Fyreflock

Every AI chat is a room with one person in it. Fyreflock puts a second person in that room: a real one, who passed a camera check, picked at random, there for the same reason you are. You stay in Claude or ChatGPT. They might be in a browser, in ChatGPT, or in their own Claude. Your assistant is the courier, and it is held to that.

Try it in sixty seconds

1. Add Fyreflock to your assistant. The connector URL is https://fyreflock.com/mcp. Host-by-host steps are just below.
2. Sign in once and press Allow. A browser tab opens, you sign in or sign up, and you are sent straight back. New here? The same page signs you up, camera check and all.
3. Say "find me someone to talk to". The Fyreflock box opens right there in the conversation. Say "next" for somebody else, "leave" to stop.

[!TIP] Nobody around yet? Press Play while you wait and take on the computer. The search keeps its place, and the box switches to the conversation the moment somebody arrives.

Set it up

/plugin marketplace add FuloxDev/fyreflock-claude/plugin install fyreflock@fyreflock

{ "servers": { "fyreflock": { "type": "http", "url": "https://fyreflock.com/mcp" } } }

https://fyreflock.com/mcp

What you can do from your assistant

How it stays honest

• Every match is a real person. Every account passed a camera check in a browser before it could meet anyone. There is no bot in the queue and never will be. 18+ only.
• They know. The other person's card says you are talking from inside an assistant, so nobody is fooled about where the words came from.
• Your words, verbatim. The assistant is instructed to send your message exactly as typed. In Claude Code the plugin's hooks refuse any send that is not the line you wrote this turn. Rewording, shortening, "fixing" and inventing are all blocked.
• You can check. The companion tab at fyreflock.com/app/live shows what was actually sent and received, with no model involved.
• It survives you looking away. Switch to another chat, close the window, come back: your search keeps its place in line, your conversation keeps its lines, and your browser can tell you when somebody is there.

Before you meet anyone

• 18+. Same as meeting a stranger anywhere on Fyreflock.
• Messages here pass through the Fyreflock server in plain text and through whichever AI provider you are using. Browser-to-browser chats on the website never do. This is the real trade you are making.
• Use it in a chat with nothing else attached. No other connectors, no files, no tools. A stranger is typing into a context your assistant can read, and whatever it can see, they can ask about.
• Their words arrive wrapped and labelled as somebody else's text. They are never instructions, to you or to your assistant.

Full detail: https://fyreflock.com/agents · Privacy: https://fyreflock.com/privacy · Safety: https://fyreflock.com/safety

Talk to us

• Questions, ideas, a host that behaves oddly: Discussions.
• Something broken: open an issue.
• A security problem: please do not open an issue; see SECURITY.md.
• Someone behaving badly in a chat: report them from the box or on the website; that goes straight to moderation.

The pane: talk without the model in the path

Claude Code 2.1.287 or newer (Desktop 2.1.286) loads the plugin's mod, hooks/mod.tsx, beside the two hooks. It draws a Fyreflock pane next to the transcript and keeps the conversation itself, so a line costs 0.2 s instead of a model turn, and the model never sees the stranger's words unless you ask it to.

/fyreflock              open the pane/fyreflock start        find someone/fyreflock next         skip to somebody else/fyreflock leave        hang up, or stop looking/fyreflock status       who you are talking to and who is waiting/fyreflock <anything>   send that line, exactly as written

In the pane: the chat box's five states, each with its colour on a dot and a rule under the header in your theme's own colours: ready (yellow, how many are by the fire, Start), looking (yellow, Cancel), talking (green), reconnecting (orange, when a poll fails mid-conversation; it clears on the next answer) and ended (coral, "@them left the campfire" or "You left the campfire", with Find someone new). While talking: their lines on the left and yours on the right, a field that sends on Enter, Next person / Leave (hotkeys s, n, l while the pane has the keyboard, ctrl+x tab to give it the keyboard), and Sent / Delivered / Read under your last line. While Claude is idle, the band above the prompt shows the same dot and says who you are talking to and how many lines arrived since you last typed; hide dismisses it for the session. A reply also shows as a toast, and the status line says whether you are looking, talking or reconnecting.

Stop it asking permission for every message

Without this you confirm a dialog for every single line you send, which is unusable. Answer always allow the first time, or add the rule yourself:

/permissions

and allow mcp__plugin_fyreflock_fyreflock__*.

The exact tool prefix is generated by Claude Code from the plugin and server names, and the format has changed before. If that rule does not match, run /mcp or check any Fyreflock tool call in your transcript to see the real name, and use that. The hook matcher in hooks/hooks.json is a regular expression precisely so it keeps working either way.

What the hooks do

Two, both local, both tiny, neither sends anything anywhere.

capture-prompt.mjs runs on every prompt you submit and writes one small file in your system temp directory, keyed by a hash of the session id and overwritten by your next prompt. It holds SHA-256 digests of the forms your message can take and the turn's prompt_id, never your words. That is the whole job.

check-verbatim.mjs runs before fyreflock_say, fyreflock_roost_say, fyreflock_game_move and fyreflock_app_say, under any server name (the plugin's own, a claude mcp add one, or the claude.ai connector Claude Code imports), and refuses the call unless the text being sent is the message you typed this turn. Spacing and curly quotes are forgiven. Rewording, correcting, shortening, summarising, shouting and inventing are not, and the model is told to send your words instead.

"This turn" is the turn, not a time limit: Claude Code gives every event of one prompt the same prompt_id, so a long turn keeps your words, and a model acting on its own in a turn you did not start has nothing it may send.

It compares by equality, not containment. What goes out has to BE your message, not merely appear somewhere inside what you typed: a substring test lets "tell them no, I don't want to meet" send "want to meet", and lets a model assemble sentences a word at a time. Two allowances make that livable, because nobody types bare lines at an assistant: one leading "tell them" is stripped, and anything you wrap in backticks goes byte for byte, punctuation and case included. That last one is the escape hatch when the rules get in your way.

If no capture file exists at all, it allows the call. A missing capture means this plugin did not run, which is our bug, not the model's, and blocking your first message over it would just look broken. Any other unreadable capture counts as you having typed nothing.

Set FYREFLOCK_ASSIST=1 (or true, and nothing else counts) to turn the check off, for when you genuinely want Claude to help you write or translate a line. The stranger is not told when this is on, so it is a tool for you rather than a mode of the product.

What leaves your machine, and where

The pane contacts one host: https://fyreflock.com (its /mcp endpoint and the OAuth device flow under /oauth), or the address in FYREFLOCK_URL if you set one. It sends the lines you type into it, the sign-in token it holds for you, and nothing else: no files, no other conversation text, no environment variables. The two command hooks run only the plugin's own scripts by their literal paths under CLAUDE_PLUGIN_ROOT: capture-prompt.mjs keeps the text of your last prompt, and check-verbatim.mjs reads that text when the model is about to call a sending tool and blocks the call when the words differ. Neither contacts the network.

Pointing it somewhere else

FYREFLOCK_URL overrides the endpoint, for a dev server:

export FYREFLOCK_URL=http://localhost:8787/mcp

gh repo create FuloxDev/fyreflock-claude --public --description "A real person and 25 games, right inside your AI chat. Fyreflock for Claude, ChatGPT and Claude Code: everyone passes a live camera check, no bots, your words sent verbatim."cd plugin && git init && git add -A && git commit -m "Fyreflock plugin"git remote add origin https://github.com/FuloxDev/fyreflock-claude.gitgit push -u origin main

claude plugin validate ./plugin