Jmunch MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 724 installs a week from pypi. Last commit 1 Sep 2026.
Transparent MCP proxy. Turns fat tool responses into queryable handles: 88-99% fewer tokens.
We read the source, 17 h ago · rules 3dff92dd89df
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.
ut.innerHTML = s.per_upstream.map(u => `
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 jmunch-mcp -- uvx jmunch-mcp
{
"mcpServers": {
"jmunch-mcp": {
"args": [
"jmunch-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.jmunch-mcp]
command = "uvx"
args = ["jmunch-mcp"]
{
"mcpServers": {
"jmunch-mcp": {
"args": [
"jmunch-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"jmunch-mcp": {
"args": [
"jmunch-mcp"
],
"command": "uvx"
}
}
}
Stdio MCP proxy: intercepts oversized tool results into a queryable embedded DuckDB.
Transparent MCP proxy that independently re-verifies tool-call claims before the Host trusts them.
Drop-in MCP proxy. 71% fewer tokens. Session dedup compounds to 92%. Zero code changes.
Transparent audit proxy for MCP servers: logs every tool call, flags poisoning and rug pulls.
Turns Obsidian vaults into AI-queryable knowledge graphs with 12 tools
Markdown-first Notion MCP server. ~6-7x fewer response tokens vs official Notion MCP. 43 tools.
MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
Turns vague automation requests into tool stacks, prompts, QA checks, and human boundaries.
Answers built from our own checks of this server.