Enterprise DNAEnterprise DNA

MCP Servers

aggrete/aggrete

Policy proxy that governs what AI assistants can reach and do: refuses forbidden tool calls before the upstream is conta

Visit site ↗

Our verdict

Not reviewed yet

We have not reviewed aggrete/aggrete yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About aggrete/aggrete

Aggrete is a policy proxy for AI assistants. It sits between an assistant and upstream tools, refusing forbidden tool calls before they reach the target. Written in Python, it governs what assistants can reach and do.

Best for

Developers who need a lightweight policy gate for AI assistant tool calls

Use cases

  • Enforce allow or deny policies on AI tool calls
  • Block disallowed actions before upstream execution
  • Add a governance layer for assistant tool access

Notes

1 stars on GitHub. Last updated 2026-09-15. Licensed Apache-2.0.

Pros

  • Simple Python implementation
  • Prevents forbidden calls before upstream contact
  • Lightweight proxy approach

Cons

  • Very early stage with minimal adoption
  • Limited documentation or community
  • Python only

Key facts

What we have checked

Days since the last commit
10
Checked GitHub
GitHub forks
2
Checked GitHub
GitHub stars
2
Checked GitHub
Days to a first reply on issues
50.8
Checked GitHub
Open issues
6
Checked GitHub
Releases in the last 90 days
30
Checked GitHub

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

How to use

How to set it up

As the listing publishes it. We have not run this install.

Install

uvx aggrete --demo                  # the walkthrough — no config, auth, or network

Clients the listing names (not checked here)

Claude Code

Install

Add aggrete/aggrete to your client

Not verified yet

Our lab has not run this server yet. "Config checked" on a client means the recipe matches that client's documented config format; it does not mean we ran it.

Claude Code

Config checked

Run in your terminal (runs on your computer)

claude mcp add --transport stdio aggrete-aggrete -- uvx aggrete@0.13.4

Version 0.13.4 · From the Official MCP registry, read · Format checked against Claude Code's config docs

Claude Desktop

Config checked

Add to claude_desktop_config.json (runs on your computer)

{
  "mcpServers": {
    "aggrete-aggrete": {
      "command": "uvx",
      "args": [
        "aggrete@0.13.4"
      ]
    }
  }
}

Version 0.13.4 · From the Official MCP registry, read · Format checked against Claude Desktop's config docs

Cursor

Config checked

Add to .cursor/mcp.json (runs on your computer)

{
  "mcpServers": {
    "aggrete-aggrete": {
      "command": "uvx",
      "args": [
        "aggrete@0.13.4"
      ]
    }
  }
}

Version 0.13.4 · From the Official MCP registry, read · Format checked against Cursor's config docs

VS Code

Config checked

Add to .vscode/mcp.json (runs on your computer)

{
  "servers": {
    "aggrete-aggrete": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "aggrete@0.13.4"
      ]
    }
  }
}

Version 0.13.4 · From the Official MCP registry, read · Format checked against VS Code's config docs

Codex

Config checked

Add to ~/.codex/config.toml (runs on your computer)

[mcp_servers.aggrete-aggrete]
command = "uvx"
args = ["aggrete@0.13.4"]

Version 0.13.4 · From the Official MCP registry, read · Format checked against Codex's config docs

  • ChatGPT: ChatGPT connects only to remote servers that need no API key.

Recipes come from the server's entry in the official MCP registry. Check the package name before you run it, and keep keys out of shared files.

Works with

What aggrete/aggrete connects to

5 clients, each with how we know and when we checked.

Works withTypeHow we knowChecked
Claude CodeClientInstall recipe matches the client's documented formatRuns locally, version 0.13.4Config checkedClaude Code docs
Claude DesktopClientInstall recipe matches the client's documented formatRuns locally, version 0.13.4Config checkedClaude Desktop docs
CursorClientInstall recipe matches the client's documented formatRuns locally, version 0.13.4Config checkedCursor docs
VS CodeClientInstall recipe matches the client's documented formatRuns locally, version 0.13.4Config checkedVS Code docs
CodexClientInstall recipe matches the client's documented formatRuns locally, version 0.13.4Config checkedCodex docs

Health and security

Is aggrete/aggrete looked after, and what do its setup files show

Health score

60 out of 100

Does someone look after this repository? It does not say the code is good or safe. Worked out from GitHub signals checked . How it is worked out

PartPointsWhat we saw
Recent activity30 of 30Last push 10 days ago
Releases15 of 1530 releases in 90 days
Issue replies0 of 20First reply in 50.8 days (median)
Maintainer15 of 15Owned by an organisation
Official source0 of 20Community server

Sources

Where this comes from

  • GitHubRegistry

    Checked · Days since the last commit, GitHub forks, GitHub stars, Days to a first reply on issues, Open issues, Releases in the last 90 days

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to MCP ServersSubmit your own entry →