Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HEADLO_API_URLNoAPI base URLhttps://api.headlo.com
HEADLO_ANON_KEYNoAnon key for public tool calls
HEADLO_API_TOKENYesYour Headlo API token (hl_pat_...)

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
}
resources
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_page_modulesA

List all modules on a page with their records (public, anon key auth)

get_moduleB

Get a single module with its records (public, anon key auth)

get_contextA

Get all sites and workspaces for the active agency — call this first to orient yourself

list_collectionsA

List all collections for the active workspace

create_collectionC

Create a new collection

update_collectionB

Update a collection label or schema

list_recordsC

List records in a collection (includes drafts)

get_recordA

Get a single record by ID with all field values

create_recordC

Create a new record in a collection

update_recordA

Update a record — partial update, only provided fields are changed

delete_recordD

Delete a record

list_pagesB

List all pages for a site

create_pageC

Create a new page

update_pageC

Update a page title or layout

list_modules_editorB

List all modules on a page (editor auth)

create_moduleC

Add a module to a page slot

update_moduleB

Update a module — change its record, options, or template

delete_moduleB

Remove a module from a page

setup_agencyA

Create a new agency/workspace during onboarding

create_siteB

Create a new site under the active agency

save_brandingC

Save branding details for the active agency

get_onboarding_progressA

Get the current onboarding step and completion status

cap_capture_expertA

Run an existing CAP (Context Accumulation Protocol) as a live intake session. Pass cap_id and an empty message to load and start the first question. Answer each question in subsequent calls. On completion returns a synthesized answer built from the CAP knowledge pairs. Returns { response, session_state, complete, answer? } as JSON.

cap_edit_expertA

Conversationally edit an existing CAP — add questions (with AI-generated knowledge probes), remove questions, or edit multiple-choice options. Pass cap_id and empty message to load. Returns { response, session_state, complete, cap_id? } as JSON.

create_expert_protocolB

Create a CAP (Context Accumulation Protocol) for a question on the Headlo Ask network. Before writing any knowledge probes, always do a web search to gather current, specific facts. Each probe answer must contain 4–6 specific facts sourced from your research.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
collections

TDQS

C2.8/5.0

Scored across 25 tools

Disambiguation4/5

Most tools have a clear and distinct resource+action purpose (e.g., create_record vs update_record, list_pages vs create_page). The main confusion risk is between list_page_modules and list_modules_editor, which differ only by auth context, and possibly get_module vs list_page_modules, though the singular/plural distinction helps.

Naming Consistency3/5

The dominant pattern is verb_noun (get_context, create_site, update_record), but there are notable deviations: 'cap_capture_expert' and 'cap_edit_expert' use a prefix and less predictable structure, and 'list_modules_editor' is inconsistent with 'list_page_modules'. Overall still readable but not uniform.

Tool Count4/5

25 tools is at the high end but well-justified given the server covers multiple domains: onboarding, sites, pages, collections, records, modules, and expert protocols. Each tool serves a distinct purpose, though the count feels slightly heavy for a single server.

Completeness2/5

There are significant lifecycle gaps: no delete or update for sites, no delete for pages, no delete for collections, and no get_collection or update_site. Records and modules have full CRUD, but the broader content model lacks essential operations that agents would likely need.

Maintenance

ActivityInactive
ResponsivenessNo issues