Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Magg

PYPI · MAGG · SCANNED SEP 20

Aggregates and proxies other MCP servers, letting LLMs discover, add, and manage tools at runtime.

Available components

0 this week 83 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 2 of 53 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (AGPL-3.0-or-later).Pass
  • Actively maintained (last published 48 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability86
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 1474 tokens (~81/item across 18 items; 16 tools + 2 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
  • Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (88% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "magg_remove_server" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Magg MCP server?

Magg runs locally as a PyPI package, launched with uvx magg. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · magg

# add to Claude Code
claude mcp add sitbon-magg -- uvx magg
// .cursor/mcp.json
{
  "mcpServers": {
    "sitbon-magg": {
      "command": "uvx",
      "args": [
        "magg"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "sitbon-magg": {
      "command": "uvx",
      "args": [
        "magg"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add sitbon-magg -- uvx magg
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sitbon-magg": {
      "type": "local",
      "command": [
        "uvx",
        "magg"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add sitbon-magg --command uvx --arg magg
# ~/.hermes/config.yaml
mcp_servers:
  sitbon-magg:
    command: "uvx"
    args: ["magg"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "sitbon-magg": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "magg"
      ]
    }
  }
}
# add to Vellum
assistant mcp add sitbon-magg -t stdio -c uvx -a magg
// mcp.json
{
  "mcpServers": {
    "sitbon-magg": {
      "command": "uvx",
      "args": [
        "magg"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 18 Sept 26 0
    • Stability: 0.97 → pass security
  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +16
    • Malware scan: unverified → pass security
  • 14 Sept 26 −15
    • Malware scan: pass → unverified security
  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +12
    • Malware scan: unverified → pass security
    • Stability: pass → 0.80 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/magg@1.2.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 53 packages
Packages resolved 53
Stale 1
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 16 exposed · ~1,321 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
magg_add_server ~438

Add a new MCP server.

NameTypeReqDescription
commandFull command to run (e.g., 'python server.py', 'npx @playwright/mcp@latest')
cwdWorking directory (for commands)
enableWhether to enable the server immediately (default: True)
envEnvironment variables (dict or JSON string)
namestringyesUnique server name
notesSetup notes
prefixTool prefix (defaults to conformed server name)
sourcestringyesURL of the server package/repository
transportTransport-specific configuration (dict or JSON string) Common options for all command-based servers: - `keep_alive` (boolean): Keep the process alive between requests (default: true) Python servers…
uriURI for HTTP servers
NameTypeReqDescription
errors
output

No examples provided.

magg_analyze_servers ~21

Analyze configured servers and provide insights using LLM.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

magg_check ~68

Check health of all mounted servers and handle unresponsive ones.

NameTypeReqDescription
actionstringAction to take for unresponsive servers: 'report' (default), 'remount', 'unmount', or 'disable'
timeoutnumberTimeout in seconds for health check per server
NameTypeReqDescription
errors
output

No examples provided.

magg_disable_server ~25

Disable a server.

NameTypeReqDescription
namestringyesServer name to disable
NameTypeReqDescription
errors
output

No examples provided.

magg_enable_server ~25

Enable a server.

NameTypeReqDescription
namestringyesServer name to enable
NameTypeReqDescription
errors
output

No examples provided.

magg_kit_info ~32

Get detailed information about a specific kit.

NameTypeReqDescription
namestringyesKit name to get information about
NameTypeReqDescription
errors
output

No examples provided.

magg_list_kits ~19

List all available kits with their status.

Input schema present but exposes no named parameters.

NameTypeReqDescription
errors
output

No examples provided.

magg_list_servers ~38

List all configured servers. Unlike the /servers/all resource, this tool also provides the runtime status of each server (mounted or not).

Input schema present but exposes no named parameters.

NameTypeReqDescription
errors
output

No examples provided.

magg_load_kit ~37

Load a kit and its servers into the configuration.

NameTypeReqDescription
namestringyesKit name to load (filename without .json)
NameTypeReqDescription
errors
output

No examples provided.

magg_reload_config ~81

Reload configuration from disk and apply changes. This will: 1. Re-read the configuration file 2. Detect changes (added/removed/modified servers) 3. Apply changes by mounting/unmounting servers as needed Note: This operation may briefly interrupt service for affected servers. Config reload can also be triggered via SIGHUP signal on Unix systems.

Input schema present but exposes no named parameters.

NameTypeReqDescription
errors
output

No examples provided.

magg_remove_server ~25

Remove a server.

NameTypeReqDescription
namestringyesServer name to remove
NameTypeReqDescription
errors
output

No examples provided.

magg_search_servers ~44

Search for MCP servers online.

NameTypeReqDescription
limitintegerMaximum number of results to return per search source
querystringyesSearch query for MCP servers
NameTypeReqDescription
errors
output

No examples provided.

magg_smart_configure ~158

Use LLM sampling to intelligently configure and add a server from a URL. This tool performs the complete workflow: 1. Collects metadata about the source URL 2. Uses LLM sampling (if context provided) to generate optimal configuration 3. Automatically adds the server to your configuration Note: This requires an LLM context for intelligent configuration. Without LLM context, it falls back to basic metadata-based heuristics. For generating configuration prompts without sampling, use configure_server_prompt.

NameTypeReqDescription
allow_addbooleanWhether to automatically add the server after configuration (default: False)
server_nameOptional server name (auto-generated if not provided)
sourcestringyesURL of the server package/repository
NameTypeReqDescription
errors
output

No examples provided.

magg_status ~18

Get basic Magg server status and statistics.

Input schema present but exposes no named parameters.

NameTypeReqDescription
errors
output

No examples provided.

magg_unload_kit ~35

Unload a kit and optionally its servers from the configuration.

NameTypeReqDescription
namestringyesKit name to unload
NameTypeReqDescription
errors
output

No examples provided.

proxy ~257

Main proxy tool for dynamic access to mounted MCP servers. This tool provides a unified interface for: - Listing available tools, resources, or prompts across servers - Getting detailed info about specific capabilities - Calling tools, reading resources, or getting prompts Annotations are used to provide rich type information for results, which can generally be expected to ultimately include JSON-encoded EmbeddedResource results that can be interpreted by the client.

NameTypeReqDescription
actionstringyesAction to perform: list, info, or call.
argsArguments for a 'call' action (call tool, read resource, or get prompt). Can be a dict or JSON string.
filter_serverFilter results by server name prefix (for 'list' action only)
limitMaximum number of items to return (for 'list' action only). Default: 100
offsetNumber of items to skip (for 'list' action only). Default: 0
pathName or URI of the specific tool/resource/prompt (with FastMCP prefixing). Not allowed for 'list' and 'info' actions.
typestringyesType of MCP capability to interact with: tool, resource, or prompt.

No output schema declared.

No examples provided.

Common questions

What is the Magg MCP server?

Magg is an MCP server listed in the public MCP registry as io.github.sitbon/magg. Aggregates and proxies other MCP servers, letting LLMs discover, add, and manage tools at runtime. This page covers its PyPI package (magg).

Is the Magg MCP server safe to use?

Magg scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Magg MCP server expose?

Magg exposes 16 tools: proxy, magg_add_server, magg_remove_server, magg_list_servers, magg_enable_server, and 11 more. Their descriptions and schemas cost roughly 1,321 tokens of context every time the server is loaded.

Is the Magg MCP server still maintained?

Magg is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Magg MCP server under?

Magg declares the AGPL-3.0-or-later licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.