Blender Bridge

Start account sign-in

start_auth

Destructive

Request sign-in state for the receiving MCP connection. Standalone MCP can create a browser account flow; open_browser defaults to true. The user enters credentials only on the account website. A new standalone flow can replace a pending one; use poll_auth_status to check an existing flow. Desktop-managed receiving connections use the current Desktop account and return its readiness or a request to resolve access there, without a separate MCP sign-in.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_auth"
  }
}

Input Schema

Name	Required	Description	Default
`open_browser`	No	For standalone sign-in, open the browser unless false.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 23, 2026
- addedInput schema / properties / open_browser / description
```
Added value: +"For standalone sign-in, open the browser unless false."
```
First observedOct 23, 2026

TDQS

A4/5.0

Behavior4/5

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

Adds context beyond the annotations: a pending flow can be replaced (compatible with destructiveHint=true and idempotentHint=false), credentials are entered only on the account website (a meaningful security trait), and Desktop connections short-circuit to a readiness check. It does not disclose what the call returns or how long a flow stays pending.

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?

Four sentences, each carrying a distinct distinction (standalone vs Desktop, credential handling, replacement behavior, polling alternative), with the core action front-loaded. Some density from repeated 'receiving connection'/'Desktop-managed receiving connections' phrasing, but no filler.

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?

There is no output schema, and the description compensates reasonably by describing the two possible outcomes (browser account flow vs. returns readiness or a request to resolve access there). The exact return payload of a successful standalone start is still left implicit, which is the only real gap.

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, and the description adds the one thing the schema omits: that open_browser defaults to true. It also scopes the parameter ('for standalone sign-in'), clarifying it is irrelevant in the Desktop path.

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?

States a specific action (request sign-in state) on a specific resource (the receiving MCP connection) and immediately splits the two execution modes, standalone browser flow vs. Desktop-managed connection. The phrasing 'receiving MCP connection' is somewhat internal jargon, but an agent can still distinguish this from poll_auth_status and the view_sign_in family.

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?

Explicitly routes the agent: use poll_auth_status to check an existing flow, and a new standalone flow can replace a pending one. It also carves out the Desktop-managed case where no separate MCP sign-in should be started. Missing only an explicit 'when not to call this at all' exclusion.

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

All Blender Bridge 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?