Pil runs on your own machine — the client starts it, so there is no endpoint to ping. 52 installs a week from pypi. Last commit 16 Sep 2026.
PIL: local-first knowledge base for your Instagram saved posts, with a read-only MCP server.
We read the source, 3 d ago · rules 995398eba69f
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.
p = subprocess.run(["instagram-cli"] + args, capture_output=True, text=True, timeout=300)
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(["instagram-cli"] + args, capture_output=True, text=True, timeout=300)
with open(os.path.join(HERE, name), 'rb') as f:
try { execSync(`node --check ${tmp}`, { stdio: 'pipe' }); ok(true, 'script[' + i + '] syntax'); }
window.eval(fs.readFileSync(path.join(HERE, 'ring-component', 'pil-ring.js'), 'utf8'));
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Pil and you get told the day something new turns up.
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 pil -- uvx personal-instagram-library
{
"mcpServers": {
"pil": {
"command": "uvx",
"args": [
"personal-instagram-library"
]
}
}
}
[mcp_servers.pil]
command = "uvx"
args = ["personal-instagram-library"]
{
"mcpServers": {
"pil": {
"command": "uvx",
"args": [
"personal-instagram-library"
]
}
}
}
{
"servers": {
"pil": {
"type": "stdio",
"command": "uvx",
"args": [
"personal-instagram-library"
]
}
}
}
Kromatic's public MCP server for read-only access to the Kromatic knowledge base.
MCP server for Yuque — expose your knowledge base to AI assistants.
Read-only access to your Molio local knowledge base: search, read, browse, and AI Q&A.
Read-only offline MCP server over a curated Shopware developer knowledge base
nol MCP server -- search, cited Q&A, and pages over your team's knowledge base
Local RAG MCP server for your own .md knowledge base: BM25 + local Ollama, offline, zero egress.
Guru MCP Server - Connect AI tools to your Guru knowledge base
MCP server for GLPI: tickets, ITIL, assets, knowledge base. GLPI 10/11. Not affiliated with Teclib'.
Answers built from our own checks of this server.