Pigeonpost runs on your own machine — the client starts it, so there is no endpoint to ping. 566 installs a week from npm. Last commit 17 Sep 2026.
Private asynchronous Pigeonpost messaging for AI agents over local MCP stdio.
We read the source, 23 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.
std::fs::remove_file(path)?;
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.
ppcompliance shred --before <YYYY-MM-DD> [--dry-run|--execute]\n\
address: "169.254.169.254",
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.
этот файл ставится пользователю, но в репозитории его нет
(SELECT COUNT(*) FROM outbox),
(SELECT COALESCE(SUM(length(wrap) +
CASE WHEN token IS NULL THEN 0
const alias = path.join(root, first);
subprocess.run(["python3", str(root / "install.py"), "--destdir", staging], check=True)
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
this.child = spawn(binary, ["mcp"], {
KEY="${PIGEONPOST_BLOB_KEY:-$HOME/.ssh/pigeonpost-blob-mirror}"
with patch.dict(os.environ, {"KC_ALLOW_LOOPBACK_TEST": "1"}):
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 pigeonpost -- npx -y @bekirdag/pigeonpost
{
"mcpServers": {
"pigeonpost": {
"args": [
"-y",
"@bekirdag/pigeonpost"
],
"command": "npx"
}
}
}
[mcp_servers.pigeonpost]
command = "npx"
args = ["-y", "@bekirdag/pigeonpost"]
{
"mcpServers": {
"pigeonpost": {
"args": [
"-y",
"@bekirdag/pigeonpost"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"pigeonpost": {
"args": [
"-y",
"@bekirdag/pigeonpost"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
PIGEONPOST_HOME (Directory containing this agent's local Pigeonpost identity and state.), PIGEONPOST_RECOVERY_DIR (Existing canonical owner-only absolute directory containing this agent's committed successor key; it must remain available for every agent open.).
The author declared them in the registry entry; get the values from the project itself.
Real signed-browser automation for AI agents, over a local stdio MCP server.
Local-first web intelligence MCP server for AI coding agents
Local grounded memory for coding agents: MCP over stdio, stdlib only, a verdict per answer
Local-first codebase intelligence MCP server for AI coding agents.
Local-first, state-centric memory for coding agents. MCP server + CLI.
StremAI MCP: shared memory for AI coding agents. Connected agents can recall. OAuth + local stdio.
Artifact store for AI agents. Hosted OAuth at mcp.artifacta.io/mcp; local stdio via npm/PyPI.
Local-first semantic memory for MCP agents. Recall, remember, forget, echo, drift, stats over stdio.
Answers built from our own checks of this server.