// SCAN REPORT

Moxis

11 tools. 5 can modify or destroy data without limits.

5 write tools that can modify data. Rate limits recommended.

Last updated: 5 Jul 2026

5 can modify or destroy data

6 read-only

11 tools total

Verified server · catalogue entry verified 05/07/2026 · full schemas captured for 6 of 11 tools

How to control Moxis ↓

TOOL MAP

What Moxis exposes to your agents

Read (6) Write / Execute (5) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Moxis costs in tokens

755 tokens of tool definitions, loaded on every request

0.4% of a 200k context window

125 heaviest tool: login-instance

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Moxis tools

Write · Medium upload The upload function creates or adds a new document to MOXIS and generates a corresponding URL. Write · Medium login-instance Logging into an instance creates or modifies session/authentication state on the server, which is a reversible write operation (a logout tool also exists). Write · Medium logout-all Logging out from all registered instances is a reversible write/state-change operation — it terminates active sessions across all instances, but sessions can be re-established via login. Write · Low logout-instance Logging out from a specific instance modifies session/authentication state (terminates a session), which is a reversible write-like operation.

5 of Moxis's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Moxis

PolicyLayer is an MCP gateway — it sits between your AI agents and Moxis, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "login-instance": {
    "limits": [
      {
        "counter": "login-instance_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "hello-moxis": {
    "limits": [
      {
        "counter": "hello-moxis_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Moxis — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MOXIS →

Instant setup, no code required.

FULL CATALOGUE

All 11 Moxis tools

WRITE 5 tools

Write logout-all logout from all registered MOXIS instance Write logout-instance logout from one registered MOXIS instance, where the url is given as parameter Write set-alias-instance set alias for MOXIS instance Write upload uploads document to MOXIS and returns an url

READ 6 tools

Read hello-moxis hello moxis is the welcome call that returns an overview of all registered dashboards Read inbox-count-all returns the number of items in your inboxes for all registered instances Read inbox-count-instance returns the number of items in your inbox for a moxis instance Read inbox-overview returns items of your inbox for a moxis instance Read list-all-registered-moxis-instances Return the MOXIS instances, which are already registered Read moxis-help Simple introduction to moxis mcp plugin

FAQ

Questions about Moxis

How do I prevent bulk modifications through Moxis? +

The Moxis server has 5 write tools including login-instance, logout-all, logout-instance. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Moxis.

How many tools does the Moxis MCP server expose? +

11 tools across 2 categories: Read, Write. 6 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Moxis? +

Register the Moxis MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Moxis tool call.

Deterministic rules across all 11 Moxis tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MOXIS →

Instant setup, no code required.

11 Moxis tools catalogued and risk-classified — across an index of 43,000+ MCP servers.