# search_tools

A read tool on the GNS3 MCP Server MCP server.

Agent View of the PolicyLayer registry record for `search_tools`. HTML page: https://policylayer.com/tools/chistokhinsv-gns3-mcp/search-tools

## Facts

- Tool: `search_tools`
- Server: GNS3 MCP Server (`chistokhinsv/gns3-mcp`) — https://policylayer.com/tools/chistokhinsv-gns3-mcp.md
- Homepage: https://github.com/ChistokhinSV/gns3-mcp
- Risk category: Read (Low risk)
- Registry record: grade B, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "search_tools",
    "arguments": {}
  }
}
```

## Why search_tools is rated Low

The name indicates this tool searches available tools or documentation, which is a read-only operation with no side effects. However, confidence is reduced due to the empty description, which prevents full verification of its actual behavior and scope. Within the context of a GNS3 lab automation server, a search function would likely be informational rather than operationally impactful.

From the tool's own definition: "Tool name 'search_tools' and the absence of any description suggesting data retrieval or discovery functionality."

## Use case

AI agents call search_tools to retrieve information from GNS3 MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches GNS3 MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_tools": {}
  }
}
```

## Other tools on GNS3 MCP Server (15)

- `console` — Execute — https://policylayer.com/tools/chistokhinsv-gns3-mcp/console.md
- `http_client` — Execute — https://policylayer.com/tools/chistokhinsv-gns3-mcp/http-client.md
- `node` — Execute — https://policylayer.com/tools/chistokhinsv-gns3-mcp/node.md
- `ssh` — Execute — https://policylayer.com/tools/chistokhinsv-gns3-mcp/ssh.md
- `drawing` — Other — https://policylayer.com/tools/chistokhinsv-gns3-mcp/drawing.md
- `gns3_connection` — Other — https://policylayer.com/tools/chistokhinsv-gns3-mcp/gns3-connection.md
- `link` — Other — https://policylayer.com/tools/chistokhinsv-gns3-mcp/link.md
- `my_tool` — Other — https://policylayer.com/tools/chistokhinsv-gns3-mcp/my-tool.md
- `node_file` — Other — https://policylayer.com/tools/chistokhinsv-gns3-mcp/node-file.md
- `project` — Other — https://policylayer.com/tools/chistokhinsv-gns3-mcp/project.md
- `tftp` — Other — https://policylayer.com/tools/chistokhinsv-gns3-mcp/tftp.md
- `notification` — Read — https://policylayer.com/tools/chistokhinsv-gns3-mcp/notification.md
- `project_docs` — Read — https://policylayer.com/tools/chistokhinsv-gns3-mcp/project-docs.md
- `query_resource` — Read — https://policylayer.com/tools/chistokhinsv-gns3-mcp/query-resource.md
- `export_topology_diagram` — Write — https://policylayer.com/tools/chistokhinsv-gns3-mcp/export-topology-diagram.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=chistokhinsv-gns3-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/chistokhinsv-gns3-mcp