q-skillvault
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SKILLVAULT_COMPAT_ENGRAM | No | Set to 1 to run SkillVault as a drop-in replacement for Engram, exposing compatible MCP tool aliases. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| save_entryC | Save a vault entry (prompt, skill, decision, etc.) |
| search_entriesC | Search entries with FTS5 and filters |
| get_entryB | Get a vault entry by ID (includes artifact reference if linked) |
| save_artifactC | Save a long AI output or file-backed artifact |
| get_contextC | Compile agent-ready context pack from vault data |
| compose_seriesC | Return ordered entries in a series |
| render_workflowB | Return workflow steps as a checklist |
| session_wrapC | Save a compact session summary with decisions, pending items, and learnings |
| archive_entryB | Soft-delete an entry (set status to archived) |
| list_projectsB | List all projects and their statuses |
| save_entry_refC | Create or update a link between two entries (graph edge) |
| list_entry_refsC | List graph edges between entries |
| get_entry_graphC | Traverse entry graph from a starting entry, returning connected nodes and edges |
| search_by_tagsC | Search entries by tags with all/any match against the junction table |
| get_context_bundleB | Return structured JSON bundle: project info, entries grouped by type, and artifact refs |
| compare_entriesA | Compute line-based LCS unified diff between two entries |
| save_resultC | Save an AI prompt result as a vault entry |
| run_workflowC | Execute a workflow with structured step inputs and return per-step results |
| route_scenarioC | Resolve a free-text scenario to a matching workflow or skill |
| get_statsB | Return vault statistics including workflow run analytics |
| list_workflow_runsC | List workflow runs with optional workflow filter and step progress |
| get_runA | Get a single workflow run with its step details |
| list_entry_versionsB | List version history for an entry (descending by version number) |
| restore_entry_versionC | Restore an entry to a previous version by version number |
| save_handoffC | Save a structured agent-to-agent task handoff / checkpoint |
| get_handoffA | Retrieve the latest agent-to-agent task handoff for a project or task_id |
| add_linkC | Store a URL bookmark with an alias keyword for quick retrieval |
| get_linkC | Resolve an alias keyword to its stored URL |
| search_linksA | Search stored URL bookmarks with FTS5 across title, summary, tags, and URL |
| list_linksA | List all stored URL bookmarks, optionally filtered by project |
| add_instructionC | Store a command snippet or instruction recipe with placeholders (e.g. {{input}}) |
| get_instructionB | Resolve an instruction recipe by alias with optional variable interpolation |
| search_instructionsC | Search instruction recipes and command snippets with FTS5 |
| list_instructionsA | List all stored instruction recipes, optionally filtered by project |
| vault_mem_saveA | Save an episodic observation memory with deduplication and topic indexing |
| vault_mem_searchB | Search observation memories with preview truncation and filters |
| vault_mem_getC | Get complete content and metadata of an observation memory by ID |
| vault_mem_timelineC | Retrieve chronological context before and after a memory observation |
| vault_mem_contextC | Build a compact agent-ready memory context pack for a project |
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 39 tools
Tools are broadly separated by resource (entries, links, instructions, memories, workflows), but there is real overlap: get_context, get_context_bundle, and vault_mem_context all build agent context; save_entry and save_result both save entries; search_entries and search_by_tags overlap. Descriptions help, but an agent can still hesitate between several similarly scoped tools.
Most names are readable snake_case, often verb_noun (save_entry, get_entry, list_links, search_instructions). However, conventions are mixed: vault_mem_save puts the verb last with a namespace prefix, while session_wrap, compose_series, route_scenario, and render_workflow use less predictable verb/noun shapes.
With 39 tools, the server is clearly overgrown for a single MCP surface, spanning entries, graph refs, versions, workflows, runs, memories, links, instructions, handoffs, artifacts, and projects. This likely exceeds what an agent can comfortably scan and select from without grouping or splitting.
Entry lifecycle coverage is strong, including save/get/search/archive, versions, restore, graph refs, tags, compare, and context packs. But secondary resources have notable gaps: links and instructions lack update/delete, memories lack update/delete, handoffs have only save/get, and projects have list but no create/update operations.