Rediscover tools from all MCP servers so the mcp_chain tool can be used
AI agents call discover_tools to retrieve information from Mcp Tool Chainer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about available MCP tools for the purpose of enabling the chaining functionality. It performs discovery/enumeration without creating, modifying, deleting, or executing any operations. This is a low-severity read operation with minimal blast radius—an AI agent misusing it could only enumerate what tools exist, not execute them or cause damage.
From the tool's definition Tool name 'discover_tools' and description 'Rediscover tools from all MCP servers' indicate querying/listing available tools. The verb 'discover' and the action of enumerating tools with no modification capability suggests a read-only retrieval operation.
Documented attack patterns abuse exactly the kind of access discover_tools gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Tool Chainer, and nothing reaches the server without passing your rules. This is the rule we recommend for discover_tools:
{
"version": "1",
"default": "deny",
"tools": {
"discover_tools": {}
}
}discover_tools is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Rediscover tools from all MCP servers so the mcp_chain tool can be used. It is categorised as a Read tool in the Mcp Tool Chainer MCP Server, which means it retrieves data without modifying state.
Register the Mcp Tool Chainer MCP server in PolicyLayer and add a rule for discover_tools: 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 Mcp Tool Chainer. Nothing to install.
discover_tools 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 discover_tools 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 discover_tools. 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.
discover_tools is provided by the Mcp Tool Chainer MCP server (thirdstrandstudio/mcp-tool-chainer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Mcp Tool Chainer tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
3 Mcp Tool Chainer tools catalogued and risk-classified — across an index of 42,500+ MCP servers.