Context Oversharing Auditor runs on your own machine — the client starts it, so there is no endpoint to ping. 500 installs a week from npm. Last commit 11 Oct 2026.
OWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks
What the code does
We read the source, 5 h ago · rules ccca72095570
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 result = spawnSync(process.execPath, [cliPath, entry.cmd, ...args], {
pattern: /\b(?:read|cat|include|attach|append)\b[^.]{0,80}(?:\.ssh\b|\bid_rsa\b|\.env\b|\.aws[\\/]credentials\b|\bprivate[\s_-]?key\b|\.npmrc\b)/i,
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
Connect this server
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 context-oversharing-auditor -- npx -y @guardbee/mcp-context-oversharing-auditor{
"mcpServers": {
"context-oversharing-auditor": {
"args": [
"-y",
"@guardbee/mcp-context-oversharing-auditor"
],
"command": "npx"
}
}
}[mcp_servers.context-oversharing-auditor]
command = "npx"
args = ["-y", "@guardbee/mcp-context-oversharing-auditor"]{
"mcpServers": {
"context-oversharing-auditor": {
"args": [
"-y",
"@guardbee/mcp-context-oversharing-auditor"
],
"command": "npx"
}
}
}{
"mcpServers": {
"context-oversharing-auditor": {
"args": [
"-y",
"@guardbee/mcp-context-oversharing-auditor"
],
"command": "npx"
}
}
}Alternatives to Context Oversharing Auditor
same job, measured the same wayshared AI-context layer for teams — persistent memory your agents search and update over MCP
Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).
An MCP server that provides persistent memory and context management across sessions
Multi-agent context sharing, memory, and status coordination via MCP tools.
Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).
Append-only event log for cross-agent context/memory sharing via 3 MCP tools.
Read and write shared BitsWeave context, projects, tasks, and work sessions through MCP.
Shared memory for coding agents and their teams: docs, epics, tasks and decisions over MCP.
Context Oversharing Auditor — questions
Answers built from our own checks of this server.