Skip to main content
Glama
Mapbox MCP Server

Mapbox MCP Server

Official
by mapbox

Send Feedback to Mapbox

report_tool

Send feedback about the Mapbox MCP Server to its builders for bugs, wrong or confusing tool results, missing capabilities, or suggestions, after showing the user the exact text and getting approval.

Instructions

Send feedback about the Mapbox MCP server to the Mapbox team that builds it: a bug, a tool that failed or gave a wrong or confusing result, a missing capability or a suggestion. It goes to Mapbox, not to the user's account, needs no special token scope, and cannot be read back or withdrawn afterward. It is for feedback about this server, not for reporting wrong map, place or routing data. Use it only when the user asks to send feedback, or agrees when you offer. Before calling it, show the user the exact text you will send and get their go-ahead. Leave out personal details the user did not ask to share. The server adds its own version and the client name. Send one report per problem, and do not resend one that already succeeded. Returns the report id.

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": {
      "feedback": "<feedback>",
      "category": "<category>"
    },
    "name": "report_tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
categoryYesThe kind of feedback: - bug: a tool failed, errored or the map did not draw - wrong_result: a tool worked but gave a wrong, confusing or unhelpful answer - feature_request: something the user wishes the server could do - other: anything else
feedbackYesWhat happened or what the user wants, in the user's own words. For a bug or wrong result, say what was asked, what came back and what was expected. Example: "search_and_geocode_tool returned a Blue Bottle in Oakland when I asked for the one on Mint St in San Francisco."
tool_nameNoThe tool the feedback is about, if any, for example directions_tool.

Output Schema

NameRequiredDescriptionDefault
idYes
statusNo
categoryYes
feedbackYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.18.1

TDQS

A4.4/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing destination (Mapbox staff, not the user's account), that no special token scope is needed, that the report cannot be read back or withdrawn, and that the server appends version and client name. These are exactly the irreversible, side-effect details an agent needs before a non-readOnly call. Slightly short of 5 only because it does not describe failure modes or how long sending takes.

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-loads what the tool is and who receives it, then moves to constraints and the consent step. Dense but nearly every clause carries operational meaning; the personal-details sentence is the only mild restatement of general good practice.

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?

Complete for a feedback-submission tool: destination, consent requirement, irreversibility, prompt-injection-safe content rules, and expected return (the report id, which the output schema covers in detail). An agent could invoke this correctly and safely on the first attempt.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema itself enumerates the category values and explains feedback and tool_name, so the baseline applies. The description adds marginally useful guidance (personal details, one report per problem, what to include for a bug), but nothing about tool_name or the 2000-character limit beyond what the schema already states.

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: sending feedback about the Mapbox MCP server to the team that builds it. It also draws the boundary explicitly ("feedback about this server, not for reporting wrong map, place or routing data"), so an agent can separate it from data-reporting siblings without opening schemas.

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 an explicit trigger ("Use it only when the user asks to send feedback, or agrees when you offer") plus a required pre-call step: show the user the exact text and get their go-ahead. It also rules out duplicate sends and resending succeeded reports, which is when/when-not guidance at its most actionable.

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