AiLinkAny

Create isolated local coding peer

agent_create_peer

Destructive

Explicitly creates one peer coding Agent bound to the current authorized account, device, AI Session, workflow, and Workspace. This tool always starts the existing Agent Runtime in a new git_worktree; it never performs cloud inference or automatically decomposes a single-Agent task. Returns peer_id for agent_send_peer and agent_id for the existing agent_status/agent_result/agent_stop tools. Shared Files Advisory is coordination-only, not a lock or overwrite permission. 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": {
      "workspace_id": "<workspace_id>",
      "provider_id": "<provider_id>"
    },
    "name": "agent_create_peer"
  }
}

Input Schema

Name	Required	Description
`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.
`provider_id`	Yes	Provider id returned by agent_list, such as codex.
`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.
`shared_files`	No	Optional relative files this peer expects to edit, for advisory overlap detection only. Examples: Cargo.toml, package.json, wrangler.toml, schema/api/release files.
`workspace_id`	Yes	Required Workspace id returned by open_workspace. The peer source project and device are derived from this authorized Workspace.
`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

A3.6/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, openWorldHint=true, idempotentHint=false and readOnlyHint=false, so the safety profile is covered. The description adds real context beyond that: the peer always runs the existing Agent Runtime inside a NEW git_worktree, never uses cloud inference, and never auto-decomposes a single-Agent task — exactly the facts an agent needs before spawning something destructive. It omits auth/permission prerequisites and any limits on concurrent peers.

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 important behavioral facts (worktree isolation, no cloud inference, no auto-decomposition) are front-loaded and the return-ID mapping is efficient. However, 'Select this tool from the user's intent when it is the best match' is filler that says nothing actionable, and the closing sentence about not needing to mention ailinkany.com/MCP/a plugin is a long tail for one triggering hint.

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?

With an output schema present, the description need not describe return values, yet it goes further by mapping peer_id to agent_send_peer and agent_id to agent_status/agent_result/agent_stop, which closes the cross-tool workflow gap. Combined with the worktree-isolation and shared-files semantics, an agent has enough to call this correctly for an 8-parameter tool; only permission/prerequisite detail is missing.

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 8 parameters, which sets the baseline at 3. The description adds a small amount of meaning — the Shared Files Advisory is coordination-only and not a lock or overwrite permission, and the destination may be inherited rather than passed — but no syntax, format, or defaults beyond what the schema states.

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

Purpose4/5

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

The description gives a specific verb and resource ('Explicitly creates one peer coding Agent') plus its binding scope (account, device, AI Session, workflow, Workspace), and 'peer' plus 'git_worktree' distinguishes it from plain agent_start. It stops short of naming the alternative tool an agent should pick when it does not want a peer, so the sibling differentiation is inferential rather than explicit.

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

Usage Guidelines3/5

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

'Select this tool from the user's intent when it is the best match' is near-tautological and gives no real selection rule, and no sibling (agent_start, agent_resume, agent_send_peer) is named as the alternative for a competing case. The guidance that a local destination may be explicit or inherited from context, and that the user need not mention the product name, does help an agent decide to invoke it, but when-not guidance is absent.

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?