Skip to main content
Glama
mcp-browserdata

mcp-browserdata

by igortetyuev

sync_data

Copy or merge cookies, bookmarks, credentials, and browser storage between two browsers with dry-run previews, conflict handling, and counters-only results that keep secret values server-side.

Instructions

Copy/merge data between two browsers. Returns COUNTERS ONLY — secret values stay inside the server.

kinds defaults to all four. domain limits cookies/credentials/bookmarks by substring and is REQUIRED for per-origin storage sync (unless both browsers are quit Chromium — then whole storage dirs are raw-copied). direction=merge syncs both ways. dry_run=True (default) reports what would change without writing. Run writes only on explicit user request.

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": {
      "src": "<src>",
      "dst": "<dst>"
    },
    "name": "sync_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
dstYes
srcYes
kindsNo
domainNo
dry_runNo
conflictNonewest
directionNomerge

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full behavioral burden and mostly succeeds: it discloses that output is counters only, that secret values never leave the server, that dry_run is the default, and that merge is bidirectional. The notable gaps are permission/auth requirements and the irreversibility or conflict-handling behavior of a real write.

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?

The most consequential fact, counters-only output with secrets withheld, is front-loaded, followed by parameter semantics and then the write-safety rule. The telegraphic style is dense but nearly every clause carries information; minor tightening is possible in the domain/Chromium sentence.

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?

For a seven-parameter, cross-browser mutation tool with no annotations, this covers the essentials: what it returns, how the default-safe mode works, and the one parameter whose requirement is conditional. An output schema exists so return shape needs no further explanation. What remains missing is conflict-resolution behavior and any failure or permission conditions for the actual write path.

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 description coverage is 0%, so the description has to explain seven parameters itself, and it does so for the non-obvious ones: kinds defaults to all four, domain filters by substring and is required for per-origin storage sync with a stated exception, direction=merge is bidirectional, dry_run defaults true. The conflict enum (newest/prefer_src/prefer_dst/skip) and the src/dst semantics are left entirely to the schema, so it does not fully close the coverage gap.

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?

"Copy/merge data between two browsers" gives a concrete verb and a two-endpoint resource, which immediately separates it from the single-datatype get_/set_ siblings. It stops short of naming export_state/import_state as the alternative path, so the distinction from siblings is implied rather than stated.

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?

The final two sentences are effective routing guidance: dry_run defaults to reporting-only, and real writes are gated on "explicit user request." It also documents the domain prerequisite and its Chromium exception. It does not name which sibling to use instead for single-value operations, so alternatives remain inferred.

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