MCP server

writ

io.github.withwrit/writ

Checked 25 Oct 2026, 21:11 UTC · Still published on its registry; checked against OSV.dev; never run by us

Commit-time policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log.

Website Source

At a glance

Type

MCP server

Publisher

Not verified

Status

Runs on your computer

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code

Last checked

25 Oct 2026, 21:11 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. It then runs the package on your computer with your permissions. For other apps, copy the setup below.

Claude Code

claude mcp add writ --env WRIT_API_KEY=YOUR_VALUE -- uvx writ-mcp@0.1.3

Claude Desktop

{"mcpServers":{"writ":{"command":"uvx","args":["writ-mcp@0.1.3"],"env":{"WRIT_API_KEY":"YOUR_VALUE"}}}}

Codex (config.toml)

[mcp_servers.writ]
command = "uvx"
args = ["writ-mcp@0.1.3"]
env = { WRIT_API_KEY = "YOUR_VALUE" }

Gemini CLI

{"mcpServers":{"writ":{"command":"uvx","args":["writ-mcp@0.1.3"],"env":{"WRIT_API_KEY":"YOUR_VALUE"}}}}

Cursor

{"mcpServers":{"writ":{"command":"uvx","args":["writ-mcp@0.1.3"],"env":{"WRIT_API_KEY":"YOUR_VALUE"}}}}

VS Code

{"servers":{"writ":{"type":"stdio","command":"uvx","args":["writ-mcp@0.1.3"],"env":{"WRIT_API_KEY":"YOUR_VALUE"}}}}

Runs on your computer with your permissions: check the package and its source before installing. Replace YOUR_VALUE with your own WRIT_API_KEY.

Browse

• GitHub tools
• GitHub and code hosting

Related MCP servers

• DCL Trust Oracle — AI/LLM Output Audit (x402 MCP)
  AI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base.
• Sella
  Marketplace where AI agents buy datasets and API access, pay per call in USDC over x402.
• whoisbrowsing
  Add live visitor cursors to any website, no signup: create a site, get the snippet, check it's live.
• Policy Gate
  Deterministic allow/require_approval/deny verdicts for agent actions, before they happen.
• MemoryRouter
  Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
• Writ Cloud
  Read, crawl and act on websites, signed in as the user, and turn any site into an API.
• Trust Switchboard
  Read public privacy policies: dated source excerpts, follow-up questions and change comparisons.
• MUJ428 Trust Layer — Bind Approved Intent to Verified Effect
  Payment-rail-independent intent-to-effect integrity for consequential agent actions.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.withwrit/writ.svg)](https://aptlynx.net/servers/io.github.withwrit/writ)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents