search_capabilities

SERVERAdrata SOURCE@adrata/adrata-mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/adrata-adrata-mcp/search-capabilities.md

WHAT IT DOES

What search_capabilities does on Adrata

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

RISK

Why search_capabilities is rated Low

Even though search_capabilities only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs search_capabilities safely

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

search_capabilities Allowed

search_capabilities 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": {
    "search_capabilities": {}
  }
}

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

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

FAQ

Questions about search_capabilities

What does the search_capabilities tool do? +

Search the authorized capability registry without loading schemas into context. A branded server fixes the namespace to its product. Search is discovery only: describe one exact result before run_capability, and never execute a fuzzy result. It is categorised as a Read tool in the Adrata MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_capabilities? +

Register the Adrata MCP server in PolicyLayer and add a rule for search_capabilities: 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 Adrata. Nothing to install.

What risk level is search_capabilities? +

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

Can I rate-limit search_capabilities? +

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

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

search_capabilities is provided by the Adrata MCP server (@adrata/adrata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Adrata, and thousands of servers like it.

This server

All 395 Adrata tools →

Across the catalogue

binary_search on 010 Editor →evaluate_search_quality on ACE-MCP →search_torrents on M-Team MCP Server →aiva_search_customers on AIVA MCP Server → The MCP Attack Database →

Guides

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