Skip to main content
Glama
IPGeolocation MCP Server

IPGeolocation MCP Server

Bulk User-Agent Parser

bulk_parse_user_agent
Read-only

Parse up to 250 user-agent strings in one request and return structured browser, device, engine, and OS details.

Instructions

Read-only bulk user-agent parsing via POST /v3/user-agent-bulk. Paid only. Cost: 1 credit per successful string. This MCP server accepts up to 250 explicit user-agent strings. Larger batches are rejected before any API call. Complete results within upstream and cache byte limits are returned directly or as cached pages. Cached pages use get_cached_result without another API call or additional credits. An upstream body above its byte limit, or a required pagination snapshot too large to retain, returns a non-retryable resource_limit error with no cursor; the API may already have used credits.

Returns one parsed object per string with user_agent_string, name, type, version, version_major, device, engine, and operating_system. uaStrings must be a non-empty array of exact user-agent strings; empty/null strings are rejected locally before any API call. parse_user_agent handles a single string. force_refresh bypasses cached data, makes a new upstream request, and can consume credits.

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": {
      "uaStrings": "<uaStrings>"
    },
    "name": "bulk_parse_user_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
uaStringsYesArray of user-agent strings to parse. Minimum 1, maximum 250 in this MCP server.
force_refreshNoDefault false. When true, bypasses cached bulk user-agent parsing data; a successful refresh makes a new upstream request and can consume credits.

Output Schema

NameRequiredDescriptionDefault
pageNo
errorNoPresent when the whole tool call fails, with isError: true.
itemsNoPresent on success: complete API results in input order, including any per-item error messages.
errorsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.0.4
    • addedInput schema / properties / uaStrings / items / pattern
      Added value: +"\\S"
  2. Changed2 schema fields changedv2.0.3
    • removedOutput schema / properties / items / items / additionalProperties / anyOf
      Removed value: -[
      -  {
      -    "type": "null"
      -  },
      -  {
      -    "type": "boolean"
      -  },
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "array"
      -  },
      -  {
      -    "type": "object"
      -  }
      -]
    • addedOutput schema / properties / items / items / additionalProperties / type
      Added value: +[
      +  "null",
      +  "boolean",
      +  "number",
      +  "string",
      +  "array",
      +  "object"
      +]
  3. Addedv2.0.1
  4. Removedv2.0.0
  5. Changed1 schema field changedv1.0.16
    • addedInput schema / properties / uaStrings / items / minLength
      Added value: +1
  6. Changed1 schema field changedv1.0.15
    • changedInput schema / properties / force_refresh / description
      Previous value: -"Default false. Leave unset unless the user asks to refresh or rerun."New value: +"Default false. Set true only when the user asks to refresh cached bulk user-agent parsing data; a successful refresh makes a new upstream request and can consume credits."
  7. First observedv1.0.10

TDQS

A4.8/5.0
Behavior5/5

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

Goes well past the readOnlyHint/openWorldHint annotations by disclosing billing semantics (1 credit per successful string, paid only), local pre-flight rejection of empty/null strings, and a precise failure mode: a non-retryable resource_limit error with no cursor where credits may already have been consumed. That credit-consumption caveat is exactly the kind of context annotations cannot express.

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?

Front-loaded with purpose and cost, then limits, then caching, then error behavior — good ordering. It is somewhat dense and partially restates the schema (the 250 cap appears in both the description prose and the maxItems constraint), but almost every sentence carries operational weight.

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 a 2-parameter bulk tool with an output schema, the description covers cost, batch limits, validation behavior, caching/pagination routing, and failure modes. The return-shape sentence is slightly redundant with the output schema, but nothing an agent needs in order to call this correctly 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 would be 3, but the description adds real meaning: uaStrings must be *exact* strings and invalid entries are rejected locally before any API call, and force_refresh is framed as bypassing cache at the cost of a new upstream request and credits. It does not add format or example guidance for what a valid UA string looks like.

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?

Opens with a specific verb+resource (bulk user-agent parsing) plus the exact upstream endpoint, and immediately distinguishes itself from the single-string sibling by naming parse_user_agent. An agent can tell what this does and which tool it competes with without opening the schema.

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?

Explicitly states the selection conditions: use this for batches up to 250 explicit strings, use parse_user_agent for a single string, and use get_cached_result for cached pages without spending credits. It also states the exclusion boundary (larger batches are rejected before any API call) and the cost tradeoff for force_refresh.

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