Skip to main content
Glama

Server Details

Read-only unofficial platform predictions and departure information for London Euston and Paddington, with measured accuracy. Predictions may be wrong; station screens are the official source.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-06-18
URL
ChatGPT
–
Claude
Platform Whisperer

TDQS

A4.4/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: find_train searches when no train id is known, get_departures gives a station board, get_train returns detail for one known train, get_track_record reports prediction accuracy, and list_stations lists coverage. The descriptions explicitly cross-reference each other and clarify boundaries, so an agent can reliably choose the right tool.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern: find_train, get_departures, get_track_record, get_train, list_stations. The verbs vary appropriately by action (find/get/list) while remaining predictable.

Tool Count5/5

Five tools is well-scoped for a focused platform-prediction server. Each tool earns its place: discovery, station board, train detail, accuracy reporting, and station coverage.

Completeness5/5

The read-only domain is fully covered: station discovery, departure boards, train search, single-train status, and accuracy metrics. No obvious lifecycle operation is missing, and the tools provide clear entry points and fallbacks.

Publisher details

Operator
Longford Consulting Limited (company number 11075527) · Publisher source
Vendor relationship
First-party · Publisher source
Privacy policy
Not provided
Trust center
Not available
Restrictions
Sign-in required (Google or email link, no password). Read-only. Covers London Euston and Paddington only. · Publisher source

Available Tools

5 tools
find_trainFind a trainA
Read-onlyIdempotent
Inspect

Use to find a train when you do not have its id: search by destination, time window or headcode. Returns every candidate with a match quality, never a silent choice. A station code such as MAN or the full name is an exact match, due_now trains are included, and departed trains are hidden unless include_departed is true. Use get_departures for a general board and get_train for one known train. Read only. Predictions are unofficial and may be wrong. Station screens are the official source.

Inputs: after, before, station, headcode, +2 more.

get_departuresGet departuresA
Read-onlyIdempotent
Inspect

Use for 'which platform' and 'what is leaving' questions at a station. Returns the next departures with the platform if it has been released, otherwise a prediction with confidence that never exceeds the measured accuracy of its group and can be lower. The typical percentage is the measured accuracy in the nearest estimated time-to-release group for that station, shown only when the group has at least 30 results. Each train has a status: due_now means its expected time has passed with no recorded departure, and platform_withdrawn means an announced platform was withdrawn and no number is shown. Absent fields mean unknown. Departed trains are hidden unless include_departed is true, and trains more than 15 minutes past their expected time with no departure are dropped. Times are London local with offset. Filter by operator, destination or window_min. A long board is shortened with a note saying how many trains are not shown; narrow with window_min, operator or destination. Read only. Predictions are unofficial and may be wrong. Station screens are the official source.

Inputs: station, operator, window_min, destination, +1 more.

get_track_recordGet track recordA
Read-onlyIdempotent
Inspect

Use when asked how accurate the platform predictions are. Returns measured accuracy by minutes before release, with sample sizes, from released platforms only. Read only. Predictions are unofficial and may be wrong. Station screens are the official source.

Inputs: days, station.

get_trainGet one trainA
Read-onlyIdempotent
Inspect

Use for the full platform status of one train, including departed, due_now and platform_withdrawn trains. Give train_id (from get_departures or find_train), or a headcode plus time (HH:MM today). Several matches return candidates, a headcode alone returns train_needs_time, and a train no longer on the board returns train_not_on_board, which is not retryable. Read only. Predictions are unofficial and may be wrong. Station screens are the official source.

Inputs: time, station, headcode, train_id.

list_stationsList stationsA
Read-onlyIdempotent
Inspect

Lists the stations covered, whether each is live, and its platform range. Use it first when the person asks about a station other than Euston. It does not return departures. Read only. Predictions are unofficial and may be wrong. Station screens are the official source.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
      16
      11 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources