvious listing/enumeration of available sources or archives, and the relationship between query, search, and get_record is unclear enough to create potential dead ends.