What can you do with this server?

MCP server providing LLM agents access to the Wheel Fitment API for vehicle wheel and tire compatibility data. * Catalog navigation: list makes, models, years, generations, modifications/trims, and regions. * Vehicle fitment lookup: get OEM wheel/tire specs for a specific vehicle (make/model/year/trim). * Reverse searches: find vehicles compatible with a rim, metric tire size, or high-flotation (LT) tire size. * Fitment checks: verify whether a rim, tire, or HF tire fits a specific vehicle in one call. * Upstep calculator: compute plus/minus sizing alternatives for a wheel/tire combo. * Classified/e-commerce tools: find tires for a rim, vehicles for a rim, vehicles for a tire, vehicles for rim+tire packages, and drill down into trims. * Spec metadata utility: get computed geometry, population stats, and fitment hints for a spec. * Pre-built workflow prompts: vehicle fitment lookup, rim compatibility check, product card generation. * Engine and powertrain data included with modification/search results. * Runs over stdio or as a remote HTTP MCP server; configurable via environment variables.

How do I use wheel-size-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@wheel-size-mcp What are the OEM wheel specs for a 2024 Toyota Camry?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

wheel-size-mcp

by driveate

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

wheel-size-mcp

The official MCP server for the Wheel Fitment API — built and maintained by Wheel-Size.com, the API provider. Gives LLM agents access to vehicle wheel and tire compatibility data.

Ask your AI assistant things like:

"What are the OEM wheel specs for a 2024 Toyota Camry?"
"Which vehicles fit 5x114.3 18x8 ET35 rims?"
"Calculate plus-size options for 225/50R17 on 7Jx17 ET40"
"Generate a product card for this wheel showing all compatible vehicles"

Quick Start

1. Get an API key

2. Set the API key in your shell

Add to your ~/.zshrc (or ~/.bashrc):

export WHEELSIZE_API_KEY="your-api-key-here"

Then reload your shell: source ~/.zshrc

3. Add to your AI client

Choose your client below — each config block is copy-paste ready.

Claude Code

claude mcp add wheel-size-api -- uvx wheel-size-mcp

Or add to .mcp.json in your project root:

{
  "mcpServers": {
    "wheel-size-api": {
      "command": "uvx",
      "args": ["wheel-size-mcp"],
      "env": {
        "WHEELSIZE_API_KEY": "${WHEELSIZE_API_KEY}"
      }
    }
  }
}

Claude Desktop

Add to claude_desktop_config.json (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "wheel-size-api": {
      "command": "uvx",
      "args": ["wheel-size-mcp"],
      "env": {
        "WHEELSIZE_API_KEY": "your-api-key-here"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "wheel-size-api": {
      "command": "uvx",
      "args": ["wheel-size-mcp"],
      "env": {
        "WHEELSIZE_API_KEY": "your-api-key-here"
      }
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "wheel-size-api": {
      "command": "uvx",
      "args": ["wheel-size-mcp"],
      "env": {
        "WHEELSIZE_API_KEY": "your-api-key-here"
      }
    }
  }
}

Zed

Add to your Zed settings.json (Cmd+, → Open Settings):

{
  "context_servers": {
    "wheel-size-api": {
      "command": {
        "path": "uvx",
        "args": ["wheel-size-mcp"],
        "env": {
          "WHEELSIZE_API_KEY": "your-api-key-here"
        }
      }
    }
  }
}

4. Restart your client

The MCP server starts automatically when the client launches.

Related MCP server: perplexity-mcp

Remote Server (Streamable HTTP)

Besides stdio, the server can run as a standalone HTTP service — useful for hosting one shared instance instead of installing Python on every machine:

wheel-size-mcp --transport http --port 8000

The MCP endpoint is served at http://127.0.0.1:8000/mcp/. Point HTTP-capable clients at it:

{
  "mcpServers": {
    "wheel-size-api": {
      "url": "http://127.0.0.1:8000/mcp/"
    }
  }
}

Security: the server binds to 127.0.0.1 by default. The WHEELSIZE_API_KEY lives on the server side, so anyone who can reach the port consumes your API quota — expose it beyond localhost (--host 0.0.0.0) only behind a reverse proxy that handles authentication.

Available Tools (22)

Catalog — vehicle lookup

Tool	Description
`ws_list_makes`	List all manufacturers. Start here.
`ws_list_models`	Models for a make (e.g. Toyota → Camry, Corolla…).
`ws_list_years`	Available years for a make/model.
`ws_list_generations`	Generations for a make/model (alternative to years).
`ws_list_modifications`	Trims for a specific vehicle (e.g. 2.0i, 3.0 V6…).
`ws_list_regions`	Market regions (USDM, EUDM, JDM…).

Search — fitment data

Tool	Description
`ws_search_by_vehicle`	OEM wheel/tire specs for a vehicle. Requires `modification` or `region`, plus `year` or `generation` (unless `modification` is given).
`ws_search_by_rim`	Find vehicles compatible with a rim (exact specs or min/max ranges).
`ws_search_by_tire`	Find vehicles by metric tire size, with speed/load/staggered filters and refinement facets.
`ws_search_by_hf_tire`	Find vehicles by high-flotation (LT) inch size (e.g. 31x10.50R15).
`ws_check_rim_fitment_for_vehicle`	"Will these rims fit my 2020 Civic?" — one-call fitment check.
`ws_check_tire_fitment_for_vehicle`	Same for a metric tire size.
`ws_check_hf_tire_fitment_for_vehicle`	Same for a high-flotation tire size.
`ws_calculate_upsteps`	Plus/minus sizing calculator: asymmetric diameter range (`steps_min`/`steps_max`), per-diameter counts, width/diameter tolerances.

Classified — product cards for e-commerce

Tool	Description
`ws_find_tires_for_rim`	Compatible tire sizes for a rim spec.
`ws_find_vehicles_for_rim`	Vehicles that fit a given rim (geometric 2D filtering).
`ws_find_vehicle_modifications_for_rim`	Drill down into trims for a specific generation.
`ws_find_vehicles_for_tire`	Vehicles that use a specific tire size.
`ws_find_vehicle_modifications_for_tire`	Drill down into trims for a generation that uses the tire.
`ws_find_vehicles_for_package`	Vehicles compatible with a rim + tire combo.
`ws_find_vehicle_modifications_for_package`	Drill down into trims for a rim + tire package.

Utility

Tool	Description
`ws_get_spec_metadata`	Computed geometry, population stats, and intelligence hints for any spec.

Engine and Powertrain Data

Since the API release of 2026-09-15, every modification row returned by ws_list_modifications, ws_search_by_vehicle and the ws_check_*_fitment_for_vehicle tools carries two sibling blocks:

engine — the legacy block {fuel, capacity, type, power, code}, unchanged. engine.power is the headline figure whose source depends on the electrification level (combustion engine for combustion-only cars and mild hybrids, system power for full/plug-in hybrids and EVs). engine.fuel is a display string; group and filter on the powertrain fuel codes instead.
powertrain — combustion_engine, electrification_level, primary_fuel, secondary_fuel, engine_power, system_power, engine_power_secondary, motors. ws_search_by_vehicle returns the block as the API sends it ({kW, PS, hp} power objects, {code, title} fuel refs); the list and fitment-check tools return a compact summary (hp figures, fuel codes, motors [{axle, hp, code}]) to stay within token limits.

Absence words in enums and fuel codes are data, not errors: not_applicable (cannot apply — a BEV has no engine), not_reported (applies, not recorded yet), unknown (neither electrification tier nor fuel recorded). engine_power is the combustion engine alone and is the figure most other vehicle-data providers publish as "power" (on bi-fuel vehicles it may still be the higher of the engine's two ratings while engine_power_secondary is being filled in); system_power is the manufacturer-declared total of the whole powertrain, normally null outside full/plug-in hybrids and EVs with a motor on each axle, and must never be reconstructed by adding engine and motor figures.

The fuel filter of ws_list_modifications takes fuel codes (biodiesel_blend, cng, diesel, e100, electric, ethanol_blend, flex_fuel, h2, hybrid, lpg, petrol, petrol_cng, petrol_lpg); one value matches the legacy engine.fuel, the primary fuel or the secondary fuel, and a real code read from powertrain.primary_fuel / secondary_fuel can be passed straight back. Older spellings such as natural-gas are still accepted; the absence words (not_applicable, not_reported, unknown) and anything else are a 400 error.

MCP Prompts

Pre-built workflow prompts that guide LLM agents through multi-step operations:

Prompt	Description
`vehicle_fitment_lookup`	Complete catalog→search chain for a vehicle description
`rim_compatibility_check`	Metadata→classified flow for rim compatibility
`product_card_generation`	E-commerce product card workflow for wheels/packages

Environment Variables

Variable	Required	Default	Description
`WHEELSIZE_API_KEY`	Yes	—	API key from developer.wheel-size.com
`API_BASE_URL`	No	`https://api.wheel-size.com`	API base URL
`API_HOST_HEADER`	No	—	Host header override (only needed for local Docker routing)
`MCP_TRANSPORT`	No	`stdio`	`stdio` or `http` (same as `--transport`)
`MCP_HOST`	No	`127.0.0.1`	Bind address for http transport (same as `--host`)
`MCP_PORT`	No	`8000`	Port for http transport (same as `--port`)

API Terms of Service

Search tools (ws_search_by_vehicle, ws_search_by_rim, ws_search_by_tire, ws_search_by_hf_tire, the ws_check_*_fitment_for_vehicle checks) and classified tools (ws_find_*) must be initiated by real users per API Terms of Usage. Do not call them in autonomous agent loops or for bulk data generation. Catalog tools, utility tools and ws_calculate_upsteps have no such restriction.

Evals

tests/test_questions.json contains 89 natural-language questions across 12 categories (catalog navigation, fitment lookups, reverse searches, fitment checks, upstep calculation, e-commerce product cards, spec metadata, multi-step workflows, edge cases, tool selection). Each entry includes expected_tools, optional expected_params / expected_params_search, and a free-text tests note.

evals/run_evals.py feeds these questions to a real Claude model with the MCP tools attached, records which tools it calls with which parameters, and grades them against the expectations — catching regressions in tool descriptions and server instructions:

# needs ANTHROPIC_API_KEY and a reachable Wheel Fitment API; costs money
uv sync --group evals
uv run --group evals python evals/run_evals.py                  # all questions
uv run --group evals python evals/run_evals.py -n 10            # smoke run
uv run --group evals python evals/run_evals.py --category catalog_flow
uv run --group evals python evals/run_evals.py --json report.json --min-pass 0.8

Grading is deterministic (no LLM judge): every expected tool must be called (multiset — repeats counted, extra navigation calls allowed), and some single call must carry the expected parameters. Questions without machine-checkable expectations are reported as SKIP and excluded from the pass rate. The default model is pinned (claude-sonnet-5) so pass-rate history stays comparable; override with --model.

The eval runner is not part of pytest or CI — it bills the Anthropic API. The grading logic itself is unit-tested in CI (tests/test_eval_grading.py). ToS note: every question simulates a user-initiated request, so the search-tool restriction is respected.

Development

# Install dev dependencies
uv sync --dev

# Unit tests (no API needed — this is what CI runs)
uv run pytest -m "not integration"

# Full test suite (requires a private API instance, see note below)
uv run pytest

# Lint
uv run ruff check .

# Run server (stdio)
wheel-size-mcp

Note on tests: integration tests run against a private test instance of the API and auto-skip when it is unreachable. External contributors should rely on the unit suite (pytest -m "not integration"), which mocks all HTTP and is what CI runs on every push and pull request.

Available Tools

21 tools

ws_calculate_upstepsSearch (user-initiated only)A

Read-onlyIdempotent

Calculate plus/minus sizing alternatives for a wheel/tire combo.

Given OEM wheel specs, returns safe replacement sizes at different plus/minus levels (e.g. +1, +2 = larger rim with lower-profile tire). Tighten do_max for "without changing the overall diameter" requests.

This is a calculator tool — can be called freely without user initiation.

Inputs: rim_width (required), rim_offset (required), aspect_ratio (required), rim_diameter (required), +4 more. Returns: object

ws_check_hf_tire_fitment_for_vehicleSearch (user-initiated only)A

Read-onlyIdempotent

Check whether a high-flotation (LT) tire size fits a specific vehicle.

Answers "do 31x10.50R15 tires fit my 2000 Chevy Blazer?" in one call: returns the vehicle's modifications (trims) where this HF tire size appears as a documented fitment. An EMPTY result means no documented fitment for that combination. Inch-based HF sizes only — for metric sizes use ws_check_tire_fitment_for_vehicle.

The API has no year parameter, so 'year' is filtered MCP-side against each modification's production range (start_year/end_year); each row echoes its range so near-misses can be explained.

IMPORTANT: This is a Search method — only call when a user explicitly requests a fitment check. Do not call in autonomous loops.

Inputs: make (required), model (required), rim_diameter (required), section_width (required), +6 more. Returns: object

ws_check_rim_fitment_for_vehicleSearch (user-initiated only)A

Read-onlyIdempotent

Check whether specific rims fit a specific vehicle (make + model, optionally year).

Answers "will 5x114.3 17x7 ET40 rims fit my 2020 Honda Civic?" in one call: returns the vehicle's modifications (trims) where this rim appears as a documented fitment. An EMPTY result means no documented fitment for that combination — the rim is likely incompatible or undocumented.

The API has no year parameter, so 'year' is filtered MCP-side against each modification's production range (start_year/end_year); each row echoes its range so near-misses can be explained.

Prefer this over ws_search_by_rim + ws_search_by_vehicle comparison when the user names a specific vehicle.

IMPORTANT: This is a Search method — only call when a user explicitly requests a fitment check. Do not call in autonomous loops.

Inputs: make (required), model (required), rim_width (required), bolt_pattern (required), +8 more. Returns: object

ws_check_tire_fitment_for_vehicleSearch (user-initiated only)A

Read-onlyIdempotent

Check whether a specific tire size fits a specific vehicle (make + model, optionally year).

Answers "do 225/45R17 tires fit my 2020 Honda Civic?" in one call: returns the vehicle's modifications (trims) where this tire size appears as a documented fitment. An EMPTY result means no documented fitment for that combination. Metric sizes only.

The API has no year parameter, so 'year' is filtered MCP-side against each modification's production range (start_year/end_year); each row echoes its range so near-misses can be explained.

Prefer this over ws_search_by_tire + ws_search_by_vehicle comparison when the user names a specific vehicle.

IMPORTANT: This is a Search method — only call when a user explicitly requests a fitment check. Do not call in autonomous loops.

Inputs: make (required), model (required), aspect_ratio (required), rim_diameter (required), +6 more. Returns: object

ws_find_tires_for_rimClassified (user-initiated only)A

Read-onlyIdempotent

Find compatible tire sizes for a given rim specification.

Returns tire sizes (e.g. '245/70R17') with the number of vehicle generations that use each tire on this rim. Set diameter_range to also include tires for ±N inch rim diameters.

Useful for tire product recommendations on wheel product pages.

Inputs: rim_width (required), rim_offset (required), bolt_pattern (required), rim_diameter (required), +12 more. Returns: object

ws_find_vehicle_modifications_for_packageClassified (user-initiated only)A

Read-onlyIdempotent

Drill down into individual trims for a generation from ws_find_vehicles_for_package.

PREREQUISITES — call ws_find_vehicles_for_package first to get:

make, model, generation slugs (from the results)
Use the same rim AND tire parameters and tolerances as the parent search

Returns per-vehicle rows with OEM wheel specs (rim, tire) and fitment deltas vs the searched rim + tire package. Completes the e-commerce chain: package search → generations → specific trims.

Inputs: make (required), model (required), rim_width (required), generation (required), +17 more. Returns: object

ws_find_vehicle_modifications_for_rimClassified (user-initiated only)A

Read-onlyIdempotent

Drill down into individual trims for a generation from ws_find_vehicles_for_rim.

PREREQUISITES — call ws_find_vehicles_for_rim first to get:

make, model, generation slugs (from the results)
Use the same rim parameters and tolerances as the parent search

Returns per-vehicle rows with OEM wheel specs (rim, tire, frontspace, backspace) and fitment deltas vs the searched rim.

Inputs: make (required), model (required), rim_width (required), generation (required), +15 more. Returns: object

ws_find_vehicles_for_packageClassified (user-initiated only)A

Read-onlyIdempotent

Find vehicles compatible with a rim + tire package.

Most precise classified search — considers both physical wheel fitment (backspace) and tire size compatibility simultaneously. Use sort='fitment' to put the closest matches first.

For e-commerce combo/bundle product pages. To drill into a specific generation, use ws_find_vehicle_modifications_for_package.

Inputs: rim_width (required), rim_offset (required), aspect_ratio (required), bolt_pattern (required), +14 more. Returns: object

ws_find_vehicles_for_rimClassified (user-initiated only)A

Read-onlyIdempotent

Find vehicle generations compatible with a given rim via geometric backspace calculations.

Unlike ws_search_by_rim (which does direct 1:1 wheel pair matching), this endpoint uses advanced 2D geometric filtering based on frontspace/backspace calculations to determine physical fitment. This yields broader results — any vehicle where the rim physically fits the wheel housing, even if this exact spec isn't in the OEM database.

Returns make/model/generation with fitment deltas (frontspace/backspace), load capacity, and OEM ratio ranges. Use sort='fitment' to put the closest matches first on product pages.

Note: in some cases spacers or special bolts/nuts may be required. Always verify rims don't interfere with brake calipers or extend beyond the wheel arch.

For e-commerce product pages: "This wheel fits: BMW X5, Audi Q7..." To drill into a specific generation, use ws_find_vehicle_modifications_for_rim.

Inputs: rim_width (required), rim_offset (required), bolt_pattern (required), rim_diameter (required), +12 more. Returns: object

ws_find_vehicles_for_tireClassified (user-initiated only)A

Read-onlyIdempotent

Find vehicle generations that use a specific tire size.

Simplest classified search — matches tire dimensions only, no bolt pattern or backspace filtering.

For e-commerce: "This tire fits: Honda Civic, Toyota Camry..."

Inputs: aspect_ratio (required), rim_diameter (required), section_width (required), limit, +1 more. Returns: object

ws_get_spec_metadataUtility (freely callable)A

Read-onlyIdempotent

Get computed geometry, population stats, and hints for a wheel/tire spec.

Auto-detects mode from parameters:

rim: rim_diameter + rim_width (optionally rim_offset)
tire: section_width [mm] + aspect_ratio + rim_diameter
hf_tire: overall_diameter + section_width [inches] + rim_diameter
package: rim + tire params combined

Use before search or classified calls to understand whether a spec is common or unusual, what tolerances to use, and what to expect.

This is a utility tool — can be called freely without user initiation.

Inputs: cb, rim_width, rim_offset, aspect_ratio, +4 more. Returns: object

ws_list_generationsCatalog (freely callable)A

Read-onlyIdempotent

List generations for a make/model.

Returns generation slugs, names, platform codes, and production spans. Alternative to ws_list_years for models with many generations (e.g. BMW 3 Series). After getting a generation, use ws_list_modifications with the generation slug.

Inputs: make (required), model (required), year, region. Returns: object

ws_list_makesCatalog (freely callable)A

Read-onlyIdempotent

List all vehicle manufacturers (makes).

Returns slugs and names for all car brands in the database.

Common starting point for vehicle fitment lookups, but not the only one — ws_list_years can also be called first (without params) to start from year.

After getting a make slug, use ws_list_models to find models.

Inputs: lang, year, brands, region, +1 more. Returns: object

ws_list_modelsCatalog (freely callable)A

Read-onlyIdempotent

List models for a given make.

Returns model slugs, names, and production year ranges.

Can be filtered by year to narrow results (e.g. "which Toyota models existed in 2020?").

After getting a model slug, use ws_list_years or ws_list_generations next.

Inputs: make (required), lang, year, region. Returns: object

ws_list_modificationsCatalog (freely callable)A

Read-onlyIdempotent

List modifications (trims) for a specific vehicle.

Returns trim names, engine specs, and production years. One of year or generation is required. Filter by power via horsepower (exact ±2.7 hp) or horsepower_min/max (e.g. "trims over 300 hp" → horsepower_min=300). After getting a modification slug, use ws_search_by_vehicle for fitment data.

Inputs: make (required), model (required), fuel, lang, +8 more. Returns: object

ws_list_regionsCatalog (freely callable)A

Read-onlyIdempotent

List all market regions where vehicles are sold.

Returns region slugs and display names (e.g. usdm=USA, eudm=Europe, jdm=Japan). Use region slugs to filter results in other tools.

Inputs: no named parameters. Returns: object

ws_list_yearsCatalog (freely callable)A

Read-onlyIdempotent

List available years, optionally filtered by make and model.

Can be called without params to get all years globally — this makes it an alternative starting point for navigation (Scenario 3: years first). Can also be called with make only to get years for that brand (Scenario 2).

After getting a year, use ws_list_modifications to get trims.

Inputs: make, model, region. Returns: object

ws_search_by_hf_tireSearch (user-initiated only)A

Read-onlyIdempotent

Find vehicles compatible with a high-flotation (LT) tire size.

HF tires use inch-based sizing like 31x10.50R15: overall diameter x section width R rim diameter, all in inches. Common on trucks, SUVs, and offroad vehicles. For metric sizes (e.g. 225/45R17) use ws_search_by_tire instead.

IMPORTANT: This is a Search method — only call when a user explicitly requests a tire compatibility search. Do not call in autonomous loops.

Inputs: rim_diameter (required), section_width (required), overall_diameter (required), mode, +3 more. Returns: object

ws_search_by_rimSearch (user-initiated only)A

Read-onlyIdempotent

Find vehicles compatible with given rim specs via direct 1:1 wheel pair matching.

Uses a direct mapping of existing wheel pair data to vehicle specs — returns only vehicles where this exact rim (or close offset) appears in the database as an OEM or documented fitment. Does NOT calculate whether the rim would physically fit based on wheel housing geometry.

Diameter and width accept either an exact value (rim_diameter, rim_width) or a min/max range pair — e.g. "18-19 inch, ET30-45" → rim_diameter_min=18, rim_diameter_max=19, rim_offset_min=30, rim_offset_max=45. One of exact or range is required per dimension.

IMPORTANT: This is a Search method — only call when a user explicitly requests a rim compatibility search. Do not call in autonomous loops.

For e-commerce product cards, use ws_find_vehicles_for_rim instead — it uses geometric backspace calculations for broader, physics-based matching.

Inputs: bolt_pattern (required), cb, fd, mode, +14 more. Returns: object

ws_search_by_tireSearch (user-initiated only)A

Read-onlyIdempotent

Find vehicles compatible with a given tire size (metric).

The response includes 'facets' (per-value car counts for speed_symbol, load_index, region, fitment — use them to offer refinements) and 'summary' (feature counts like runflat/winter + physical tire data). Echo a facet value back as a filter to drill down.

IMPORTANT: This is a Search method — only call when a user explicitly requests a tire compatibility search. Do not call in autonomous loops.

This tool accepts metric sizes only. For high-flotation (LT) tires with inch-based sizing (e.g. 31x10.50R15), use ws_search_by_hf_tire.

Inputs: aspect_ratio (required), rim_diameter (required), section_width (required), mode, +10 more. Returns: object

ws_search_by_vehicleSearch (user-initiated only)A

Read-onlyIdempotent

Get wheel and tire fitment data for a specific vehicle.

REQUIRED parameter combination:

Either 'modification' OR 'region' (to narrow fitment results)
Either 'year' OR 'generation' (to identify the vehicle) — not required when 'modification' is provided

PREREQUISITES — you MUST have valid slugs before calling:

make: lowercase slug from ws_list_makes (e.g. 'toyota', 'land-rover')
model: lowercase slug from ws_list_models (e.g. 'camry', '3-series')
modification or region: from ws_list_modifications / ws_list_regions
year or generation: from ws_list_years / ws_list_generations (skip when modification is provided)
NOTE: this endpoint accepts only ONE region (unlike other tools)

Do NOT guess these values. Call the prerequisite tools first.

Returns OEM and optional wheel/tire specs including rim diameter, width, offset, bolt pattern, tire sizes, and tire pressure. Each wheel has setup='symmetric' (same front/rear) or 'staggered' (different).

IMPORTANT: This is a Search method — only call when a user explicitly requests fitment information. Do not call in autonomous loops.

Inputs: make (required), model (required), lang, year, +6 more. Returns: object

Tool Schema Changelog

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

Loading tool schema changelog…

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

A4/5.0

Scored 2026-07-31 12:45 across 21 tools

Disambiguation3/5

Several tools have overlapping purposes, such as ws_search_by_rim and ws_find_vehicles_for_rim both finding vehicles for a rim, and ws_search_by_tire and ws_find_vehicles_for_tire both finding vehicles by tire size. The detailed descriptions help differentiate the algorithms, but the three parallel families (search, find, check) could still confuse an agent when choosing the right tool.

Naming Consistency4/5

All tools share a ws_ prefix and follow a verb-noun pattern (list_, search_by_, check_, find_). Minor deviations like calculate_upsteps and get_spec_metadata don't break the overall predictability, and the find_ family's use of '_for_' is consistent.

Tool Count3/5

With 21 tools, the set is on the heavy side. Many are specialized variants (HF tire versions, drill-down tools) that could potentially be consolidated, though each does serve a distinct purpose in the wheel/tire fitment domain.

Completeness4/5

The tool set provides thorough coverage of vehicle navigation, fitment searches, direct check tools for specific vehicles, plus/minus sizing calculations, and e-commerce package finding. The only notable gap is the inability to list all modifications for a model without specifying year or generation, but the navigation workflow handles this via ws_list_years.

Maintenance

ActivitySlowing

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

Subfeed MCP
app.subfeed.mcp
Official MCP server for subfeed.app — the cloud for agents. 15+ tools for AI agents to register, build, and deploy other agents. Zero human required. Start here: subfeed.app/skill.md
Agent Orchestration Cloud Platforms Autonomous Agents
2
https://mcp.subfeed.app/sse
Lovable
dev.lovable
Official MCP server for Lovable, the AI-powered full-stack app builder.
Developer Tools AI & Machine Learning
29
https://mcp.lovable.dev
Intrinio
com.intrinio
Official Intrinio MCP server. US stock prices, options and fundamentals for AI agents.
Finance Data Platforms
1
https://intrinio-mcp.intrinio.com/mcp
agentwork-mcpA
io.github.ferm-ai
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
Agent Orchestration Autonomous Agents App Automation
2
https://mcp.agentwork.so/

Related MCP Servers

Perplexity API MCP Server
Search AI & Machine Learning
Hanato238
A
license
A
quality
C
maintenance
Official MCP server for the Perplexity API Platform, enabling AI assistants to perform real-time web search, reasoning, and deep research using Sonar models.
Updated 6 months ago (2026-05-02 04:41 UTC)
4
55,781 npm
MIT
perplexity-mcp
Search AI & Machine Learning RAG Systems
KaizenRose
A
license
A
quality
D
maintenance
Official MCP server for Perplexity API Platform, enabling AI assistants with real-time web search, reasoning, and research capabilities through Sonar models and the Search API.
Updated 4 months ago (2026-07-12 18:36 UTC)
4
55,781 npm
MIT
boltpatternhq-mcp
Search Databases E-commerce & Retail
double2dev
A
license
A
quality
D
maintenance
Official BoltPatternHQ MCP Server for instant automotive wheel fitment, PCD, center bore, and offset reference data.
Updated 3 months ago (2026-08-17 11:10 UTC)
3
16 npm
MIT
ZapifyAPI MCP Server
Developer Tools Image & Video Processing Networking & Infrastructure
TamirKashy
A
license
B
quality
D
maintenance
Official MCP server for ZapifyAPI, providing AI agents access to 32 tools across image conversion, text analysis, network diagnostics, developer utilities, and data conversion.
Updated 3 months ago (2026-08-03 13:16 UTC)
32
13 npm
MIT

wheel-size-mcp

Quick Start

1. Get an API key

2. Set the API key in your shell

3. Add to your AI client

Claude Code

Claude Desktop

Cursor

Windsurf

Zed

4. Restart your client

Remote Server (Streamable HTTP)

Available Tools (22)

Catalog — vehicle lookup

Search — fitment data

Classified — product cards for e-commerce

Utility

Engine and Powertrain Data

MCP Prompts

Environment Variables

API Terms of Service

Evals

Development

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Perplexity API MCP Server

perplexity-mcp

boltpatternhq-mcp

ZapifyAPI MCP Server