Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
WHALORY_HUBNoSet to 0 to turn off the whole Hub (WHALORY_HUB=0).

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

Whalory tools check and support English and Persian business copy. Call lint_text or lint_file after drafting, and check_final once on the copy the user approves; channel_limits before writing for a platform; get_playbook to load the procedure for a task; get_reference_section to read one section of a craft reference; profile_lookup to find the brand voice. Tools never access the network. «ابزارهای والوری برای متنِ فارسی و انگلیسی‌اند.»

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

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

Tools

Functions exposed to the LLM to take actions

NameDescription
lint_textA

Check Persian or English copy against Whalory's rules (AI tells, puffery, spelling, punctuation, sentence length, readability, brand profile and channel limits). Language is detected per line unless set.

lint_fileB

Lint a text, Markdown, HTML, CSV/TSV or locale file (json, po, arb, xliff, strings, strings.xml) inside an allowed folder. Locale keys and placeholders are never changed; CSV issues are keyed row/sku/column.

check_finalA

Final check of the copy the user approved: runs Whalory's checks and returns any remaining findings, in the same form as lint_text. Call it once when the user approves final copy. If the user turned on Whalory Hub statistics or weekly packets in their own terminal, it also records counts on this computer, never text, of which Whalory checks the user's own edits removed. With statistics, the user chose to send those counts weekly to Whalory's server in Iran; a packet leaves the computer only if the user posts it on GitHub.

get_playbookA

Return the Whalory playbook section for a task (steps, questions, references, output, QA). Accepts a playbook anchor such as 'caption' or a free-text task in English or Persian; returns the best match and up to limit-1 alternatives.

get_reference_sectionA

Read one section (or the contents list) of a Whalory reference file under references/ (method, fa/, en/), profiles/ or data/channels/. Long files: call without anchor to get the contents list first.

profile_lookupA

Find the brand voice profile in Whalory's order: project VOICE.md/voice.json/voice/VOICE.md, ~/.whalory/profiles/, the skill's profiles, the closest starter. Returns the normalized JSON profile, the learnings note and starter suggestions.

Prompts

Interactive templates invoked by user choice

NameDescription
writeLoad the Whalory method and write copy for a task, channel and output language.
reviewScore a draft as a blind editor: score table, must-fix list and at most three line edits.
voiceBuild VOICE.md and voice.json for a brand from a few answers or sample texts.

Resources

Contextual data attached and managed by the client

NameDescription
SKILL.md
GUIDE.en.md
GUIDE.fa.md
README.en.md
README.md
references/brief.md
references/editor.md
references/gathering.md
references/hub.md
references/intake.md
references/judgment.md
references/playbooks-messages.md
references/playbooks-product.md
references/playbooks-repair.md
references/playbooks-social.md
references/playbooks-strategy.md
references/playbooks-web.md
references/playbooks.md
references/profile-builder.md
references/review.md
references/router-examples.md
references/router.md
references/task-index.md
references/voice-profile.md
references/en/ai-tells.md
references/en/channels.md
references/en/claims.md
references/en/common-errors.md
references/en/craft.md
references/en/ethics.md
references/en/forms.md
references/en/occasions.md
references/en/plain-english.md
references/en/prose.md
references/en/style-guide.md
references/en/style-repair.md
references/fa/ai-tells.md
references/fa/channels.md
references/fa/claims.md
references/fa/common-errors.md
references/fa/conventions.md
references/fa/craft.md
references/fa/ethics.md
references/fa/forms.md
references/fa/occasions.md
references/fa/persian-prose.md
references/fa/plain-persian.md
references/fa/style-repair.md
references/writing/brand.md
references/writing/commerce.md
references/writing/copy_ads.md
references/writing/credentials_sales.md
references/writing/management.md
references/writing/messaging.md
references/writing/operations.md
references/writing/people.md
references/writing/pr_media.md
references/writing/product.md
references/writing/scripts_training.md
references/writing/seo_editorial.md
references/writing/social.md
references/writing/support.md
references/writing/ux.md
references/writing/web.md
profiles/LEARNINGS-template.en.md
profiles/LEARNINGS-template.md
profiles/_template.en.json
profiles/_template.en.md
profiles/_template.json
profiles/_template.md
profiles/whalory.en.json
profiles/whalory.en.md
profiles/whalory.json
profiles/whalory.md
profiles/starters/README.md
profiles/starters/cafe.json
profiles/starters/cafe.md
profiles/starters/saas.json
profiles/starters/saas.md
profiles/starters/en/cafe.json
profiles/starters/en/cafe.md
profiles/starters/en/saas.json
profiles/starters/en/saas.md

TDQS

A3.6/5.0

Scored across 6 tools

Disambiguation3/5

The three lint-related tools overlap: check_final is explicitly described as returning findings 'in the same form as lint_text', and lint_file vs lint_text differ only in input source, so an agent may struggle to pick the right one. get_playbook and get_reference_section both read from Whalory's knowledge base with different anchors, which descriptions partially clarify but not decisively.

Naming Consistency4/5

Five of six names follow a verb_noun pattern (lint_file, lint_text, get_playbook, get_reference_section, check_final), giving a predictable shape. profile_lookup breaks the convention with noun_verb ordering, a minor but visible deviation.

Tool Count5/5

Six tools is well-scoped for a copy-linting and brand-voice guidance server: two lint entry points, one final gate, one profile resolver, and two knowledge retrieval tools. No tool appears redundant enough to drop, and none is filler.

Completeness3/5

Core lint-and-check workflows are covered, but there is no way to create, edit, or save a brand profile (profile_lookup only reads and suggests starters) and no tool to enumerate available playbooks or reference files upfront. An agent must discover anchors by trial or by calling get_reference_section without an anchor, which is a notable gap.

Maintenance

ActivityNo data
ResponsivenessOutdated data