// SCAN REPORT

Agent Store

19 tools. 6 can modify or destroy data without limits.

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

Last updated: 31 Aug 2026

6 can modify or destroy data

13 read-only

19 tools total

Community server · catalogue entry checked 07/07/2026

How to control Agent Store ↓

TOOL MAP

What Agent Store exposes to your agents

Read (13) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Agent Store tools

Execute · Medium gbrain_think While 'gbrain_think' retrieves and synthesizes data from existing wiki pages (suggesting Read-like properties), the explicit action verb 'Run' combined with the complexity of 'multi-hop synthesis' indicates code executio Execute · High fleet_dispatch This tool triggers an external multi-stage pipeline (classification, worker execution, QA gates) on a fleet of agents. Execute · High gbrain_query The name 'gbrain_query' suggests querying a knowledge base or brain system. Execute · Medium reindex_wiki This tool rebuilds a full-text search index from scratch, which is an operation that executes a rebuild process.

6 of Agent Store's 19 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Agent Store

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

Cap read operations

{
  "find_related": {
    "limits": [
      {
        "counter": "find_related_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 Agent Store — 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 AGENT STORE →

Instant setup, no code required.

FULL CATALOGUE

All 19 Agent Store tools

EXECUTE 4 tools

Execute fleet_dispatch Dispatch a task to the Asteroid Fleet. Routes through pipeline: classification → worker → QA gates → response. Execute gbrain_query gbrain_query Execute gbrain_think Run multi-hop synthesis across wiki pages. Produces a cited answer Execute reindex_wiki Rebuild the FTS5 search index from scratch.

READ 13 tools

OTHER 2 tools

Other file_synthesis file_synthesis Other suggest_edges suggest_edges

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Agent Store

Is the Agent Store MCP server safe to use without restrictions? +

The Agent Store server is primarily read-only with 13 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Agent Store MCP server expose? +

19 tools across 2 categories: Execute, Read. 13 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Agent Store? +

Register the Agent Store 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 Agent Store tool call.

Deterministic rules across all 19 Agent Store tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AGENT STORE →

Instant setup, no code required.

19 Agent Store tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Agent Store's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →