Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
BACKLOGR_DBNoPath to the SQLite database used by the server and local CLI.~/backlogr/data/backlogr.db
BACKLOGR_TZNoTime zone for the dashboard.
BACKLOGR_URLNoCLI remote mode URL and base URL for MCP client configs; unset means local DB.
BACKLOGR_BOTSNoBot names that can never be approved_by.
BACKLOGR_PORTNoPort the server listens on.8796
BACKLOGR_HOSTSNoComma-separated list of server bind IPs.127.0.0.1
BACKLOGR_OWNERNoName used in messages and default person for act (server and CLI).owner
BACKLOGR_TOKENYesBearer token for the server (required for HTTP).
BACKLOGR_EXPORTNoPath for the nightly JSON export and CLI export.~/backlogr/exports/backlogr-export.json
BACKLOGR_HUMANSNoPeople whose act done attestation can satisfy completion gates.
BACKLOGR_APPROVERSNoIf set, the only names accepted as approved_by.
BACKLOGR_BACKUP_DIRNoDirectory for nightly SQLite backups (backlogr-YYYY-MM-DD.db); unset disables backups.
BACKLOGR_TOKEN_FILENoPath to the token file for CLI remote mode.~/backlogr/.token
BACKLOGR_BACKUP_KEEPNoNumber of nightly backups to keep.14
BACKLOGR_ALLOWED_HOSTSNoExtra MCP Host headers (proxy DNS names).
BACKLOGR_DASHBOARD_CATEGORIESNoCard grouping for the dashboard.
BACKLOGR_TRUST_TAILSCALE_HEADERSNoEnable Tailscale identity header authentication.off

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": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
task_createA

Create a task. key: a stable idempotency key (e.g. "forge:pr-12-review"); if a task already has it, that task is returned unchanged with existing=true, so retries never duplicate. The result has warnings when an open task has a very similar title: check it before carrying on. source: direct_to_bot | via_coordinator | bot_initiated. status: todo|in_progress|waiting_on_owner|blocked|done|declined. due: ISO 8601. done_means: one line saying what done looks like. ask: required with status waiting_on_owner, one line saying exactly what the owner must decide or do. approved_by/approval_source: the human approval (never a bot name); required before an approval_needed task can be in_progress or done. evidence/test_results: see task_update. actor: your bot name.

task_updateA

Update a task's status/due/owner/approval_needed and/or append a note to its log. due="" clears the due date. Moving to waiting_on_owner requires ask (one line: exactly what the owner must decide or do). Record a human approval with approved_by (the human, never a bot) and approval_source (e.g. "owner in chat"); an approval_needed task cannot move to in_progress or done without one. Moving to done requires evidence (link, commit sha, path or command output summary), and test_results {test name: "pass"|"fail"} when done_means mentions tests. actor: your bot name.

task_add_linkC

Attach a link (URL or plain text) to a task. kind e.g. pr, doc, order, message, page, file, other.

task_getC

Get one task with its full updates log and links.

task_listA

List tasks (open only unless status or include_closed given). Filters (AND): owner, status (one or comma list e.g. "todo,in_progress"), overdue, stale_hours (no update in N hours), due_before (ISO date), q (text in title/done_means/notes/links), source.

task_flagsB

Check-in view: overdue, stale, blocked, waiting_on_owner, open questions for owners, and tasks created in the last N hours.

task_actA

One-call action by a person (default BACKLOGR_OWNER), e.g. from dashboard buttons. action: later (note only; reason required) | done (status done; the person's word is the evidence) | na (status declined, reason in the note) | question (status unchanged; reason is the question, marked as open_question for the owner bot until the owner updates) | undo (reverts the last act if nothing changed since). Logged in the task history as "act by ".

task_waitingA

Owner queue: every waiting_on_owner task, oldest first, with its exact ask and age in hours.

task_staleA

in_progress tasks with no note or change in the last N hours, grouped by owner (oldest first).

task_importA

Bulk create tasks. items: a list, or an export object {tasks, rules, playbooks}. Each task takes task_create fields except actor (title, owner_bot, source, done_means, due, status, approval_needed, note, created_at) plus optional links [{ref, kind}]. Rules and playbooks are upserted as in rules_import.

rule_listB

List rules with optional playbook, testability and category filters.

rule_getC

Get one rule.

rule_addB

Add a rule; replace=true explicitly updates an existing ID. UNTESTED tests derive testable=false. actor defaults to BACKLOGR_OWNER.

rule_untestedA

List every rule whose testable flag is false, including rules with test text.

playbook_listB

List playbooks with linked rules.

playbook_getA

Get a playbook with linked rules embedded.

playbook_addC

Upsert a playbook and its rule links; unknown rule IDs are errors.

rule_removeA

Delete a rule and its playbook links.

playbook_removeA

Delete a playbook; its rules are kept, and rules whose primary playbook it was are detached.

rules_importC

Atomically import a rules/playbooks object; return created/updated/unchanged counts.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3/5.0

Scored across 20 tools

Disambiguation3/5

Core operations are distinguishable, but several specialized views overlap: task_list can reproduce much of task_stale and task_waiting, task_flags aggregates those same concerns, and rule_untested overlaps filtered rule_list. The two import tools also overlap because task_import can upsert rules and playbooks, though their descriptions help clarify the intended entry points.

Naming Consistency4/5

Names consistently use snake_case and mostly follow a predictable resource_action pattern. Minor deviations include plural rules_import, mixed create/add verbs, and view names such as task_flags and rule_untested that do not use action verbs.

Tool Count3/5

Twenty tools is somewhat heavy for this backlog and rules domain. Several tools are specialized convenience views or overlapping import paths rather than clearly essential capabilities, so the surface could be consolidated.

Completeness4/5

Task creation, querying, status transitions, evidence, approvals, links, and bulk import are covered, while rules and playbooks have list/get/add-or-update/remove workflows. Remaining gaps include limited editing of general task fields, no task or link deletion, and no export counterpart to the import tools, though closure states and upserts provide partial workarounds.

Maintenance

ActivityNo data
ResponsivenessOutdated data