Skip to main content
Glama
Mapbox MCP Server

Mapbox MCP Server

Official
by mapbox

Send Feedback to the Developer

feedback_tool

Sends user feedback about map, place, route, traffic, or app problems to the developer via Mapbox Feedback API so they can review and improve the product.

Instructions

Send the user's feedback about this app or agent to its developer, through the Mapbox Feedback API (Public Preview), so the developer can understand what users need and improve the product. Feedback can be about anything in the product: for example a place that has closed or has wrong details, a missing place, a closed road, a route with an illegal turn, a wrong travel time, or something about the app itself. It is filed under the Mapbox account that owns the access token, in the same feed as that account's Feedback Agent reports, and the developer reviews it in Feedback Explorer. It does not report the problem to Mapbox. Use it only when the user asks to send feedback, or agrees when you offer. Before calling it, show the user the exact feedback text, category and location you will send and get their go-ahead. Take the coordinates from an earlier search, place or directions result rather than guessing, and leave them out when the feedback is not about a place, such as most feedback about the app itself. Send one report per problem, and do not resend one that already succeeded. To avoid filing the same problem twice, the tool first checks the account's own reports from the last 30 days and does not send if one with the same category within 50 m is still awaiting review; it returns that report instead. Only set send_anyway when the user says the earlier report is about a different problem. Returns the item id and its status (received).

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": "feedback_tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
categoryYesThe kind of problem: - poi_closed: the place no longer exists - poi_details: wrong name, hours, phone, website or other details - poi_location: the place is on the wrong spot - poi_missing: a place, address or business could not be found - map_data_issue / map_rendering_issue: wrong map features, or the map draws wrong - routing_issue: something else wrong with a route - poor_routing_issue / alternative_route_issue / no_route: a bad, missing or no route - illegal_turn / illegal_entrance / missing_expected_maneuver: a turn or entrance the route got wrong - eta_issue: the travel time was wrong - road_closure_issue / road_incident_issue / speed_limit_issue: road data - traffic_issue / false_negative_traffic_issue / false_positive_traffic_issue: traffic shown wrong (missed congestion, or congestion that is not there) - application_issue: anything about the app itself rather than the map data, such as a bug, a confusing screen or a suggestion
feedbackYesWhat is wrong, in the user's own words, plus what it should be if they said. Name the place or road. Example: "Blue Bottle Coffee at 66 Mint St has closed permanently."
coordinatesNoWhere the feedback is about: the place or the spot on the route, usually taken from an earlier search or directions result. Do not guess. Leave it out when the feedback is not about a place, such as most feedback about the app itself.
send_anywayNoSkip the check for an earlier report from this account. Set it only after the tool said a report already exists and the user says theirs is about a different problem.

Output Schema

NameRequiredDescriptionDefault
idYes
statusYesreceived (new, awaiting review), fixed, reviewed or out_of_scope. The API may add more.
categoryYes
feedbackYes
locationNo
trace_idNo
duplicateNoTrue when nothing was sent because this account already has a matching report awaiting review; the fields describe that earlier report.
created_atNo
updated_atNo
received_atNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.18.1

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations, the description discloses account ownership, the Feedback Explorer review flow, that it does not report the problem to Mapbox, the 30-day and 50 m duplicate check, the returned existing report instead of sending, and the success status returned. These are meaningful behavioral traits for a write operation with open-world effects.

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 description is long but well structured: purpose first, then filing behavior, consent rules, coordinate guidance, duplicate handling and return value. A few clauses such as the developer-improvement rationale are slightly padded, but overall it is efficient for a tool with this much required behavior.

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?

Given that this is a non-destructive but non-read-only open-world submission tool with four parameters, an output schema, and duplicate-detection behavior, the description covers everything an agent needs: consent, parameter source rules, deduplication, send_anyway use, and return values.

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 description coverage is 100%, and the schema already explains the category enum, feedback wording, coordinates source and omission rule, and send_anyway condition. The description reinforces those constraints through the consent step, but it adds little parameter-level syntax or meaning beyond what the schema already provides, so the baseline 3 is appropriate.

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?

The description states a specific verb and resource: send the user's feedback about the app or agent to its developer through the Mapbox Feedback API. It also distinguishes the action from reporting to Mapbox and from the account's Feedback Agent reports, so an agent can tell what this tool is and is not for.

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?

It gives explicit when-to-use guidance: only when the user asks or agrees after being offered. It also states the required consent step of showing the exact feedback text, category and location before sending, and names when coordinates should be omitted.

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