404_mcp
404.directory MCP Streamable HTTP endpoint. Discover and compare ecosystem tools, inspect approved remote MCP schemas, and invoke curated read-only third-party tools through a controlled gateway.
This record as markdown: /tools/404-directory/404-mcp.md
What 404_mcp does on 404 Directory
AI agents invoke 404_mcp to trigger actions in 404 Directory. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why 404_mcp is rated High
Invokes third-party tools via a gateway; execution effects depend on arguments passed.
From the tool's definition invoke curated read-only third-party tools through a controlled gateway
Attacks that exploit this kind of access
The rule that runs 404_mcp safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 404 Directory, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For 404_mcp, this is the rule to start with:
404_mcp stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 404 Directory, apply this rule, and every 404_mcp call is checked against it from then on.
Questions about 404_mcp
404.directory MCP Streamable HTTP endpoint. Discover and compare ecosystem tools, inspect approved remote MCP schemas, and invoke curated read-only third-party tools through a controlled gateway. It is categorised as a Execute tool in the 404 Directory MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the 404 Directory MCP server in PolicyLayer and add a rule for 404_mcp: 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 404 Directory. Nothing to install.
404_mcp is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the 404_mcp 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 404_mcp. 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.
404_mcp is provided by the 404 Directory MCP server (MM-sheng/404-directory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 404 Directory, and thousands of servers like it.
Across the catalogue