Spicrawl

Who controls a remote browser

spicrawl_browser_control

Idempotent

Reads or changes who drives a connected remote browser: agent (your CDP connection) or human (a person in its live view, see spicrawl_browser_live_view). status reads it: poll it after sending a live-view link, and continue once controller is agent again. takeover hands control to the person before they ask (your input and navigation then fail with error -32001); release takes it back. The person can also take and give back control from the live view themselves.

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": {
      "session_id": "<session_id>"
    },
    "name": "spicrawl_browser_control"
  }
}

Input Schema

Name	Required	Description	Default
`action`	No	`status` (default) reads; `takeover` gives control to the person; `release` gives it back to the agent.
`session_id`	Yes	The remote browser session, as `session_id` from spicrawl_browser_connect_url. It exists while that connection is open.

Output Schema

Name	Required	Description
`status`	No	`running` while the connection is open.
`controller`	Yes	Who drives the browser: `agent` (your CDP connection) or `human` (a person in the live view).
`expires_at`	No	When the session ends at the latest, RFC 3339 UTC.
`session_id`	Yes	The remote browser session.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 10, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Goes well beyond the annotations (which only declare non-read-only, idempotent, non-destructive): it discloses that input and navigation calls fail with error -32001 while a human holds control, and that control can change asynchronously from the live view. That is exactly the behavioral context an agent needs to avoid misinterpreting failures.

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

Conciseness5/5

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

Two dense but well-ordered sentences: what it does, then each action, then the failure mode, then the external actor. No filler, and the cross-reference to the live-view sibling is parenthetical rather than disruptive.

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?

With an output schema present, no return-value explanation is needed, and the description still names the relevant `controller` field to poll. For a two-parameter control tool, nothing an agent needs in order to call it or interpret failures 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% and the enum already documents each action, so the description's restatement is largely redundant. It does add value by tying `takeover` to the concrete consequence (your own calls failing) and `status` to the `controller` field, which the schema does not say.

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 and resource: 'Reads or changes who drives a connected remote browser', and immediately defines the two values (`agent` / `human`). This is clearly distinguishable from siblings like spicrawl_browser_live_view and spicrawl_browser_connect_url.

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?

Gives per-action guidance: `status` is for polling after sending a live-view link, `takeover` pre-empts a person asking for control, `release` gives it back. It also warns the person may take control unprompted, which tells the agent when this tool is required rather than optional.

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

All Spicrawl 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?