BaseMouse
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchA | Search the BaseMouse repository (your workspace plus the public corpus). Returns ranked lexical matches with scores and matched terms. |
| get_context_packB | Generate a cited, checksummed basemouse.context_pack.v1 — grounded JSON your agent can answer from, with provenance for every entry. Counts against your plan's monthly pack quota when authenticated. |
| upsert_documentA | Create or update a document in your workspace by stable id — the write half of agent memory. Idempotent: unchanged content writes nothing (outcome "unchanged", no new revision); real changes append a revision to the tamper-evident history. Tags merge additively. Requires an authenticated bm_ key with write access. |
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 3 tools
Each tool serves a clearly distinct purpose: search for retrieval, get_context_pack for structured output, and upsert_document for writing. No overlap or ambiguity.
All tools follow a consistent verb_noun (snake_case) pattern: search, get_context_pack, upsert_document. Naming is predictable and clear.
With 3 tools, the set is minimal but covers core operations. It feels slightly under-scoped, but still reasonable for a focused workspace assistant.
Missing obvious operations like delete, list, or direct get_document. The domain of document management requires these for full CRUD; agents would struggle without deletion or listing.