ecosystem_stats

Measured aggregates across the whole catalog: totals, maintainer count, license coverage, star concentration. Computed from harvested data, nothing estimated. Source: getagentictools.com/stats

SERVERCatalog SOURCEhttps://getagentictools.com/api/mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/com-getagentictools-catalog/ecosystem-stats.md

WHAT IT DOES

What ecosystem_stats does on Catalog

AI agents call ecosystem_stats to retrieve information from Catalog without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why ecosystem_stats is rated Low

This tool only reads and returns pre-computed aggregate statistics about the catalog ecosystem (totals, maintainer count, license coverage, star concentration). It has no capability to modify, create, delete, or execute external operations. It is a straightforward data retrieval operation with no side effects.

From the tool's definition Tool description states it retrieves 'Measured aggregates' and 'Computed from harvested data' with no mention of modification, creation, deletion, or side effects. The name 'ecosystem_stats' and description align with querying/retrieving aggregate statistics.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs ecosystem_stats safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Catalog, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ecosystem_stats, this is the rule to start with:

ecosystem_stats Allowed

ecosystem_stats is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ecosystem_stats": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Catalog, apply this rule, and every ecosystem_stats call is checked against it from then on.

FAQ

Questions about ecosystem_stats

What does the ecosystem_stats tool do? +

Measured aggregates across the whole catalog: totals, maintainer count, license coverage, star concentration. Computed from harvested data, nothing estimated. Source: getagentictools.com/stats. It is categorised as a Read tool in the Catalog MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on ecosystem_stats? +

Register the Catalog MCP server in PolicyLayer and add a rule for ecosystem_stats: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Catalog. Nothing to install.

What risk level is ecosystem_stats? +

ecosystem_stats is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit ecosystem_stats? +

Yes. Add a rate_limit block to the ecosystem_stats rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block ecosystem_stats completely? +

Set action: deny in the PolicyLayer policy for ecosystem_stats. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides ecosystem_stats? +

ecosystem_stats is provided by the Catalog MCP server (https://getagentictools.com/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Catalog, and thousands of servers like it.

This server

All 5 Catalog tools →

Across the catalogue

cache_stats on ACE-MCP → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →