devcontrol
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
English | 简体中文
devcontrol
A discipline kernel for coding agents.
It keeps Claude Code / Codex / Cursor / OpenCode on rails: claim a task before you touch code, only touch files that task owns, and prove you ran the check. The kernel verifies the proof — it never runs your tests.
You do three things: file it, approve it, unblock it. The agent walks the rest.
The problem
Jira tracks features. Nobody tracks what the agent actually did.
It says "all tests pass". Did it actually run them?
It fixes a bug by editing a file three layers away from the bug.
It adds a second helper that already exists.
Two agents working in parallel quietly overwrite each other.
Two weeks later, nobody can say which task a line belongs to.
Related MCP server: agent-work-mcp
What changes
Before | After |
"Tests pass" — take its word for it | A recorded run: command, exit code, output, and the fingerprint of the code it ran against. Edit anything afterwards and the evidence goes stale |
It edits whatever it thinks needs editing | Out-of-scope files are refused. One hard gate, nothing else |
Every task re-explores the project | Your architecture/ conventions are written once and attached to every task automatically |
Nobody knows who wrote a line, or why | Every commit carries its task id. "Why does this line exist" has an answer |
You babysit the whole loop | You answer three things: approve, decide, unblock |
"Is this tool actually helping?" |
|
Three steps
npm install -g mcp-devcontrol # Node >= 22.5, git >= 2.30
cd your-project
devcontrol initinit sets up state, freezes a draft contract per directory, registers the MCP server in Claude Code / Cursor / OpenCode / Codex, and drops a rules block into AGENTS.md.
Then, from your agent's session or a terminal:
devcontrol intake "Make the homepage headline readable" --accept "npm test :: exit==0" # you
devcontrol approve FR-001 --path P-001 # you
devcontrol next # the kernel decides what's nextNo MCP? devcontrol init --no-mcp — same gates, same evidence, everything in the terminal.
One task, end to end
bootstrap → "claim T-003, scope src/, run npm test"
task.claim → returns the task's scope, the test command, and your project context
...write code...
devcontrol run -- npm test → recorded as evidence: command, exit code, fingerprint
devcontrol commit -m "..." → commits only in-scope files, stamps the task id
devcontrol close → verifies the evidence and closes. It does not run testsClose fails if the evidence is missing, was produced against different code, or the command isn't in the contract. Fixing it is a normal step, not a rework round.
How it stays small
Most tools in this space grow until they manage your environment. This one refuses:
It never runs your tests. The moment it does, it owns installs, timeouts, process reaping, clean checkouts — and starts fighting how your project really works. The agent runs; the kernel checks that the evidence matches the code.
Scope is the only hard gate. Whether a line is good is a judgement call. Whether a line belongs to this task is a fact. The kernel enforces facts.
Standards are handed out, not policed. Line budget, no
TODOmarkers, don't touch existing tests — these get counted and reported at close. You decide what to do about it.It never writes your documentation prose. It knows which documents a project needs and asks for them; your agent fills in the content, because the kernel doesn't know your business.
The honest limit: evidence is self-reported. It catches "ran, then edited the code" and "closed without running anything". It cannot catch deliberate forgery. The tool governs process, not character.
Agent surface
One MCP tool, devcontrol, with an action field:
action | Purpose |
| Start here. Returns |
| The kernel says hold; returns current state |
| Your turn to write code; returns the four-step order |
| Split work into a task (scope, acceptance, dependencies) |
| Take a task (45-minute lease, one at a time) |
| Extend the lease on a long task |
| Hand up the result you got in your own shell |
| Close: verify the evidence |
| Report a bug with repro steps |
| Ask when ambiguous instead of guessing |
| Record a reusable lesson |
| Search this project's memory |
| Start a release |
| Attach tasks to a release |
| Ship it, tag it, once every task is done |
CLI equivalents, for clients without MCP:
devcontrol status # = bootstrap
devcontrol run -- npm test # run and record evidence
devcontrol commit -m "feat: ..." # commit in-scope files
devcontrol close # verify and close
devcontrol task abandon T-003 --reason "not needed any more"Your console, as a side effect
Connect an MCP client and a local console appears at http://127.0.0.1:7373 — nine views: inbox, requirements, bugs, tasks, releases, memory, docs, evidence, settings. It starts itself, restarts itself if it dies, and never kills another project's instance. You never launch or refresh it.
What it is not
Not a board. No kanban, no sprints, no assignees.
Not a linter. It won't tell you your code is ugly.
Not a test runner.
Not multi-user. One owner, no accounts.
Not a rules engine. Five standards, one enforced.
Docs
docs/03-discipline-core.md— every rule, and whydocs/04-v6-architecture.md— design and trade-offsdevcontrol --help— every commanddevcontrol doctor— reconciles the repo against its database; speaks only when something's wrong
MIT.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Source control for coding agents: declare an intent, settle overlaps before code, verify each push.
Shared project docs, task planning and GitHub evidence for people and their AI agents.
Git collaboration for AI agents and people: tasks, hand-offs, reviews, teams, shared memory.
Coordination hub for AI coding agents: message teammates, ask humans, audit every event.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceCoordinates parallel AI coding agents by providing task ownership, scoped file locks, handoffs, and verification workflows.MIT
- AlicenseAqualityCmaintenanceEnables coding agents to run persistent, budgeted work sessions with dependency graphs, human decision queues, required validation, and clean handoffs for autonomous or human-in-the-loop execution.16MIT
- AlicenseNot gradedqualityBmaintenanceEnables many coding agents to change one codebase at once by granting function-level clearances before edits, holding conflicting work, landing verified commits one at a time, and recording each change's intent, plan and test evidence as retrievable git notes.2 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI coding providers to run structured multi-agent workflows, manage specs and tracked tasks, record handoffs, and enforce health-gated completion evidence.29 npmMIT