agentmods.dev

stale-write-guard-fs

stale-write-guard-fs is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from Cohexa-ai/agent-coherence. Its token cost is not measured, scanned A, original, no licence file.

A local coordinator for keeping multiple coding agents from overwriting newer state. It uses MESI-style coordination and optimistic concurrency, so an outdated write is rejected or reported as a conflict.

In plain words
What is it for?
Use it to coordinate concurrent agent updates and detect conflicting or outdated writes in the agent-coherence Python package.
Why use it?
It prevents an agent from silently applying changes based on stale information when several agents work on shared state.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 11repo +1 today A scan tokens not measured custom licence

Good fit Use it to coordinate concurrent agent updates and detect conflicting or outdated writes in the agent-coherence Python package.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/cohexa-ai/agent-coherence/stale-write-guard-fs
View source ↗ Cohexa-ai/agent-coherence agent-coherence.dev
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/Cohexa-ai/agent-coherence

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for stale-write-guard-fs

README.md
[![agentmods](https://agentmods.dev/badge/mcp/cohexa-ai/agent-coherence/stale-write-guard-fs/github.svg)](https://agentmods.dev/mcp/cohexa-ai/agent-coherence/stale-write-guard-fs)
Your own site
<a href="https://agentmods.dev/mcp/cohexa-ai/agent-coherence/stale-write-guard-fs"><img src="https://agentmods.dev/badge/mcp/cohexa-ai/agent-coherence/stale-write-guard-fs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for stale-write-guard-fs

Your own site · 80×15
<a href="https://agentmods.dev/mcp/cohexa-ai/agent-coherence/stale-write-guard-fs"><img src="https://agentmods.dev/badge/mcp/cohexa-ai/agent-coherence/stale-write-guard-fs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Security

Grade A, and why

stale-write-guard-fs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 9 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 9 lines scan A 4ee5acc560dd

Subscribe to this mod's changes

stale-write-guard-fs is an MCP server published in the GitHub repository Cohexa-ai/agent-coherence (11 stars, last pushed today), with no licence file. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agentsagent-memoryai-agentautogencache-coherencestate-synchronizationtoken-efficiency
Related

Other mcp servers, from other repositories

synap

Persistent memory for AI agents — log and recall conversation context over MCP. Remote server at synap-mcp.maximem.ai.

maximem-ai/maximem_synap_sdk · not measured

pare-search

Pare Search ג€” Structured code search operations (ripgrep + fd) as typed JSON. Runs locally from the @paretools/search npm package.

Dave-London/Pare · not measured

pare-test

Pare Test ג€” Auto-detects test framework (pytest, jest, vitest, mocha), returns typed JSON. Runs locally from the @paretools/test npm package.

Dave-London/Pare · not measured

palinode

MCP server "palinode" as configured in phasespace-labs/palinode. Launched with palinode-mcp.

phasespace-labs/palinode · not measured

memex

Temporal engineering context for agents via MCP. Runs locally from the stifler-memex-mcp npm package. Needs 4 environment variables to run.

STiFLeR7/memex · not measured

hive-mind

MCP server "hive-mind" as configured in toml0006/hive-mind. Runs locally from the hive-mind Python package.

toml0006/hive-mind · not measured