Remit

Name: Remit
Author: mrpacstar2-oss

by mrpacstar2-ossversion 0.1.0i★ –iRuns in the cloud

Registry nameio.github.mrpacstar2-oss/remit

Install

Overview

Description from the maker (original English)

Checked language for AI-written agent workflows: limits, cost and data flows known before running.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiNot measured yet★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs in the cloud
Transport: Streamable HTTP
Category: Other

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on the maker’s server: what you ask it goes through their server.
The registry lists no key to fill in.

You need

Runs in the cloudNothing to install; it connects over the internet

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Works in Claude on the web, desktop and mobile:

Open Settings → Connectors
Press Add custom connector
Paste the address below and press Add
If it asks you to sign in, sign in with the maker

https://77-68-52-20.sslip.io/mcp

Run this in your terminal

claude mcp add --transport http remit https://77-68-52-20.sslip.io/mcp

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "remit": {
      "url": "https://77-68-52-20.sslip.io/mcp"
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "remit": {
      "type": "http",
      "url": "https://77-68-52-20.sslip.io/mcp"
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

ChatGPT connects only to servers on the internet:

Open ChatGPT on the web → Settings → Connectors (Apps)
Press Create or Add (some plans need Developer mode under Advanced first)
Paste the address below, give it a name and save
If it asks you to sign in, sign in with the maker

https://77-68-52-20.sslip.io/mcp

Menu names can differ slightly by plan and over time.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

We have not read this server’s tool list yet; we check endpoints in rotation.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account mrpacstar2-oss, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
… Not checked yet
Endpoint responds
Not checked yet; we check endpoints in rotation
… Not checked yet
Sign-in with OAuth
Not checked yet; we check endpoints in rotation
… Not checked yet
No hidden instructions in tool descriptions
Not checked yet; we read the tool list when we check the endpoint

Compared with others in Otheri

More stars than 0% of the other 32725 servers in this category
Published to the registry more recently than 53% of the other 32725 servers in this category
Basic checks equal to or better than 100% of the other 32725 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Remit safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.1.0) reached the registry 35 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.

What can I use instead?

In the same category: Spec Driven Development, Remote Desktop Commander, Signoff

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Spec Driven Development

by formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

Runs on your computer★ 440MITUpdated 14 months ago

Install

Remote Desktop Commander

by desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

Runs in the cloud★ 211Updated 2 days ago

Install

Signoff

by ayuanxx-max

Five gates that make an agent's 'done' provable: run them, read the verdict, audit the record.

Runs on your computerUpdated today

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

Remit

Know what an AI-written program can do before it runs.

Remit is a small, statically checked language for agent workflows, meaning programs that call tools and models. It is meant to be written and edited by AI agents. Before a program runs, the checker reports:

which capabilities it can use, from a host-controlled list;
at most how many times it can call each one, and its worst-case spend;
whether untrusted data (documents, web pages, model output) or private data can reach sensitive parameters, such as payment details or email recipients. Each such flow is rejected outright, or sent to a human for approval bound to the exact arguments.

A runtime broker then enforces the same rules and records a replayable trace.

Try it in your browser: https://77-68-52-20.sslip.io/try.html (pick an edit an AI might make and see it allowed or blocked, with the reason). For AI agents: connect the MCP server at https://77-68-52-20.sslip.io/mcp.

payments.schedule(vendor_id: vendor.id, iban: inv.iban_on_invoice, amount: inv.amount, ...)

error[E0301]: data tagged untrusted flows into 'payments.schedule' parameter 'iban', which denies it note: 'inv.iban_on_invoice' is untrusted because it derives from inbox.read (line 20)

For AI agents

MCP server, local: remit mcp (stdio).
MCP server, hosted: remit mcp --http, with optional API keys and usage metering.
Tools:

Tool	What it does
`remit_guide`	the guide or the full spec
`remit_check`	errors plus the authority manifest
`remit_format`	canonical formatting
`remit_authority_diff`	did an edit widen authority?
`remit_examples`	complete example programs
`remit_run_fixtures`	offline test runs

Quick guide: docs/AI_GUIDE.md.
Full specification: docs/LANGUAGE_SPEC.md.
`llms.txt`: site/llms.txt, plus site/llms-full.txt.

Claude Code configuration example:

{ "mcpServers": { "remit": { "command": "remit", "args": ["mcp"] } } }

Quick start

python3 -m venv .venv && .venv/bin/pip install -e ".[mcp]" pytest pydantic

.venv/bin/python -m pytest -q tests baselines cd examples/invoices ../../.venv/bin/remit check invoices.rmt # manifest and policy check ../../.venv/bin/remit run invoices.rmt # offline fixtures; stops for approval ../../.venv/bin/remit approve && ../../.venv/bin/remit resume # approve that exact call, continue

Evidence

docs/BENCHMARKS.md compares Remit with a Python baseline that uses the same runtime, so runtime features are not credited to the language. Samples are small, use one model family and include no human trials.

Safety:
Of 17 unsafe program mutations, 14 were rejected before running. Python on the same runtime executed 8 of them.
Asked to make unsafe changes, Haiku 4.5 agents shipped executable unsafe code 0/6 times in Remit and 6/6 in Python. Sonnet 5.5 refused in both languages.
Review: every agent-written feature change (20 of 20) was mechanically shown not to widen authority.
Ease:
Agents modified programs (15/15 against 14/15) and built a new workflow from a spec (5/5 against 5/5) equally well in both languages, so there is no penalty for a language the models had never seen.
Agents that only had the MCP server built correct programs 5/5.
Recovery: crash-and-resume behaviour is identical in both, as expected, since it is a runtime property.

Status

Remit is an early, open-source release. The language, checker, runtime, MCP server, demo and five example apps all work and are tested. It is not yet a finished product: there is no built-in sandboxing (run it inside your own isolated environment) and no module system, concurrency or editor language server yet. See LANGUAGE_SPEC §13 for what is planned.

Running your own copy of the website and MCP server is covered in deploy/README.md.

Licence: Apache-2.0.

Remit

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Otheri

Common questions

Alternatives

Spec Driven Development

Remote Desktop Commander

Signoff

README from the maker

Remit

For AI agents

Quick start

Evidence

Status