Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

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

CapabilityDetails
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
scan_data_mapB

Call to see what personal data the code collects and which third-party services it sends data to. Scans the whole codebase (current folder if no config) and returns third-party services (company, country, purpose, evidence file:line), personal-data fields, and a feature list. Facts only; no judgment.

scan_changesA

Call before deploy/release when the user asks whether terms of service or privacy policy need updating. Compares the base branch (merge-base) with the working tree and returns newly added/removed third-party services, personal-data fields, features, and changed business-rule numbers, plus skipped roots and notes on comparison limits; when either is non-empty, "no impact" is not a valid answer. Optional base (branch, tag or commit) overrides the base branch.

get_policiesA

Call after scan_changes or audit to read the published terms of service and privacy policy, split into clauses (id, title, body, line). Use it to quote current wording and to locate the clause that needs to change. Requires .policy-drift.json.

get_checklistA

Call to get the required sections a privacy policy must have for the configured jurisdictions (kr, gdpr), the legal basis for each, default notice periods for changes, and the answer format to use.

auditA

Call for a first-time or full check of the published documents against the code. Mechanically compares the code with the privacy policy (services not mentioned, required sections missing, cross-border transfer) and checks both documents for broken article references. Returns findings with evidence; candidates still need a human or AI to confirm. Requires .policy-drift.json.

Prompts

Interactive templates invoked by user choice

NameDescription
pre-deploy-checkCheck whether the code changes since the base branch require updating the terms or privacy policy.
full-auditFull comparison of the published terms and privacy policy against the code.

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.9/5.0

Scored across 5 tools

Disambiguation4/5

Each tool targets a distinct phase of the policy-drift workflow: inventory, change diff, policy reading, checklist lookup, and full audit. The boundaries between scan_data_map, scan_changes, and audit are mostly clear, though an agent may occasionally hesitate between scan_changes and audit without reading descriptions carefully.

Naming Consistency4/5

Most names follow a readable verb_noun or clear action pattern: scan_data_map, scan_changes, get_policies, get_checklist. The lone 'audit' is a verb/noun hybrid but remains understandable and does not disrupt the overall pattern.

Tool Count5/5

Five tools is well-scoped for a policy-drift analysis server, covering the core workflow without redundant operations. Each tool has a clear role in the inventory, diff, read, checklist, and audit sequence.

Completeness4/5

The surface covers the main analysis lifecycle: code scanning, change detection, policy reading, jurisdiction checklist, and full audit. Minor gaps exist around updating policies or inspecting configuration, but these may be intentionally out of scope for a read-only drift-analysis server.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues