Search vehicles across dealerships, compare prices, check safety ratings and recalls, and get deal scores.
Connects to OpenDealer's automotive inventory database covering dealerships, vehicles, pricing, and market data. Muse can search for vehicles by make/model/location, get detailed specs and safety information, check NHTSA recalls, compare prices across the market, and provide deal scoring to help with purchase decisions.
Try asking Muse: "Find me a used Honda Civic under $25,000 within 50 miles of my zip code and tell me if it's a good deal."
Source: Found in the official MCP Registry (app.opendealer/mcp) · First listed September 24, 2026
Each bar is one check, every 15 minutes. Green means it answered. Last checked 2 h ago.
What Muse can see: You sign in to your own account with it, so Muse can reach what that account allows. Read what it asks for before you agree.
Before it acts: Read what Muse plans to do before you approve it, and remove the app from Muse when you stop using it.
musedirectory.ai is not part of Meta. More about how Muse handles your information
Not in Muse's Connectors list yet, but Muse can still use it. Copy the request below and paste it into Muse. Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.
https://mcp.opendealer.app/rpcNot in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
OpenDealer is a remote MCP server, so any assistant that can add a custom connector by link can use it. Same link, same tools.
In ChatGPT, open Settings, then Connectors (called Apps & Connectors on some accounts).
Under Advanced settings, switch on Developer mode. That is what lets you add a connector by link.
Choose Create, give it a name, paste the link as the MCP server URL, and save. If it needs a sign-in, ChatGPT asks for it here.
Start a chat, open the tools menu, pick the connector, and ask. ChatGPT asks before it runs a tool the first time.
Custom connectors need a paid ChatGPT plan, and on Team, Enterprise and Edu accounts only an admin can add them. Our "Working" label means the server answered us; it cannot tell whether your plan lets you add it. All connectors that work in ChatGPT
In Claude, open Settings, then Connectors.
Choose Add custom connector, give it a name, and paste the link.
If it needs a sign-in, Claude sends you to it. Then turn the connector on in a chat from the tools menu and ask.
Custom connectors are available on paid Claude plans; on Team and Enterprise accounts an admin may need to add them. Our "Working" label means the server answered us; it cannot tell whether your plan lets you add it. All connectors that work in Claude
https://mcp.opendealer.app/rpcResponse time at the last check: 143ms. Worked in 99.1% of checks over 30 days.
Screened, no issues found
Screening looks for known threats and hidden instructions at the time of the check, and runs again weekly and whenever the tool list changes. It cannot see the server's code, so only connect what you need and review what Muse asks to do. How screening works.
check_recallsOpen safety recalls for a listing. Cars use NHTSA at year, make, and model grain; a campaign may not apply to every VIN. Off-road uses CPSC and the listing id on GET /v2/listings/{listingId}/recalls. The response names the source and one outcome: confirmed for this VIN, possible compare_marketPricing comparison across market segments. Input is cohortKeys (at most ten) or a make, with an optional model.compare_modelsSide-by-side comparison of two to four vehicle models. Input is composite make-model slugs such as honda-civic. The payload includes dimension deltas and the research record for each model. The link field on each model is url.compare_vehiclesSide-by-side comparison of two to five listings, with specs, price context, and per-vehicle cite fields. Each vehicle row includes cite.vin and cite.url. cite.url is that listing's page on its own host.dealer_inventoryInventory for one dealer slug. Supports the same vehicle filters as the listings route. Listings with zero photos are omitted. The page size follows the tool limit, which is at most 100. Each vehicle row includes cite.vin and cite.url. cite.url is that listing's page on its own hdealers_nearDealerships near a search area the shopper states: zip and radius, city and state, or county and state. Each row includes name, address, phone, website, slug, distance, inventory count, and hours when the feed has them. The public list has no internal dealer UUIDs. total is the ffilter_vehiclesStructured inventory lookup. Exact filters on the same live index as search_vehicles, with totals for those filters. Listings with zero photos are omitted. fuelType is the canonical label. transmission and drivetrain match every indexed raw string in that bucket (automatic includget_deal_scoreDeal score and market context for one listing: a 1 to 100 score with a rating, price versus the market average, days on lot, price history, and similar vehicles in the market.get_dealerDealership record for one slug, or a display name that matches one rooftop. A shared display name returns candidate slugs. Fields include name, address, phone, website, Google rating, review count, hours, business status, inventory count, and profile links. URL fields on the recoget_market_overviewMarket statistics for one vertical. inventory.totalVehicles is searchable priced listings on the live index. inventory.activeDealers is active dealers with at least one priced vehicle, the same population as dealers_near. marketData holds year-make-model cohort medians and sampleget_market_segmentPricing statistics for one market segment: average, median, minimum, and maximum price, percentiles, average mileage, average days on lot, and certified versus non-certified pricing when both exist.get_market_trendsPrice timeline for one market segment: median and average prices and days on lot.get_market_velocityDays-on-lot velocity by segment, fastest and slowest. The API paginates this list. Optional make and condition filters.get_safety_ratingNHTSA 5-Star Safety Ratings for a year, make, and model. Includes overall and crash-test stars when published, rollover rating, and NHTSA-evaluated ADAS availability. A missing rating is reported as missing. The NHTSA link field is sourceUrl.get_similar_vehiclesOn-lot vehicles similar to one VIN, using the same make and model keyword comparison as the shop listing rail. The API caps the list. Each vehicle row includes cite.vin and cite.url. cite.url is that listing's page on its own host.get_suggested_ratesNational average suggested auto loan APRs for cars. This is not a credit offer. Other verticals return a not-available result until that vertical has a rate source. Optional filters are condition, termMonths from 36 to 84, and creditTier.get_vehicleListing details for one listingId or VIN. A VIN listed at more than one rooftop returns a vehicle_listings envelope of every listing, with no single price, seller, or url. listingId selects one store. The payload is Schema.org Vehicle data: specifications, images, price, availabiget_vehicle_historyOpenDealer listing history for a VIN or listing id: price changes, days on lot, and status, including vehicles that left a dealer feed. Fields include chronological price history, days-on-market signals, badges, and active or no-longer-listed status when known. A sold vehicle hasget_vehicle_rankingsData-driven vehicle rankings. With no category, the response lists ranking categories. A category slug returns that scored ranking. Scores use NHTSA ratings, EPA fuel economy, manufacturer pricing, and live availability. The link field is url.list_facetsCanonical filter tokens and counts from the live search index: make, bodyType, fuelType, transmission, drivetrain, and price and year ranges. Counts match filter_vehicles totals for the same make, condition, and location. Optional make, condition, certified, near, and radius scoplist_market_segmentsOne page of market segments with cohortKey, median price, and sample size. The API paginates this list at a maximum of 100.list_research_makesResearch catalog of vehicle makes, with model counts and live inventory counts. The API returns one page, capped by limit.list_research_modelsModels for one make from the research catalog, with MSRP and body summaries.list_verticalsLive shopper verticals: key, label, host, identifier kind, example classes, tool families, and whether the vertical is public. Reserved hosts are omitted. An absent vertical on other tools covers every public vertical.research_modelResearch record for one vehicle model: trims, MSRPs, engine and body specs, EPA fuel economy, NHTSA ratings, open recall count, and the live inventory count and price range. The link field is url.search_vehiclesForgiving vehicle search over the live index. Accepts a natural-language query, a 17-character VIN, or structured filters. Listings with zero photos are omitted. Location is a search area the shopper states: zip and radius, near, city and state, or county and state. Each vehicle https://mcp.opendealer.app/rpcNot in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use OpenDealer to help me. It is a free service with an MCP server at https://mcp.opendealer.app/rpc. It needs an API key from OpenDealer; ask me to enter it through your secure credential prompt. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.
At the last check (November 13, 2026, 12:30 UTC) the endpoint was working, answering in 143ms. Over the last 7 days it answered 100% of health checks. It is checked every 15 minutes.
It was screened on September 24, 2026 with the result "screened, no issues found". Screening checks the domain against threat feeds and reads the tools for hidden instructions and requests for passwords or card numbers. It cannot see the server's code, so grant only the access you need.
It exposes 26 tools, including check_recalls, compare_market, compare_models, compare_vehicles. For example, you could ask Muse: "Find me a used Honda Civic under $25,000 within 50 miles of my zip code and tell me if it's a good deal."
This listing was added from public sources (Found in the official MCP Registry (app.opendealer/mcp)). If you build OpenDealer, claim it to correct the details and get your badge.
Paste this on your site or README. It always shows the latest check.
<a href="https://musedirectory.ai/connector/opendealer"><img src="https://musedirectory.ai/badge/opendealer.svg" alt="OpenDealer on musedirectory.ai" width="236" height="40"></a>