MCP.Market

Agent Lease MCP server

by Buggy1111·io.github.Buggy1111/agent-lease-mcp·v0.2.0
No reviews yet

Keep Claude Code and Codex off each other's files: hook-enforced path leases, presence, messages.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars72 downloads/wk

Reviews

Write one

Nobody has reviewed Agent Lease yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agent Lease tools (15, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • accept

    Acknowledge that you are TAKING an addressed message/task — do it now, BEFORE the work.

  • ack

    Confirm the state of your own delivery; an active lease needs the right token.

  • cancelwrite action

    Cancel an unfinished delivery; its history is kept.

  • claim

    Lease the files or directories you are about to change.

  • history

    Who touched what and how it ended (lease, refusal, blocked edit).

  • inbox

    Messages newer than `since_id`. Keep the cursor between calls.

  • jobs

    Addressed items and their delivery state (only those you sent or received).

  • next_task

    Atomically take the oldest ready task addressed to this agent.

  • owner

    Who holds this path (directly or through a directory lease above it)?

  • release

    Return leases as soon as you are done. Without `paths` returns everything you hold.

  • report_limit

    Running out of quota/rate limit? Call THIS before you stop.

  • retrywrite action

    Put a failed/needs_review/dead_letter delivery back into the pending queue.

  • room

    Room state in one call: who is here, what is held, what is new.

  • say

    Message to the room — to the other agents and the human.

  • sendwrite action

    Addressed chat message or durable task; a `chat` does not start any work by itself.

Public scan report

scanner v0.1.10 · 2026-10-29 · same rubric, same numbers if you re-run it

no findings
  • Code scan24 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 5 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agent Lease compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 4,460 AI and agents servers
Tools
15
the typical AI and agents server has 6
Tools that change things
20%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
72
more than 55% of 1,538 AI and agents servers with a package

What its tools let an agent do: 12 read · 1 change · 1 delete · 1 send or post

Install Agent Lease in Claude Code, Cursor or VS Code

claude mcp add agent-lease-mcp -- uvx agent-lease-mcp
Add to Cursor

What the publisher says

From the Agent Lease repository's README, as published. We do not edit it. Read it on GitHub

agent-lease-mcp

<!-- mcp-name: io.github.Buggy1111/agent-lease-mcp -->

Keep two coding agents (Claude Code and Codex, or two sessions of either) from overwriting each other's work in the same repository.

agent-lease gives them leases on paths, presence and a shared message log — and the lease is enforced by a PreToolUse hook, not by good intentions. An agent that tries to edit a file another agent is working on is refused before the edit happens.

Česky / Czech version

Why it exists

9 September 2026. A coordination file, docs/AGENT-HANDOFF.md, existed and both agents knew about it. At 22:28 they still both touched deploy/make-work-package.sh: one was editing it while the other was running it. Bash reads a script as it goes, the text shifted under the running process, and instead of a 3.7 GB installer the build produced a useless 198 MB one.

The lesson the whole project rests on: coordination that can be ignored will be ignored. Not out of malice — an agent at work simply does not look at the notice board.

The same collision was later replayed on purpose: Codex ran the script, Claude Code tried to edit it mid-run, and the hook refused the edit. The file stayed intact.

How it differs

Advisory locks get broken; AgentRoom documents this itself. Claude Code and Codex both have PreToolUse hooks with the same semantics (exit 2 = block, reason on stderr), so a lease can be enforced deterministically at the tool-call level. One script serves both clients.

Rules it is built on

forever.

  • A lease, not a lock. 30-minute TTL. A crashed agent cannot block the repo

remember to call claim.

  • All or nothing. A claim on several paths succeeds completely or not at all.
  • A lease on a directory covers everything under it.
  • A free file is claimed automatically on the first edit, so nobody has to

combination that broke the build.

  • A running script is leased for the duration of the run — exactly the

first thing anyone does is switch the hook off. AGENTLEASEFAIL_CLOSED=1 flips this for unattended runs.

  • Fail-open by default. Broken coordination must not stop work; otherwise the

What runs on its own

Injections stay silent when there is nothing to say.

Waking a sleeping agent

Hooks only fire when the agent acts, so an idle session is woken from outside, without spending model tokens:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Agent Lease: common questions

Is Agent Lease MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Agent Lease safety report
How do I install Agent Lease?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agent Lease need an API key?
No secret keys are declared. It reads 2 settings from the environment.
Is Agent Lease maintained?
The last commit was 11 days ago (2026-10-24). The latest release is v0.2.0.
What can I use instead of Agent Lease?
Servers from other publishers that do the same job: SuperCompress MCP server, Basic Memory MCP server and Watch Skill MCP server.
How does Agent Lease compare with other AI and agents MCP servers?
safety score 92/100 (higher than 90% of 4,460 AI and agents servers); tools 15 (the typical AI and agents server has 6); tools that change things 20% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Agent Lease

Same job from other publishers: the closest match first, then the best rated.

  • SuperCompress
    Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.
    B
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • Watch Skill
    Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.
    B
  • OpenWorkProof
    Verifiable agent evidence; opt-in Codex guard and reference SOC alert review.
    A
  • Roast My Design System
    Audit your Design System and serve your Agent the rules that keep AI-written UI on-system.
    A

More from Buggy1111 →