Skip to main content
Glama
JAAvila-Of

vivac

by JAAvila-Of
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

Retain selected artifact deliveries

vivac_artifacts

Capture, list, verify, and restore retained HTML or frontend previews with pinned revisions and provenance, preferring no backend.

Instructions

Retain visual or interactive previews by default: self-contained HTML or a complete HTML/CSS/JS frontend. Use vivac-artifacts and prefer no backend. Other UTF-8 files, including reports, documentation, JSON results, SQL, source and configuration, require the person's explicit selection as deliveries. Operations mirror vivac artifacts: capabilities, list, show, capture, check and restore. Capabilities reports installed formats and limits without reading project state; it takes no other arguments. Capture requires exactly one of path or bundle, an explicit producer from, and a brief description of what this revision does. Bundle names a project-relative JSON selection file, not another delivery. Use artifact and previous to continue a known identity; never merge by filename. List defaults to focus lineage; all lists the project. Returned references pin artifact identity and revision; retention does not approve a delivery or prove a source snapshot. Check verifies the complete retained revision independently of member pagination; metadata listings remain unverified. Restore writes a new file or complete directory and never overwrites. Store check reports unrecorded objects without inventing provenance; orphan restore rescues their bytes without recording a delivery. Custody does not execute content, install dependencies or watch folders. PNG/MP4 bundle members require installed media support and prior human review of exact bytes; automatic inspection covers structure and accessible text, not pixels or speech. SQLite requires explicit installed support; never assume it. Content and descriptions must pass sensitive-value guards; a complete revision is limited to 10 MiB.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoNew project-relative destination for restore.
allNoList the whole project, instead of focus lineage.
fromNoProducer node for capture, or scope node for list.
pathNoSelected project-relative source; capture only.
limitNoList page size, between 1 and 100.
storeNoCheck the retained store explicitly; takes no artifact identity.
bundleNoProject-relative JSON selection file for a complete frontend bundle, optionally with paired database and fixed runtime identity when sqlite_application is supported; capture only, exclusive with path.
offsetNoNonnegative list offset.
orphanNoUnrecorded retained object identity for explicit rescue.
artifactNoStable artifact identity, never inferred from a filename.
previousNoExpected previous revision for capture.
revisionNoExact retained revision for show, check or restore.
operationYescapabilities, list, show, capture, check or restore.
descriptionNoRequired for capture: what this revision does, in one line of up to 280 Unicode characters.
operation_idNoOpaque ULID for retrying one capture without recapturing bytes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.20.0
    • addedInput schema / properties / bundle
      Added value: +{
+  "description": "Project-relative JSON selection file for a complete frontend bundle, optionally with paired database and fixed runtime identity when sqlite_application is supported; capture only, exclusive with path.",
+  "type": "string"
+}
    • addedInput schema / properties / description
      Added value: +{
+  "description": "Required for capture: what this revision does, in one line of up to 280 Unicode characters.",
+  "type": "string"
+}
  2. Addedv0.18.2

TDQS

A4.1/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With annotations only covering safety flags, the description adds substantial non-obvious behavior: restore writes a new file/directory and never overwrites, retention does not approve a delivery or prove a source snapshot, check verifies the full revision independently of pagination while metadata listings stay unverified, and orphan restore rescues unrecorded bytes without recording a delivery. It also discloses hard constraints — sensitive-value guards, a 10 MiB revision limit, required media support and prior human review for PNG/MP4, and explicit SQLite support.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is dense with no filler, but it is a single undifferentiated paragraph of roughly 160 words spanning eligibility rules, six operation semantics, limits and media caveats. There is no structure — no separation of operations or constraints — so an agent must parse the whole block to find the sentence relevant to its chosen operation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter, six-operation tool with no output schema, the description covers a lot that matters: return semantics (references pin artifact identity and revision), check-vs-listing verification asymmetry, restore's non-overwrite behavior, and capability probing. It is close to complete, though it never addresses list paging behavior or the operation_id retry parameter, both of which are left entirely to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description genuinely adds meaning beyond the schema: bundle is clarified as a project-relative JSON selection file rather than another delivery, artifact/previous are framed as identity continuation with 'never merge by filename', and capture's exact one-of path/bundle requirement plus required producer 'from' is stated. It does not cover limit/offset/all semantics in prose, which the schema already handles.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource — retaining artifact deliveries (visual/interactive previews, self-contained HTML or HTML/CSS/JS frontends) — and enumerates the six operations it mirrors, so an agent can tell it apart from unrelated siblings like vivac_find or vivac_note. The operation list is buried mid-paragraph rather than front-loaded, which slightly costs clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It draws a clear when/when-not boundary: previews retain by default with no backend preferred, while reports, docs, JSON, SQL, source and config require explicit human selection as deliveries. Operation-specific selection is also given (capabilities takes no arguments; capture requires exactly one of path or bundle). No sibling alternative is named, but no sibling covers artifacts.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools