get_tool
Full detail for one tool by category and id (as returned by search_tools). Includes description, install command, repo, license, and — for skills — capabilities and prerequisites extracted from the SKILL.md itself.
This record as markdown: /tools/com-getagentictools-catalog/get-tool.md
What get_tool does on Catalog
AI agents call get_tool 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | Yes | The tool id, e.g. "mattpocock-skills-tdd" |
category | string | Yes | The tool's category, e.g. "skills" |
Parameters from the server's own tool schema.
Why get_tool is rated Low
This tool queries a catalog database by tool ID to fetch and return structured metadata. There is no modification, deletion, code execution, or financial transaction involved. It is a straightforward lookup operation analogous to a GET request in REST APIs, making it a Read category tool with low severity.
From the tool's definition Tool retrieves 'full detail for one tool' by identifier, returning metadata like description, install command, repo, and license. The verb 'get' and the action of retrieving static information with 'no side effects' align with read-only query operations.
Attacks that exploit this kind of access
The rule that runs get_tool 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 get_tool, this is the rule to start with:
get_tool is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Catalog, apply this rule, and every get_tool call is checked against it from then on.
Questions about get_tool
Full detail for one tool by category and id (as returned by search_tools). Includes description, install command, repo, license, and — for skills — capabilities and prerequisites extracted from the SKILL.md itself. It is categorised as a Read tool in the Catalog MCP Server, which means it retrieves data without modifying state.
get_tool accepts 2 parameters: id, category. Required: id, category. The full parameter table on this page comes from the server's own tool schema.
Register the Catalog MCP server in PolicyLayer and add a rule for get_tool: 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.
get_tool is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_tool 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.
Set action: deny in the PolicyLayer policy for get_tool. 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.
get_tool 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.
More on Catalog, and thousands of servers like it.
This server
Across the catalogue