capacities_search

THE RISK

Low Risk

Why capacities_search needs a policy

This tool retrieves and queries data across Capacities spaces without creating, modifying, or deleting content. Search with optional filtering is a classic Read operation with no irreversible consequences or external execution risk.

From the tool's definition Tool description states 'Search for content across Capacities spaces' with no mention of modification, deletion, or side effects.

Documented attack patterns abuse exactly the kind of access capacities_search gives an agent:

POLICY

How to control capacities_search

PolicyLayer is an MCP gateway — it sits between your AI agents and Capacities MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for capacities_search:

policy.json

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

capacities_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Capacities MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Capacities MCP Server tools

Write capacities_save_to_daily_note Add markdown text to today Write capacities_save_weblink Save a web link to a Capacities space with optional title and tags Read capacities_get_space_info Get information about a Capacities space Read capacities_list_spaces Get a list of all personal spaces in Capacities Read capacities_read_object_content Retrieve the full content of a Capacities object by its ID. Optionally provide a title or

All 6 Capacities MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about capacities_search

What does the capacities_search tool do? +

Search for content across Capacities spaces with optional filtering. It is categorised as a Read tool in the Capacities MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on capacities_search? +

Register the Capacities MCP Server MCP server in PolicyLayer and add a rule for capacities_search: 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 Capacities MCP Server. Nothing to install.

What risk level is capacities_search? +

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

Can I rate-limit capacities_search? +

Yes. Add a rate_limit block to the capacities_search 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 capacities_search completely? +

Set action: deny in the PolicyLayer policy for capacities_search. 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 capacities_search? +

capacities_search is provided by the Capacities MCP Server MCP server (jem-computer/capacities-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Capacities MCP Server tool call.

Start from Capacities MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →