Prism runs on your own machine — the client starts it, so there is no endpoint to ping. 43 installs a week from npm. Last commit 23 Oct 2026.
Complete web tasks in the user's own Chrome via an observe-decide-act browser agent.
We read the source, 1 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = spawn(
join(root, ".npmrc"),
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add prism -e 'TYPESAFE_API_KEY=<TYPESAFE_API_KEY>' -- npx -y @tulipe1735/prism
{
"mcpServers": {
"prism": {
"command": "npx",
"args": [
"-y",
"@tulipe1735/prism"
],
"env": {
"TYPESAFE_API_KEY": "<TYPESAFE_API_KEY>"
}
}
}
}
[mcp_servers.prism]
command = "npx"
args = ["-y", "@tulipe1735/prism"]
env = { TYPESAFE_API_KEY = "<TYPESAFE_API_KEY>" }
{
"mcpServers": {
"prism": {
"command": "npx",
"args": [
"-y",
"@tulipe1735/prism"
],
"env": {
"TYPESAFE_API_KEY": "<TYPESAFE_API_KEY>"
}
}
}
}
{
"servers": {
"prism": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@tulipe1735/prism"
],
"env": {
"TYPESAFE_API_KEY": "<TYPESAFE_API_KEY>"
}
}
}
}
Put your own value in place of
<TYPESAFE_API_KEY> (TypeSafe API key used for the decision model).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
TEXT_MODEL_API_KEY (OpenAI-compatible key for field text; only needed when the MCP host does not support sampling), TEXT_MODEL_BASE_URL (Field-text endpoint), TEXT_MODEL (Field-text model id).
Give browser tasks to TabRunner, an agent in your own Chrome that uses your logins.
Let AI agents observe and control Chrome tabs you explicitly share via Browse Bridge.
Cotlet's own tools: a cloud browser signed in as the user, account, credits and calls.
Debug bridge inside your web app: an agent reads the DOM, console and network. Any browser.
Real browser for any agent: Chrome/Edge/Brave via CDP, Firefox via BiDi. Refs, forms, console, net.
Human-to-AI code review bridge. Review UI in the browser, AI agents fix code via MCP.
Connect AI agents to your own Chrome with scoped access, approvals, and verified task results.
Screenshots and clean markdown of any public web page, rendered in a real Chrome browser.
Answers built from our own checks of this server.