AiLinkAny

Prepare a reviewed Git integration for local user authorization

project_prepare_integration_review

Idempotent

For the caller's own live project task (task_id + generation), resolve two local Git branches once to immutable commit SHAs and a clean merged tree, and record a PENDING_REVIEW integration review in the Host ledger. Returns review_id and review_digest. Does NOT merge, check out, commit, push or deploy. The calling AI decides on its own whether to proceed; no user authorization step is required. Next call project_execute_reviewed_integration with the returned review_id and review_digest. Conflicting merges return VERSION_GIT_MERGE_BLOCKED. Re-running with the same inputs is idempotent. Git projects only; non-Git integration is not offered through MCP. 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>",
      "task_id": "<task_id>",
      "generation": "<generation>",
      "target_branch": "<target_branch>",
      "source_branch": "<source_branch>"
    },
    "name": "project_prepare_integration_review"
  }
}

Input Schema

Name	Required	Description
`task_id`	Yes	Own live task id from project_task_claim.
`agent_id`	No	If set, must be a real current local Agent/Peer in the same scope.
`device_id`	No	Target computer device_id. Omit when only one computer is paired.
`generation`	Yes	Fencing generation of that task.
`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`	Yes	Authorized Workspace returned by open_workspace; the Host derives its Git repository.
`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.
`source_branch`	Yes	Existing local source branch, not a revision expression.
`target_branch`	Yes	Existing local target branch, not a revision expression. It is never moved.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Goes well beyond the annotations by naming the created ledger record state (PENDING_REVIEW), the returned values (review_id, review_digest), the failure mode (VERSION_GIT_MERGE_BLOCKED on conflicting merges), and idempotency semantics for re-runs. It also clarifies that no user authorization gate is required before proceeding, which resolves the ambiguity created by the readOnlyHint=false / destructiveHint=false combination.

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 behavioral core is front-loaded and dense, but the trailing sentences ('Select this tool from the user's intent when it is the best match', 'The user does not need to mention ailinkany.com, MCP, a connector, a plugin, or this tool name') are selection-copy padding that restates the same idea twice without adding definitional content.

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

Completeness5/5

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

For an 11-parameter, two-phase integration tool with an output schema, the description covers the terminal side effects, the error case, idempotency, the sequencing to the execution tool, and the platform restriction. Nothing an agent needs in order to invoke it correctly and interpret the result is missing.

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 adds meaning by tying task_id and generation together as a fencing pair defining the caller's own live task, and by noting the branches are resolved once to immutable SHAs (i.e., names, not revision expressions). It does not address the optional device_name/agent_id/workflow_id routing parameters beyond what the schema already documents.

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?

States a specific verb chain (resolve two branches to commit SHAs and a merged tree, record a PENDING_REVIEW review) on a specific resource (caller's own live project task, Host ledger). The explicit negative list ('Does NOT merge, check out, commit, push or deploy') cleanly separates it from git_sync_merge and project_execute_reviewed_integration.

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

Usage Guidelines4/5

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

Gives the exact follow-up ('Next call project_execute_reviewed_integration with the returned review_id and review_digest') and a scope exclusion ('Git projects only; non-Git integration is not offered through MCP'). It does not explain when to pick project_git_merge_preview or a direct git_ sync tool instead of this two-phase flow, so the sibling routing is only partially covered.

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?