Looping Agent MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Looping Agent MCP build the project and ensure all tests pass"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Looping Agent MCP
An MCP server that turns a manager's plain-English goal into a verified, looped, watchable build run — driven entirely by the IDE's own agent (Antigravity / Claude Code). No SDK, no claude -p.
The split (do not violate)
IDE agent = the muscle + the planner. Owns the how. Does the file edits, runs commands, thinks in many directions.
This MCP server = brain + checker + governor + dashboard. Owns the what (goal, criteria, verdict, caps) and the how it's framed. Never dictates steps.
Manager = owns "is this what I meant" (goal + criteria confirmation).
Related MCP server: No-Shell Agent Architect MCP
Locked core rules (load-bearing — never soften)
DONEcomes only fromcheck_done. The agent may never self-declare done.The server returns the goal + failing criteria, never a prescribed step. (Hold the what, not the how.)
The standing order is re-injected on every tool response (survives context compaction).
Pacing + caps live in
get_next_action— it can returnSTOP/ESCALATEand the agent has nothing left to call.Three escalation triggers → one channel: too risky, can't define done, stuck. Each carries a reason + handoff.
Live counters show real numbers (turns, actions, criteria, elapsed). Token/budget is an estimate, labelled as such.
Branch-per-task & the merge gate
On a git project, each task is isolated and merged only on the manager's say-so:
confirmcuts a fresh task branch (loop/<slug>-<hash>) off the current branch (the base); the agent does all its work there.When every criterion goes green, the run doesn't silently finish — it enters
ready_to_mergeand the dashboard shows "✅ all criteria pass — mergebranch→base?"The manager clicks Merge (or Not yet). On approve, the server commits any pending work and runs
git merge --no-ff; a conflict aborts cleanly and leaves the work on the task branch. On reject, the work stays on the branch for a human.
Off git (not a repo), it's a plain DONE with no branch or merge gate.
Run
New here?
SETUP.mdhas the full copy-paste setup for a fresh machine.
uv sync # creates the venv + installs deps
cp .env.example .env # optional: tune caps / pacing / LLM drafting
uv run pytest # 88 tests; all greenThe server is meant to be launched by your IDE, not by hand. Register it from
inside the project you want it to work on — the verifier runs its command
oracles in the server's working directory, so it must be your project, not this
repo. Use --project (selects this package's venv) rather than --directory
(which would also change the cwd to here):
# run this from your target project's root — registers + pins this package:
loopai register
# (equivalent to: claude mcp add looping-agent -- uv run --project /path/to/looping_MCP loopai serve)The IDE starts it, speaks JSON-RPC over stdio, and stops it by closing stdin. The watch dashboard comes up at http://127.0.0.1:3000.
The loopai command
command | what it does |
| MCP server (backend) + dashboard (frontend) — what the IDE launches |
| frontend only, no stdio — open the control panel by hand, Ctrl-C to stop |
| register with Claude Code for the current project |
loopailives in the project's.venv, not on your global PATH. Afteruv sync, invoke it one of these ways:
uv run loopai …— from the looping_MCP folder, or
source .venv/bin/activatethenloopai …, orby absolute path from anywhere:
/abs/looping_MCP/.venv/bin/loopai …(add that dir to PATH, orln -sit into~/.local/bin, for a bareloopai).
loopai registerwrites an absolute-path launch command, so the IDE can start the server with no PATH/uv dependency — run it from your target project dir (that's the project the registration is scoped to).
Running it by hand (to watch the dashboard)
Use loopai dashboard — it serves the control panel with no stdio, so the
terminal stays a normal terminal (just press Ctrl-C to stop). Avoid loopai serve
by hand: that's a stdio server, so the terminal becomes its JSON-RPC input and
anything you type is rejected as a protocol message.
Note:
stdoutis reserved for the JSON-RPC channel — all diagnostics go tostderr.
Register in the IDE's MCP config (see specs/tool_contract.md).
Build it
You are not meant to hand-write this. Open CLAUDE_CODE_BUILD.md and feed Claude Code one phase at a time, running the checks after each. The scaffold here is the anchor; Claude Code fleshes the TODOs.
Available Tools
6 toolscheck_doneA
Explicit verifier call. Same authority as report_result's check — DONE only comes from here. When it goes green on a git project, a merge gate is raised.
Inputs: no named parameters.
confirmA
Manager confirms the criteria, optionally REPLACING them with the project's real checks, then returns the kickoff prompt.
If edited_criteria is given it becomes the authoritative final list. Each item
is {id?, text, oracle_type, oracle} where oracle_type is "command" (a shell
command that exits 0 on success), "browser" (a flow the agent proves), or
"manual". An item whose id matches a proposed criterion patches it (and
re-arms it for checking); any other item is added new. This is how you point a
criterion at YOUR stack — e.g. {"text":"build passes","oracle_type":"command",
"oracle":"cargo build"}. Returns {error, details} if a criterion is malformed.
Inputs: edited_criteria.
get_next_actionA
Agent calls this each turn. Enforces pacing + caps. Returns the goal and what still fails (NOT a prescribed step), or STOP / ESCALATE / DONE.
Inputs: no named parameters.
proposeA
Manager types a goal. Returns risk lane + proposed criteria for confirmation. May escalate immediately (too risky / can't define done).
Inputs: goal (required), repo_context.
report_resultB
Agent reports what it did. Runs the verifier. Returns FAIL+failing (with the
re-injected standing order) or DONE. proof maps criterion_id -> artifact path
for browser/manual criteria.
Inputs: summary (required), proof.
request_gateA
Agent asks permission for an irreversible action (deploy/migrate/delete/send). Sets a pending gate the manager approves on the dashboard.
Inputs: action (required), reason (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: check_done for verification, confirm for manager to set criteria, get_next_action for step retrieval, propose for goal definition, report_result for result reporting, and request_gate for permission. No overlap.
Most tool names follow a verb_noun pattern (check_done, get_next_action, report_result, request_gate), though confirm and propose are single verbs. The naming style is consistent with lowercase and underscores.
With 6 tools, the server covers the core interactions of a looping agent workflow (propose, confirm, get action, report, check done, request gate) without being excessive or insufficient.
The tool set covers the essential lifecycle: goal proposal and criteria confirmation, action retrieval, result reporting with verification, done checking, and gate requests. Minor gap: no explicit tool for listing all criteria, but get_next_action provides failing criteria and check_done tests all.
Maintenance
Related MCP Connectors
Test the idea before you build it. Rapidly works inside your AI agent.
Turn an idea or meeting transcript into a working single-file AI agent, check it, use it right away.
Turn an idea or meeting transcript into a working single-file AI agent, check it, use it right away.
Turn an idea or meeting transcript into a working single-file AI agent, check it, use it right away.
Related MCP Servers
- AlicenseAqualityFmaintenanceAn autonomous, extensible LLM build orchestrator. Give it a repo and a goal; it decomposes the goal into tasks, edits code, and gates every change on build/tests/lint, reverting regressions. Polygot, cost-aware model selection, pluggable via entry points. Ships as an MCP server so any client can drive it in plain English.1560 PyPI5AGPL 3.0
- AlicenseNot gradedqualityDmaintenanceTakes a plain-language automation goal and returns a recommended tool stack, command, validation checks, recovery guidance, and a machine-readable package contract for agents and builders.MIT
- FlicenseBqualityDmaintenanceEnables AI coding assistants to run a machine-verified DESIGN→PLAN→EXECUTE→VERIFY→COMPLETE workflow with human approval gates, state integrity checks, and DAG task scheduling.7-
- AlicenseBqualityBmaintenanceEnables goal-driven mission orchestration for Goose, turning a user goal into a structured plan with an approval gate, isolated workers in git worktrees, dual validation, auto-correction, and crash recovery to produce validated code.19MIT