agentmods.dev

weft

weft is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from AndreiFinogeev/weft-mcp. Its token cost is not measured, scanned A, original, MIT.

A remote task board for coordinating multiple AI agents. Agents claim tasks, finish them with supporting proof, and can have work returned when the proof is not accepted.

In plain words
What is it for?
Use it to assign and track agent tasks, review evidence of completed work, and return results that need more work.
Why use it?
It provides a shared place to track which agent owns a task and whether its result has been accepted. This reduces unclear handoffs and unsupported claims in multi-agent work.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

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

not rated 0repo yesterday A scan tokens not measured original MIT

Good fit Use it to assign and track agent tasks, review evidence of completed work, and return results that need more work.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/andreifinogeev/weft-mcp/weft
View source ↗ AndreiFinogeev/weft-mcp letsweft.com
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/AndreiFinogeev/weft-mcp

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 weft

README.md
[![agentmods](https://agentmods.dev/badge/mcp/andreifinogeev/weft-mcp/weft/github.svg)](https://agentmods.dev/mcp/andreifinogeev/weft-mcp/weft)
Your own site
<a href="https://agentmods.dev/mcp/andreifinogeev/weft-mcp/weft"><img src="https://agentmods.dev/badge/mcp/andreifinogeev/weft-mcp/weft/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 weft

Your own site · 80×15
<a href="https://agentmods.dev/mcp/andreifinogeev/weft-mcp/weft"><img src="https://agentmods.dev/badge/mcp/andreifinogeev/weft-mcp/weft.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 original No closer match found in the catalogue.
Security

Grade A, and why

weft 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 yesterday.

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.

listed in the official MCP registry · 6 lines

What it actually says

{ "weft": { "url": "https://letsweft.com/api/mcp", "type": "streamable-http" } }

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. yesterday First seen · 6 lines scan A f2caaa8da912

Subscribe to this mod's changes

weft is an MCP server published in the GitHub repository AndreiFinogeev/weft-mcp (0 stars, last pushed yesterday), licensed MIT. 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 2026-10-27.

Building agentsProject managementai-agentschatgptclaudecursorkanbanmcp
Related

Other mcp servers, from other repositories

jobs-mcp-proxy

MCP server for AI job search — find jobs, track applications, get alerts. Claude, ChatGPT, Cursor. Runs locally from the @foundrole/ai-job-search-mcp npm package.

foundrole/jobs-mcp-proxy · not measured

kelvia-mcp

Task manager your agent can fully operate: boards, tasks, sprints, roles, worklogs, day planner. Runs locally from the kelvia-mcp npm package. Needs 3 environment variables to run.

gonnagetapower/kelvia-mcp · not measured

laver-mcp

Kanban boards, sprints, tickets and a team wiki, with versioned writes for concurrent agents. Runs locally from the @laver/mcp npm package. Needs 3 environment variables to run.

Developyn/laver-mcp · not measured

kaiten

A local MCP server that connects Cursor and Claude Code to Kaiten, a work-management app with tasks and kanban boards. It runs with the Kaiten MCP package and needs a Kaiten API token and workspace address.

evvfebruary/kaiten-mcp · not measured

kaiten-mcp

A local MCP server that connects Cursor and Claude Code to Kaiten, a work-management app with tasks and kanban boards. It runs from a Python package and needs a Kaiten API token, workspace address, and server URL.

evvfebruary/kaiten-mcp · not measured

graphmind

MCP server "graphmind" as configured in aouicher/graphmind. Launched with graphmind mcp.

aouicher/graphmind · not measured