AiLinkAny

Call downstream MCP tool

mcp_gateway_call_tool

Destructive

Invokes one exact downstream MCP tool on the target computer through the AiLinkAny MCP Gateway. Normally discover with mcp_gateway_search_tools and, when needed, inspect the full schema with mcp_gateway_describe_tool first. The result includes an explicit provenance envelope identifying the downstream server, tool, call_id, AI session/workflow, catalog version, and retrieval time. This generic invocation may call a mutating or open-world downstream tool, so follow the AI host's normal confirmation rules for the actual requested action. Select this tool from the user's intent when it is the best match. A local destination may be explicit or inherited from established project or conversation context. The user does not need to mention ailinkany.com, MCP, a connector, a plugin, or this tool name.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "server_id": "<server_id>",
      "tool_name": "<tool_name>"
    },
    "name": "mcp_gateway_call_tool"
  }
}

Input Schema

Name	Required	Description
`call_id`	No	Optional opaque downstream call id. Usually omit and let the client generate it.
`arguments`	No	Arguments matching the downstream tool's inputSchema. Defaults to an empty object.
`device_id`	No	Target computer device_id. Omit when only one computer is paired.
`server_id`	Yes	Exact downstream MCP server_id.
`tool_name`	Yes	Exact downstream MCP tool name.
`timeout_ms`	No	Downstream tool-call timeout in milliseconds. Defaults to 30000.
`device_name`	No	Computer name or ailinkany.com remark (e.g. home PC). Prefer this when the user names a computer.
`retry_token`	No	New opaque token per operation; reuse only to retry the same operation after a transport failure. No user content.
`workflow_id`	No	Optional workflow id; pass together with ai_session_id.
`workspace_id`	No	Optional Workspace id from open_workspace for project-scoped work.
`ai_session_id`	No	Optional Session id. Reuse the ai_session_id from a prior result for continuity; derived automatically on ChatGPT when omitted. Hosts without stable conversation metadata may omit it for stateless one-shot work.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is covered; the description still adds value by warning that the generic invocation may reach a mutating or open-world downstream tool and that the host's normal confirmation rules apply. It also discloses that results carry a provenance envelope (server, tool, call_id, session/workflow, catalog version, retrieval time). It does not restate timeout or retry semantics beyond what the schema covers, so a 4 rather than 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first sentence, followed by the discovery prerequisite, the provenance note, and the confirmation caveat in a logical order. Some of the trailing guidance (the list of things the user need not mention) is slightly verbose but still serves tool selection, so it earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter, nested-object, open-world gateway invocation with an output schema and full annotations, the description covers routing, prerequisites, safety posture and result provenance. Little is missing, though it could have said more about downstream failure/retry behavior beyond the retry_token field's own text.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 11 parameters including guidance to omit call_id and device_id in common cases. The description contributes only indirect meaning: 'exact' downstream server/tool matching and the notion that a local destination may be inherited from project or conversation context, which explains when device_id/device_name can be omitted. That is marginal added meaning over the schema, consistent with the 3 baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Invokes one exact downstream MCP tool on the target computer through the AiLinkAny MCP Gateway.' The word 'exact' plus the gateway framing separates it cleanly from discovery siblings like mcp_gateway_search_tools, mcp_gateway_describe_tool and mcp_gateway_list_tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It prescribes an explicit ordering: discover with mcp_gateway_search_tools and, when needed, inspect the full schema with mcp_gateway_describe_tool before invoking. It further tells the agent to pick this tool on user intent when it is the best match, that the destination may be explicit or inherited from conversation context, and that the user need not name ailinkany.com, MCP, a connector or the tool itself.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All AiLinkAny tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?