Firekeep runs on your own machine — the client starts it, so there is no endpoint to ping. 1 608 installs a week from pypi. Last commit 8 Sep 2026.
Self-hosted operating layer for AI agents: knowledge, continuity, coordination, and governance.
We read the source, 18 h ago · rules 3dff92dd89df
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
return await r.eval(RELEASE_LUA, 1, key, agent_id)
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
файл ставится пользователю, в репозитории его нет, и в нём есть опасный вызов
(r"\brm\s+-\w*[rf]\w*[rf]\w*", "rm -rf"),
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.
p = subprocess.run(
base = os.path.normpath(os.path.join(importing_dir, module_name)).replace("\\", "/")
const child = spawn(executable, [...args], { detached: true, stdio: "ignore", windowsHide: true });
- name: Assemble and sign the isolated Studio update channel
shell: bash
env:
FIREKEEP_SIGNING_KEY: ${{ secrets.FIREKEEP_SIGNING_KEY }}
return __import__(name)
dl.innerHTML = d.domains.map(name =>
DOCKER_SOCKET: str = "/var/run/docker.sock"
Object.assign(process.env, receiverEnvironment);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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 firekeep -- uvx firekeep-client
{
"mcpServers": {
"firekeep": {
"args": [
"firekeep-client"
],
"command": "uvx"
}
}
}
[mcp_servers.firekeep]
command = "uvx"
args = ["firekeep-client"]
{
"mcpServers": {
"firekeep": {
"args": [
"firekeep-client"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"firekeep": {
"args": [
"firekeep-client"
],
"command": "uvx"
}
}
}
Governance layer for AI coding agents: knowledge-graph grounding, session audit, policy controls.
Agent-native knowledge, memory, task coordination, and self-governed collaboration.
MCP server for AI agents to manage multiple wallets with coordinated trading and batch operations on
Market knowledge layer for AI agents: competitors, opinions and regulations shaping your market.
Self-learning operational context layer for AI sports agents. Profile 001: golf.
Open-source, self-hosted posting layer with an MCP server for AI agents. 25+ platforms.
Governed finance operations for AP, AR, GL, approvals, reporting, and payments.
Self-hosted knowledge backend for AI agents with hybrid search and MCP tools
Answers built from our own checks of this server.