paraphe
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@parapheAsk the human for approval to deploy to production before proceeding."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Paraphe
The owner-decision inbox for agents. An agent raises one decision, you answer it on your phone or on the machine running it, and that same agent picks the answer up and carries on.
It is for people who run agents that should ask before they act. Paraphe is the small, self-hosted thing that holds the question until the human answers it — not a task tracker, not a chat client, and not a workflow engine.

Install and run
Python 3.11 or newer, and nothing else.
pip install parapheIn a checkout, the same install inside a virtual environment, with a configuration file to start from:
python3 -m venv .venv
.venv/bin/pip install .
cp config.example.toml paraphe.toml # then fill in two values you make up
.venv/bin/paraphe --config paraphe.tomlThose two values are yours:
Value | Who holds it |
| the agent. It creates cards and reads answers. |
| you. It answers them, and it is never given to an agent. |
With pip install paraphe and no checkout, create paraphe.toml with those
two lines; Paraphe reads it from the directory it runs in.
Paraphe ready: mcp http://127.0.0.1:8787/mcp answer-path onAdd a Telegram bot token and your Telegram user id to paraphe.toml and
decisions arrive as a message with buttons instead of on the console. Without
them the card is printed where you are looking, which is what the run above
does.
Or run the container, with the data location mounted:
mkdir -p paraphe-data && chmod 0777 paraphe-data
docker build -t paraphe .
docker run --rm -v "$PWD/paraphe-data:/data" \
-e PARAPHE_MCP_CREATE_BEARER=... -e PARAPHE_OWNER_ANSWER_TOKEN=... parapheIt binds loopback inside the container, because the answer path refuses a
non-loopback bind. To reach it from outside, configure the phone destination
(a bot token and your Telegram id) and set PARAPHE_MCP_HOST=0.0.0.0; the
answer path is then off, and taps arrive on the phone.
Related MCP server: call-a-human-mcp
The loop
ask → you see the card → you answer → the asking agent resumesThe answer returns through the ask itself: the call may wait (wait_seconds),
paraphe wait can hold the card's lifetime, and any run that missed both
drains the answer from the store at its next boundary. Nothing has to be said
in chat.
On the phone the card is ordered rich text, not a wall of prose: it names who is asking and from where (agent, runtime, repository, worktree, ticket), bolds its title, numbers the choices with their one-line notes and marks what is recommended, and lists the limits, links and expiry. A long-press reply answers it in your own words — or asks a question — and that text returns to the exact session that asked.
docs/demo/console-loop.md is a recorded run of
exactly that, on a clean checkout, with no third-party credential and no
external service: the agent asks, the card is printed, the agent's own
credential is refused when it tries to answer, the owner answers, and the
agent picks the answer up.
The line this product draws
The credential an agent holds cannot answer a decision. It creates and it reads. Answering needs the owner's credential, on a path the agent's cannot reach. An inbox an agent can approve on its behalf is not an owner-decision inbox, so this is not configurable.
Documentation
Document | What it covers |
the MCP tool surface and the card lifecycle | |
adding a destination, in two methods | |
the async return protocol, per runtime | |
what the words mean (card, tap, return path, owner) | |
the decisions behind the shape | |
the v1 specification | |
what is next, and what is not planned | |
the generated wiki index | |
what Paraphe is, and every route to a running inbox | |
how the inbox runs, page by page |
Dependencies
The runtime imports nothing outside the Python standard library, so using Paraphe pulls no dependency tree. Installing it fetches the build backend once, at install time, and nothing after that.
Licence
AGPL-3.0-or-later (LICENSE). Modify it and serve it to other
people over a network and you must offer them your modified source; nothing
here obliges a company to publish the application it builds on top.
Where your data lives
Cards are a SQLite file in your per-user data directory
($XDG_DATA_HOME/paraphe, else ~/.local/share/paraphe) unless you set
store_path. The directory is created 0700 and the file 0600, and Paraphe
never reads or writes outside that location.
Upgrading from a release that used /var/lib/paraphe: set store_path to
/var/lib/paraphe/inbox.sqlite explicitly. Paraphe refuses to start with the
default when a store exists at that location, rather than quietly beginning a
second, empty inbox.
This server cannot be deployed
Maintenance
Related MCP Connectors
Human-input bridge for AI agents with voice-first answer links, MCP tools, and HTTP APIs.
Human-in-the-loop for AI agents. Submit choices, get a human decision.
Human approvals, notifications, inbound webhooks, wake-ups for headless agents. Free trial: /try
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to pause execution at critical decision points and request human review before proceeding. Provides tools for creating interrupts, polling for decisions, and managing approvals through a simple REST API interface.11 npmMIT
- AlicenseAqualityAmaintenanceAn MCP server that enables AI agents to pause and request human approval or information via Slack, Telegram, or macOS dialogs before proceeding with actions.215Apache 2.0
- AlicenseAqualityCmaintenanceA minimal MCP server that lets AI agents pause for a specified duration before resuming their workflow. Useful for polling patterns like waiting for PR approval or file creation.15 npmMIT
- FlicenseNot gradedqualityBmaintenanceAn MCP server that lets an AI coding agent pause on human-only tasks, request structured input via a form, and resume with the answer, all locally without cloud dependencies.-