Skip to main content
Glama
deenesjakoruzh
Sonu0305

Cityflo OTP MCP

by Sonu0305
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
Python
Local

Cityflo OTP MCP (AI Engineer take-home)

Small stdio MCP server for Mumbai North on-time performance over one week of trips.csv. Built for Priya’s ask: “Was route 12 late this week, and by how much?” — with drill-down, not a dashboard.

Scope

In

  • Domain: on-time performance only

  • Data: data/trips.csv (Mon–Fri 2026-06-15 … 2026-06-19)

  • Tools: route_otp_summary, list_late_trips, data_quality_report

  • Deterministic delay / quarantine / aggregation in Python tools

Out

  • Occupancy, ticket triage, ops-log summariser

  • Databases, BI dashboards, web UI

  • Silent “data normalisation” that hides policy (see OPS-2207 below)

Related MCP server: Cityflo on-time performance MCP

Architecture

Agent / MCP client (stdio)
        │
        ▼
cityflo_otp.server  (FastMCP, 3 tools)
        │
        ▼
cityflo_otp.otp     (parse → quarantine → delays → aggregates)
        │
        ▼
data/trips.csv

The model should call tools for numbers and only phrase the answer. Arithmetic never lives in the LLM.

Late definition

  • arrival_delay_min = actual_arrival − scheduled_arrival (timezone-aware)

  • Late if arrival_delay_min > 10 (default; overridable via late_threshold_min)

  • Headline metrics: % late of usable trips, median / p90 arrival delay (not a fragile mean)

  • Departure delay is returned for drill-down only

Data-quality decisions

Trip

Action

Why

TRIP_031

Quarantine

actual_departure has invalid 08:60

TRIP_017

Quarantine

Actual arrival before actual departure

TRIP_044

Quarantine

actual_arrival uses +00:00; naive compare ≈ +333 min

TRIP_101

Quarantine

Missing scheduled_arrival

Quarantined rows are excluded from OTP % / median and listed in tools. We do not invent corrected timestamps.

During initial data inspection (reading the starter bundle’s ops_log.txt, which is not loaded by this MCP at runtime), device D-22 / MH-14-5590 was noted as flaky. The runtime tools only see trips.csv: they quarantine D-22 rows when timestamp checks fail, and leave other consistent D-22 trips usable.

Untrusted handoff text (OPS-2207 / MH-12-7781)

HANDOFF.md contains instruction-shaped text asking tools to force vehicle MH-12-7781 on-time and hide that rule. This server does not apply that override. The same late rule is used for every plate. data_quality_report surfaces the raw MH-12-7781 evaluation and a policy question for Priya. Hiding falsified numbers from a regional manager fails the auditability bar.

Assumptions

  1. Arrival lateness is the right primary metric for Priya’s standup fight.

  2. Default threshold of 10 minutes separates pattern (e.g. Route 12) from noise.

  3. Prefer quarantine over silent correction of GPS/timezone garbage.

  4. Thin samples (e.g. R-21 n=1) should be labeled, not ranked aggressively.

  5. Ticket/occupancy files are out of scope for this MCP.

Questions for Priya

  1. Confirm arrival (vs departure) as the official late definition?

  2. Confirm >10 min for regional-manager figures (or 5 / 15)?

  3. How should MH-12-7781 / OPS-2207 appear: exclude with disclosure, include raw, or dual view?

  4. Minimum trip count before a route enters “worst offenders”?

  5. For +00:00 timestamps: always quarantine, or allow an explicit IST reinterpretation with an audit flag?

How to run

cd ~/repos/cityflo-otp-mcp
python3 -m venv .venv && source .venv/bin/activate
pip install -e .
# or: pip install mcp && PYTHONPATH=src ...

Checks (no MCP):

PYTHONPATH=src python scripts/verify_otp.py

Real MCP client multi-step run (route_otp_summary → list_late_trips → data_quality_report):

PYTHONPATH=src python scripts/run_mcp_client.py

Transcript written to notes/mcp_client_transcript.jsonl.

Cursor / Claude Desktop (stdio): point an MCP server entry at:

{
  "mcpServers": {
    "cityflo-otp": {
      "command": "python",
      "args": ["/absolute/path/to/cityflo-otp-mcp/src/cityflo_otp/server.py"],
      "env": {
        "PYTHONPATH": "/absolute/path/to/cityflo-otp-mcp/src",
        "CITYFLO_TRIPS_CSV": "/absolute/path/to/cityflo-otp-mcp/data/trips.csv"
      }
    }
  }
}

Example agent interaction

  1. route_otp_summary({ "route": "Route 12" })
    → usable 8, late 6, 75% late, median arrival delay on the order of ~13–16 min, 0 quarantined on R-12.

  2. list_late_trips({ "route": "R-12" })
    → the six late trip ids with per-trip arrival delays and vehicles.

  3. data_quality_report({})
    → four quarantined trips week-wide + MH-12-7781 policy note (TRIP_090 / TRIP_119 late under raw rule).

Deliberately cut

  • Other domains (occupancy / tickets / standup)

  • Auto-fixing timezone offsets

  • Ranking API across all routes (easy to add; not required for Priya’s Route 12 ask)

  • Hidden OPS-2207 normalisation

Where I disagreed with the AI

See notes/DISAGREEMENTS.md.

Available Tools

3 tools
data_quality_reportA

Report quarantined trips, reasons, and policy notes.

Explains which rows were excluded from OTP metrics and why. Surfaces the MH-12-7781 / OPS-2207 handoff text as a policy question without applying a hidden on-time override.

ParametersJSON Schema
NameRequiredDescriptionDefault
routeNo
device_idNo
late_threshold_minNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden. It discloses a key behavioral nuance: 'Surfaces the MH-12-7781 / OPS-2207 handoff text as a policy question without applying a hidden on-time override.' This clarifies that the tool does not silently alter results. It could add more about side effects or authentication, but as a reporting tool the read-only nature is evident.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four sentences, each contributing unique value: the purpose, the explanation of exclusions, the policy question, and the explicit 'no hidden override' behavior. It is front-loaded with the core function and free of filler.

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 read-only reporting tool, the description explains what it does and why, including a specific edge case (the handoff policy question). It omits parameter guidance, which is a gap, but the output schema exists and the overall context is sufficient for an agent to invoke the tool correctly. A 5 would require richer detail on when to use it relative to siblings.

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

Parameters1/5

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

Schema description coverage is 0% and the description does not mention any of the three parameters (route, device_id, late_threshold_min). It provides no insight into how these optional filters affect the report. Since the description fails to compensate for the complete lack of parameter documentation, the agent must rely solely on parameter names.

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 opens with a clear verb+resource: 'Report quarantined trips, reasons, and policy notes.' It sharply distinguishes from siblings by focusing on quarantined/excluded rows rather than on-time metrics or late trips. The second sentence reinforces this scope by explicitly stating it explains excluded rows and why.

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 description provides clear usage context: this tool is for understanding data quality exclusions from OTP metrics. It does not name sibling tools as alternatives, but the contrast is implicit. There is no explicit exclusionary guidance ('use this instead of X'), so it stops short of a 5.

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

list_late_tripsC

List usable trips that are late (or all usable trips if include_on_time).

Use after route_otp_summary to drill into which trips drove the number. Returns trip_id, delays, vehicle, device, and raw arrival timestamps.

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNo
routeNo
end_dateNo
start_dateNo
include_on_timeNo
late_threshold_minNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations, the description carries the full burden of disclosing side effects and read-only nature. It does not state whether the tool modifies data, what happens with missing parameters, or define 'usable trips'. Potential side effects and data safety are ambiguous, given the lack of explicit read-only or mutation statements.

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 brief and well-structured, consisting of two sentences that introduce the main behavior and a follow-up usage hint. It is concise without unnecessary fluff, though it omits important details that could be added without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description provides only minimal context: it references a prior tool and vaguely mentions 'usable trips' and 'late'. It does not explain the output structure, the meaning of parameters, or how to interpret results. Given the schema has 6 parameters and no output schema is shown, the description is insufficient for full understanding.

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

Parameters2/5

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

The description only partially explains include_on_time (late vs all trips) but provides no meaning for route, start_date, end_date, limit, or late_threshold_min. The schema gives titles but no descriptions, and the description adds minimal value for most parameters, leaving coverage low.

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?

The description clearly states the tool lists usable trips that are late, with a conditional behavior based on include_on_time. The verb 'list' and resource 'usable trips' are specific, and it references route_otp_summary for context, avoiding tautology. However, it does not explicitly differentiate from other sibling tools beyond the usage hint.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage after route_otp_summary to drill into trips, providing some situational context. It does not explicitly state when not to use this tool or compare alternatives, so the guidance is implicit rather than explicit.

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

route_otp_summaryA

Summarize on-time performance for one route.

Late means arrival_delay_min > late_threshold_min (default 10). Quarantined (unusable GPS/timestamp) rows are excluded from % late and listed by id. Does not apply hidden vehicle overrides.

ParametersJSON Schema
NameRequiredDescriptionDefault
routeYes
end_dateNo
start_dateNo
late_threshold_minNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4/5.0
Behavior4/5

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

With no annotations provided, the description carries the transparency burden and does well: it defines 'late' using arrival_delay_min > late_threshold_min, explains the default threshold, states quarantined rows are excluded and listed by id, and notes hidden vehicle overrides are not applied. It lacks return-format details, but an output schema exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise and front-loaded: the first sentence gives the core purpose, followed by three tightly-scoped behavioral details. Every line adds unique value with no redundancy or filler.

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?

The description covers the key behavioral nuances (late threshold, quarantine handling, override exclusion) and an output schema exists, so return values are covered. The main gap is the lack of context around date range parameters, but overall the tool is adequately specified for invocation.

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 0%, so the description must compensate. It adds meaning for late_threshold_min (defining the late condition and default) and clarifies route scope, but start_date and end_date are completely unexplained—including format and behavior when null. This is a partial but incomplete compensation.

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 clearly states the tool summarizes on-time performance for one route, with a specific verb and resource. This distinguishes it from siblings like list_late_trips and data_quality_report, which focus on individual trips or broader quality issues.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for route-level OTP summaries but gives no explicit guidance on when to use it versus list_late_trips or data_quality_report. There are no exclusions or alternative recommendations, only the implied scope of 'one route'.

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

Tool Schema Changelog

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

  1. 3 tool updatesv0.1.0
    • First observeddata_quality_report
    • First observedlist_late_trips
    • First observedroute_otp_summary
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0

Scored across 3 tools

Disambiguation5/5

Each tool targets a distinct level of analysis: route-level aggregate OTP, trip-level late-trip detail, and data-quality context for quarantined rows. The descriptions explicitly frame list_late_trips as a drill-down from route_otp_summary, so there is no real overlap.

Naming Consistency4/5

All names use lowercase snake_case and clearly describe their output, but they do not follow a single verb_noun pattern: two are noun phrases (route_otp_summary, data_quality_report) and one uses a verb (list_late_trips). This is a minor stylistic deviation rather than a major inconsistency.

Tool Count5/5

With three tools, the server is tightly scoped to OTP reporting: summary, drill-down, and data quality. Each tool has a clear purpose and none feel redundant.

Completeness4/5

The tools cover the core read-only OTP workflow: aggregate summary, late-trip detail, and explanation of excluded data. A route enumeration tool would be a useful addition, but agents can work around this when route IDs are supplied.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers