Skip to main content
Glama
deenesjakoruzh
GeiserX

pumperly-mcp

by GeiserX
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Remote

A small bridge that exposes any Pumperly instance as an MCP server, so an AI agent can query fuel prices, find stations, plan routes and geocode places.

Features

  • Five tools: find_nearest_stations, get_stations_in_area, calculate_route, find_route_stations, geocode.

  • Three read-only resources: pumperly://config, pumperly://stats, pumperly://exchange-rates.

  • Two transports: stdio, and HTTP on a single /mcp endpoint.

  • An npm package that downloads the release binary for your platform and runs it over stdio.

  • A Docker image for amd64 and arm64.

  • Works with the public instance at pumperly.com or your own: set PUMPERLY_URL.

  • No API key: it reads the Pumperly API anonymously.

Related MCP server: Foundry MCP Server

Quick start

Add this to your MCP client's configuration (Claude Desktop, Claude Code, Cursor and others read the mcpServers format):

{
  "mcpServers": {
    "pumperly": {
      "command": "npx",
      "args": ["-y", "pumperly-mcp"],
      "env": { "PUMPERLY_URL": "https://pumperly.com" }
    }
  }
}

For the HTTP transport (/mcp on port 8080) run the Docker image; see Getting started.

Documentation

  • Getting started: npm, Docker Compose, building from source, connecting a client

  • Configuration: environment variables

  • Usage: tools, resources, the request flow, testing with the Inspector

  • Related projects: the Pumperly family, other MCP servers, registry listings

License

GPL-3.0-or-later

Available Tools

5 tools
calculate_routeC
Destructive

Calculate a driving route between two points

ParametersJSON Schema
NameRequiredDescriptionDefault
dest_latYesDestination latitude
dest_lonYesDestination longitude
waypointsNoOptional JSON array of waypoints as [[lon,lat],...]
origin_latYesOrigin latitude
origin_lonYesOrigin longitude

TDQS

C2.9/5.0
Behavior2/5

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

The description does not address the destructiveHint annotation, which suggests side effects. 'Calculate' implies a read-only computation, but the tool may modify state. No explanation of what gets destroyed or other behavioral traits is given.

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 a single, clear sentence with no redundant words. It is front-loaded with the core purpose, though it could be expanded to include output hints without losing conciseness.

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 lacks information about the return value (e.g., does it return geometry, duration, distance?) and does not clarify the destructive hint. Given no output schema, these omissions reduce completeness.

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?

All parameters are described in the input schema with clear names and types. The description adds no extra meaning beyond 'driving route', so it meets the baseline for full schema coverage.

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 'Calculate a driving route between two points', specifying the action and resource. It distinguishes from sibling tools like geocode or find_nearest_stations, which are about location data and stations rather than route calculation.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. For instance, it could mention that for station-specific queries, sibling tools like find_route_stations are appropriate, but it does not.

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

find_nearest_stationsC
Destructive

Find fuel stations nearest to a coordinate

ParametersJSON Schema
NameRequiredDescriptionDefault
latYesLatitude of the search centre
lonYesLongitude of the search centre
fuelYesFuel type code (e.g. B7, E5, E10, E85, LPG, CNG, LNG, EV)
limitNoMaximum number of results (default 5)
radius_kmNoSearch radius in kilometres (default 10)

TDQS

C2.7/5.0
Behavior1/5

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

Annotation contradiction: description says 'find' (non-destructive) but annotations have destructiveHint=true, implying potential data modification. No additional behavioral context provided.

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?

Single sentence with no wasted words, front-loads the essential action.

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?

No output schema, so description should hint at return type or behavior. Fails to mention destructive nature suggested by annotations, leaving agent uncertain about side effects.

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% with descriptions for all parameters. Description adds no extra meaning beyond schema, so baseline 3 is appropriate.

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?

Description clearly states the purpose (find fuel stations nearest to coordinate), but doesn't explicitly differentiate from sibling tool 'get_stations_in_area' which likely also returns stations by area.

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

Usage Guidelines2/5

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

No guidance on when to use this tool vs alternatives like get_stations_in_area or find_route_stations. Context signals show sibling tools but description offers no usage advice.

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

find_route_stationsC
Destructive

Find fuel stations along a route corridor

ParametersJSON Schema
NameRequiredDescriptionDefault
fuelYesFuel type code (e.g. B7, E5, E10, E85, LPG, CNG, LNG, EV)
geometryYesGeoJSON LineString as a JSON string, e.g. {"type":"LineString","coordinates":[[lon,lat],...]}
corridor_kmNoCorridor width in kilometres (default 5)

TDQS

C2.9/5.0
Behavior1/5

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

The description claims a read operation ('Find') while annotations set destructiveHint=true, suggesting data modification. This contradiction is not addressed. No additional behavioral context beyond the purpose is provided.

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?

Single sentence with no wasted words. However, it is too brief given the contradiction and lack of usage guidance, slightly reducing effectiveness.

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?

Despite low complexity, the description is incomplete: it does not explain the output, does not resolve the annotation contradiction, and assumes the agent knows what 'route corridor' means. A more complete description would include output format and usage notes.

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?

Input schema has 100% coverage with descriptions for each parameter (corridor_km, fuel, geometry). The tool description does not add new semantic details beyond what the schema provides, so a baseline of 3 is appropriate.

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 'Find fuel stations along a route corridor' clearly states the verb and resource, and implies the corridor context. It distinguishes from siblings like 'find_nearest_stations' (point-based) and 'get_stations_in_area' (area-based), though not explicitly.

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?

No explicit guidance on when to use this tool vs alternatives like find_nearest_stations or get_stations_in_area. Usage is implied by the description and the required geometry parameter (GeoJSON LineString), but no exclusion or prerequisite details.

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

geocodeB
Destructive

Search for a location by name (geocoding)

ParametersJSON Schema
NameRequiredDescriptionDefault
latNoOptional latitude for geographic biasing
lonNoOptional longitude for geographic biasing
queryYesSearch query (e.g. city name, address, POI)

TDQS

B3.3/5.0
Behavior1/5

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

Description says 'search' (read-like), but annotations set destructiveHint=true, suggesting modification. This contradiction confuses agent behavior. Description adds no further behavioral context.

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?

Single sentence is concise and front-loaded, but lacks structure (e.g., no sections) and provides minimal detail for a 3-param tool.

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?

With contradictory annotations and no output schema, description misses essential return format info and fails to disclose behavioral implications, leaving the agent underinformed.

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 has 100% description coverage, but description adds geocoding context ('by name') beyond param details. This clarifies the tool's purpose and differentiates forward vs reverse geocoding.

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?

Description clearly states verb 'search' and resource 'location by name' (geocoding), distinguishing it from sibling tools like calculate_route and find_nearest_stations.

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?

Description implies geocoding use via 'search by name' but provides no explicit when-to-use vs alternatives, no exclusions, and no context-sensitive guidance.

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

get_stations_in_areaB
Destructive

Get fuel stations within a bounding box

ParametersJSON Schema
NameRequiredDescriptionDefault
bboxYesBounding box as "minLon,minLat,maxLon,maxLat"
fuelYesFuel type code (e.g. B7, E5, E10, E85, LPG, CNG, LNG, EV)

TDQS

B3.1/5.0
Behavior1/5

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

The description says 'Get' implying a read-only operation, but annotations indicate readOnlyHint=false and destructiveHint=true, suggesting potential side effects or data destruction. This is a direct contradiction, and the description fails to disclose any behavioral traits beyond the basic action.

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 a single, concise sentence with no wasted words. However, it could be slightly more informative without losing conciseness, e.g., by noting the return type or limitations.

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?

Given the potential for destructive behavior (per annotations), the lack of explanation about side effects, return format, or operational limits makes the description incomplete. The minimal information does not compensate for the complexity implied by annotations.

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% for both parameters (bbox format and fuel type codes). The description adds no extra meaning beyond what the schema already provides, so a baseline score of 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 'Get fuel stations within a bounding box' clearly states the verb (Get), resource (fuel stations), and scope (bounding box). It effectively differentiates from sibling tools like find_nearest_stations (point-based) and find_route_stations (route-based).

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 when a bounding box is available, but it does not explicitly state when to use this tool over alternatives like find_nearest_stations or calculate_route. No guidance on prerequisites or limitations is provided.

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. 5 tool updatesv0.1.0
    • First observedcalculate_route
    • First observedfind_nearest_stations
    • First observedfind_route_stations
    • First observedgeocode
    • First observedget_stations_in_area
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: route calculation, finding stations by proximity, along a route, geocoding, and area-based search. No overlap in functionality.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case (e.g., calculate_route, find_nearest_stations). Even 'geocode' is a conventional single word verb. No mixing of styles.

Tool Count5/5

With 5 tools, the set is well-scoped for a fuel station and routing service. Each tool provides essential functionality without redundancy or unnecessary complexity.

Completeness4/5

Core operations are covered: geocoding, route calculation, and three ways to find stations. Minor gaps like station details (prices, amenities) or reverse geocoding are not critical for the primary use case.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers