Skip to main content
Glama
delimit-ai

delimit

Official
by delimit-ai
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
Python
Hybrid

Delimit Build Loop Daemon

delimit_build_loop_daemon

Start a long-running daemon to automatically execute governed build, social, or deploy loops at a set interval. Track each iteration via logged task IDs while respecting cost and error safeguards.

Instructions

Background auto-pull daemon for governed build/social/deploy loops (Pro).

When to use: to spawn a long-running daemon that ticks the governed loop every N seconds — the orchestrating Claude session tails ~/.delimit/logs/loop_daemon_.jsonl for triage. When NOT to use: for one-shot iteration (use delimit_build_loop) or to read loop metrics (delimit_loop_status).

Sibling contrast: delimit_build_loop is one iteration; this is the long-running daemon.

Side effects: action="start" spawns a daemon thread that calls run_governed_iteration / run_social_iteration on a cadence. action="stop" halts. Each tick logs returned task_id to a JSONL. Respects delimit_loop_config safeguards (cost_cap, error_threshold, max_iterations, status=paused/stopped) via loop_status before each tick. Gated by require_premium.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionNo"start", "stop", or "status" (default).status
loop_typeNo"build" (default), "social", or "deploy". Used on start.build
session_idNoSession to run. Required for all actions.
interval_secondsNoTick interval. Default 900 (15 min). Used on start.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed4 schema fields changedv4.7.9
    • changedInput schema / properties / action / description
      Previous value: -"'start', 'stop', or 'status' (default: status)"New value: +"\"start\", \"stop\", or \"status\" (default)."
    • changedInput schema / properties / interval_seconds / description
      Previous value: -"Tick interval in seconds (default 900 = 15 min). Only used on start."New value: +"Tick interval. Default 900 (15 min). Used on start."
    • changedInput schema / properties / loop_type / description
      Previous value: -"'build', 'social', or 'deploy' (default: build). Only used on start."New value: +"\"build\" (default), \"social\", or \"deploy\". Used on start."
    • changedInput schema / properties / session_id / description
      Previous value: -"Session to run (required for all actions)"New value: +"Session to run. Required for all actions."
  2. Addedv4.5.5

TDQS

A4.6/5.0
Behavior5/5

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

Even though annotations only say readOnly=false/destructive=false, the description discloses significant side effects: start spawns a daemon thread, stop halts, each tick writes task_id to JSONL, and safeguards are consulted before each tick. It also mentions the log path for triage. This is exactly the behavioral context annotations don't convey.

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

Conciseness4/5

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

Structured into headers, front-loaded with the core statement, and every section contributes either selection rules or behavioral cautions. Minor redundancy between 'When NOT to use' and 'Sibling contrast' does not hurt readability.

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

Completeness5/5

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

Given that an output schema exists and the annotations are minimal, the description supplies selection rules, side effects, logging behavior, safeguards, and premium gating. Nothing critical for invoking the tool correctly seems missing.

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

Parameters3/5

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

Schema coverage is 100%, so the baseline applies. The description mostly reiterates which params are used on start and does not substantially extend the schema's per-parameter descriptions; it provides action-level side effects more than new parameter semantics.

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

Purpose5/5

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

The lead sentence names the resource ('daemon') and function ('background auto-pull,' 'ticks governed loop'), and the sibling contrast explicitly separates it from delimit_build_loop and delimit_loop_status. An agent can tell what it does without inspecting the schema.

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

Usage Guidelines5/5

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

Includes an explicit 'When to use' block, a 'When NOT to use' block with named alternatives (delimit_build_loop for one-shot iteration, delimit_loop_status for metrics), and a sibling-contrast line. Also notes premium gating, which is a real selection constraint.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/delimit-ai/delimit-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server