AiLinkAny

Start persistent computer process

process_start

Destructive

Starts a PowerShell command as a persistent local process session and returns a session_id for later process_read_output / process_write_stdin / process_stop. Prefer this over shell_execute for builds, installs, tests, servers, or any job that may run longer than about one minute so the OS process outlives a single MCP request. Set pty=true for programs that need real terminal semantics such as interactive shells, REPLs, SSH, prompts, or terminal-aware CLIs; PTY sessions also support process_resize and process_send_control. Non-PTY remains the default. This is generic command execution with real side effects, not a specialized build or Git tool, and may require normal Host approval. 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": {
      "command": "<command>"
    },
    "name": "process_start"
  }
}

Input Schema

Name	Required	Description
`pty`	No	Use a real pseudo-terminal. Defaults to false.
`cols`	No	Initial PTY columns. Used only when pty=true. Defaults to 120.
`rows`	No	Initial PTY rows. Used only when pty=true. Defaults to 30.
`command`	Yes	PowerShell command to start.
`device_id`	No	Target computer device_id. Omit when only one computer is paired.
`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.
`initial_wait_ms`	No	How long to wait for initial output or completion before returning. Defaults to 1000 ms.
`working_directory`	No	Optional absolute working directory.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare destructive=true, openWorld=true, and non-idempotent, so the safety profile is covered; the description adds genuinely new behavior: the OS process outlives a single MCP request, Host approval may be required, the tool is generic execution rather than a build/Git tool, and PTY mode unlocks process_resize / process_send_control. It stops short of describing lifecycle details such as what happens to an uncollected session or how output buffers behave.

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

Conciseness3/5

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

The core two-thirds is front-loaded and dense with useful routing and PTY guidance. The trailing sentences ("Select this tool from the user's intent when it is the best match. A local destination may be explicit or inherited...") are generic routing boilerplate and a vague "local destination" phrase that adds no operational information, diluting an otherwise tight entry.

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?

An output schema exists, so return values need not be explained, and the description correctly frames the session lifecycle and its companion tools. For a 12-parameter, destructive, open-world execution tool the coverage of risk, approval, and PTY branching is strong; only long-running session management (cleanup expectations, output volume) is left implicit.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns an extra point by explaining what pty=true actually means for caller behavior and which follow-up tools become available under it, which the schema does not convey. The remaining ten parameters get no description-level meaning, but they are fully documented in the schema.

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+resource: "Starts a PowerShell command as a persistent local process session," and immediately states the observable outcome ("returns a session_id") plus the follow-up tools (process_read_output / process_write_stdin / process_stop). It explicitly differentiates itself from the nearest sibling, shell_execute, so an agent can choose without diffing schemas.

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 gives an explicit when-to-use rule ("Prefer this over shell_execute for builds, installs, tests, servers, or any job that may run longer than about one minute") and an explicit when-to-enable-pty rule (interactive shells, REPLs, SSH, prompts, terminal-aware CLIs), with the non-PTY default stated. Alternatives and the condition selecting them are both named.

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?