# SearchApi MCP MCP Server

> **SearchApi MCP MCP Server** is a hosted, multitenant Model Context Protocol (MCP) server run by **MewCP** (https://mewcp.com), giving AI agents managed access to SearchApi MCP.
>
> MewCP takes care of all MCP infrastructure for you — credential storage, OAuth flows,
> token refresh, and production-grade auto-scaling — so your AI agents can connect to
> third-party services and run freely without you managing any MCP server yourself.
>
> Server page:  https://mewcp.com/mcp/searchapi-mcp
> MewCP docs:   https://docs.mewcp.com
> Full catalog: https://mewcp.com/llms.txt

---

## About

SearchApi provides real-time search and structured data retrieval across Google, Bing, Google Maps, Google Flights, Amazon, eBay, YouTube, and other platforms. Search web pages, news, products, businesses, travel options, social media content, and app store listings through a unified MCP integration.

---

## Details

- Server ID: `searchapi-mcp`
- Version: 1.1.0
- Tools: 107
- Authentication: OAuth, managed by MewCP
- Transport: http

---

## Access

The gateway URL below serves your **entire MewCP toolset**, not this server on its
own. Pasting a config snippet is not enough — SearchApi MCP has to be in the toolset
first. In order:

1. Add SearchApi MCP to your toolset at https://mewcp.com/mcp/searchapi-mcp
2. Connect your SearchApi MCP account (OAuth); MewCP stores the credential and attaches it to each call
3. Copy your MewCP API key from the dashboard (Developer)
4. Configure your client with the snippet for it below

Once connected, an agent does **not** see this server's tools as top-level tools.
It sees four meta-tools and reaches everything through them:

- `search(query)` — find tools by keyword across the toolset
- `get_schema(tools)` — full description and arguments for the tools you picked
- `list_accounts(provider)` — only when one app has several connected accounts
- `call_tool(server_maskedId, tool_name, args)` — execute

So the list below is what `search` can return for this server, not a set of
callable tool names on their own.

---

## Tools (107)

Descriptions are truncated to 160 characters; call `get_schema`
for the full text and the argument schema. Where a tool is annotated, its type
is shown — treat `destructive` as irreversible.

- `airbnb_experience_details` _(read)_ — Get detailed information about a specific Airbnb experience by its experience ID. Returns top-level keys: `experience` (title, description, category, rating,…
- `airbnb_experiences_search` _(read)_ — Search Airbnb Experiences — activities, tours, and workshops hosted by locals. Returns an `experiences` array (main paginated results) and `sections` (curated…
- `airbnb_property_availability_calendar` _(read)_ — Day-by-day availability calendar for a specific Airbnb property. Returns up to 12 months of data with availability, check-in/out windows, and minimum / maximum…
- `airbnb_property_reviews` _(read)_ — Reviews for a specific Airbnb property. Returns review text, rating (1-5), date, and reviewer info. Supports filtering by text and sorting. Get `property_id`…
- `airbnb_property` _(read)_ — Get detailed information about a specific Airbnb property. Returns description, amenities, host info, photos, reviews, and pricing breakdown. **Two ways to…
- `airbnb_search` _(read)_ — Search for short-term rental properties on Airbnb. Returns listings with pricing, ratings, photos, and availability. Requires a search location or query in `q`…
- `amazon_categories` _(read)_ — Browse Amazon's category hierarchy (browse nodes). Three modes: - **List roots**: call with no category_id or q to list root categories for the selected domain…
- `amazon_offers` _(read)_ — Get the list of seller offers (the "Other sellers on Amazon" / All Offers Display) for an Amazon product by ASIN, including price, condition, seller, and…
- `amazon_product` _(read)_ — Get detailed product information from Amazon by ASIN. Returns product details including title, price, description, specifications, images, and ratings. Use the…
- `amazon_search` _(read)_ — Search for products on Amazon. Returns product listings with prices, ratings, and availability. Use amazon_product tool with the ASIN from results to get…
- `apple_app_details` _(read)_ — Get detailed information for an iOS or macOS app on the Apple App Store. Returns app name, description, ratings, reviews, screenshots, version history, and…
- `apple_appstore_search` _(read)_ — Search for iOS and macOS apps on the Apple App Store. Returns app listings with titles, ratings, prices, and developer info. Use apple_app_details with a…
- `apple_appstore_top_grossing` _(read)_ — Get the Apple App Store top grossing chart — apps ranked by revenue for a storefront, category, and device. Returns each app's rank position, id, title,…
- `apple_maps_guide` _(read)_ — Fetch a full Apple Maps editorial guide (curated place collection): the guide's title, description, and publisher, plus every member place with full details…
- `apple_maps_place_details` _(read)_ — Look up full Apple Maps details for one or more places in a single request: ratings, reviews, opening hours, current open state, amenities, contact info,…
- `apple_maps_search` _(read)_ — Search for local businesses and places on Apple Maps. Returns up to 10 local results with names, addresses, GPS coordinates, ratings, reviews, hours, phone…
- `autoscout24_listing` _(read)_ — Get the complete detail sheet for a single AutoScout24 car listing: full vehicle specification, mileage and registration, price with market context, CO2 and…
- `autoscout24` _(read)_ — Search car listings on AutoScout24, Europe's largest online car marketplace, across eight national marketplaces. Returns listings with price, mileage, first…
- `bestbuy_product` _(read)_ — Get full BestBuy product details by SKU. Returns title, brand, model number, full specifications grouped by section, pricing with member savings and…
- `bestbuy_search` _(read)_ — Search for products on BestBuy. Returns product listings with prices, ratings, reviews, images, and category taxonomy. Supports sorting, category browsing, and…
- `bing_news` _(read)_ — Search for news articles using Bing News. Returns news results with titles, sources, thumbnails, and publication dates. Good for finding recent news coverage…
- `bing_product` _(read)_ — Get detailed product information from Bing Shopping. Requires a product_token obtained from bing_shopping search results. Returns the product page with offers…
- `bing_search` _(read)_ — Search the web using Bing. Returns organic results, related searches and more. Alternative to Google for web search with different ranking algorithms and…
- `bing_shopping` _(read)_ — Search for products on Bing Shopping. Returns shopping results with titles, prices, sellers, ratings, and product_tokens. Use the product_token from a result…
- `booking_autocomplete` _(read)_ — Resolve a typed destination string to Booking.com's own identifiers, the entry point of the Booking chain. Returns suggestions with `title`, `label`,…
- `booking_property` _(read)_ — Full details for one Booking.com property: description, address, facilities, photos, house rules, review scores and nearby places, plus the bookable rooms with…
- `booking` _(read)_ — Search Booking.com for hotels, apartments, hostels and other stays. Returns properties with price, rating, review count, room type and distance from centre,…
- `chatgpt` _(read)_ — Ask OpenAI's ChatGPT a question and get its synthesized text answer. Best for explanations, summaries, reasoning, and drafting rather than raw search-result…
- `duckduckgo_search_light` _(read)_ — Search the web using DuckDuckGo. Returns organic results. Privacy-focused alternative to Google with unbiased results and no tracking.
- `ebay_product` _(read)_ — Get detailed information about a specific eBay listing. Requires either an item_id or product_id obtained from ebay_search results. Returns full listing…
- `ebay_search` _(read)_ — Search for listings on eBay. Returns product listings with prices, conditions, shipping info, and seller details. Use ebay_product with item_id or product_id…
- `ebay_shipping_calculator` _(read)_ — Quote the postage a seller would pay to ship a package on eBay, from eBay's shipping rate calculator. Returns every service eBay quotes (carrier,…
- `facebook_business_page_reviews` _(read)_ — Fetch public reviews from a Facebook business page. Returns the page itself (name, link, follower counts, photos, the percentage of visitors who recommend it,…
- `facebook_business_page` _(read)_ — Fetch public business page information from Facebook. Returns page details including name, category, address, phone, website, ratings, reviews, followers, and…
- `gemini` _(read)_ — Get Google Gemini's AI-generated answer to a question. Returns AI-synthesized text with cited grounding source reference links.
- `github_search` _(read)_ — Search GitHub. GitHub's qualifiers work inside q (e.g. `language:ruby stars:>1000`, `org:rails is:open`, `user:torvalds`). Required: q. Pick the vertical with…
- `google_ads_advertiser_search` _(read)_ — Search for advertisers by name in Google's Ads Transparency Center. Returns advertiser IDs and domains that you can use with google_ads_search to find their…
- `google_ads_search` _(read)_ — Search for ads in Google's Ads Transparency Center by advertiser ID or domain. Returns ad creatives, formats, and targeting information. You must provide…
- `google_ai_mode` _(read)_ — Get Google's AI-generated responses (AI Overviews) with source citations and reference links. Two ways to call: - Text search — requires q. - Image analysis —…
- `google_flights_calendar_one_way` _(read)_ — Get a price calendar showing the cheapest one-way flight price for each day in a date range. Returns a list of dates with prices - useful for finding the…
- `google_flights_calendar_round_trip` _(read)_ — Get a price calendar showing the cheapest round-trip flight prices for combinations of outbound and return dates. Returns a grid of date pairs with prices -…
- `google_flights_deals` _(read)_ — Discover cheap round-trip flight deals from an origin, ranked by savings vs the typical price. Use for budget-friendly destination ideas, not a specific route.…
- `google_flights_location_search` _(read)_ — Search for airports and cities to get their identifiers for Google Flights tools. Returns: - IATA airport codes (e.g., 'JFK') for specific airports - kgmid…
- `google_flights_one_way` _(read)_ — Search one-way Google Flights with airline, time, price, and booking details. Required on every call, including token follow-ups: departure_id, arrival_id,…
- `google_flights_round_trip` _(read)_ — Search round-trip Google Flights with airline, time, price, and booking details. Required on every call, including token follow-ups: departure_id, arrival_id,…
- `google_hotels_autocomplete` _(read)_ — Autocomplete destinations and properties for hotel searches. Use to disambiguate user-typed location strings before calling `google_hotels`. Returns…
- `google_hotels_property` _(read)_ — Detailed information about a specific hotel or vacation rental from Google Hotels — name, address, amenities, photos, reviews, ratings, and pricing for the…
- `google_hotels` _(read)_ — Search for hotels using Google Hotels. Provides pricing, ratings, amenities, and availability for hotels, resorts, inns, motels, and other traditional…
- `google_images_light` _(read)_ — Search Google Images for photos and visual content. Returns image results with thumbnails, source pages, and original image URLs. Useful for finding reference…
- `google_jobs` _(read)_ — Search for job listings on Google Jobs. Returns job postings with titles, company names, locations, descriptions, and apply links aggregated from multiple job…
- `google_lens` _(read)_ — Analyze images using Google Lens. Upload an image URL to get visual matches, product identification, text extraction, and exact match detection. Supports…
- `google_local` _(read)_ — Search local businesses, restaurants, and services via Google Search's local pack. Each result includes `place_id`, `data_id`, and `kgmid` in the same format…
- `google_maps_directions_search_along_route` _(read)_ — Find places (gas stations, restaurants, hotels, etc.) along a Google Maps driving route. Two-step workflow: 1. Call the `google_maps_directions` tool with the…
- `google_maps_directions` _(read)_ — Get directions between two locations on Google Maps for driving, walking, cycling, or flying (use `google_maps_directions_transit` for public-transit routing).…
- `google_maps_directions_transit` _(read)_ — Get public-transit directions (bus, subway, train, tram/light rail) between two locations on Google Maps. Returns route options with distance, duration,…
- `google_maps_photos` _(read)_ — Get photos for a specific place on Google Maps. Requires `data_id` or `place_id` from `google_maps_search`, `google_maps_place`, or `google_local` results — at…
- `google_maps_place` _(read)_ — Get detailed information about a specific place from Google Maps. Requires a data_id or place_id obtained from google_maps_search results. At least one of…
- `google_maps_reviews` _(read)_ — Get reviews for a specific place on Google Maps. Requires `data_id` or `place_id` from `google_maps_search`, `google_maps_place`, or `google_local` results —…
- `google_maps_search` _(read)_ — Search for local businesses and places on Google Maps. Returns local results with names, addresses, ratings, reviews, and contact information. Use the data_id…
- `google_news_light` _(read)_ — Search Google News for recent articles and headlines. Returns news results with title, source, date, snippet, and thumbnail. Supports time filtering and…
- `google_patents_search` _(read)_ — Search Google Patents for patent documents and scholarly articles. Returns patent titles, IDs, inventors, assignees, filing dates, and abstracts.
- `google_place` _(read)_ — Google Knowledge Graph entity card for a place, organization, or thing. Distinct from `google_maps_place` — uses `kgmid` (e.g., '/m/02j81' or '/g/11b_3cn7rv')…
- `google_play_details` _(read)_ — Get detailed information for an Android app on the Google Play Store. Returns app name, description, ratings, reviews, screenshots, version history, and…
- `google_play_search` _(read)_ — Search for Android apps on the Google Play Store. Returns app listings with titles, ratings, prices, and developer info. Use google_play_details with a…
- `google_product` _(read)_ — Get detailed product information from Google Shopping. Requires a product_token obtained from google_shopping_search results. Returns comprehensive product…
- `google_rank_tracking` _(read)_ — Get Google organic search results for SEO rank tracking. Returns up to 100 results per request with position, title, URL, and snippet. Ideal for monitoring…
- `google_reverse_image` _(read)_ — Search Google with an image instead of a text query. Returns the web results Google shows for the image (pages about what it depicts), visual matches (visually…
- `google_scholar_case_law` _(read)_ — Get the full opinion and citation graph of a US federal or state court case on Google Scholar. Required: caselaw_id as a string of digits. To search by legal…
- `google_scholar_cases` _(read)_ — Search US federal and state court opinions (case law) on Google Scholar. Returns matching cases, each with a `caselaw_id`, the case `title`, and a…
- `google_scholar_courts` _(read)_ — Look up Google Scholar case-law `court` identifiers to use with google_scholar_cases. Search by keyword (state, circuit, district, "supreme court",…
- `google_scholar` _(read)_ — Search Google Scholar for academic papers, citations, and scholarly articles. Returns results with titles, authors, publication info, citation counts, and…
- `google_search_light` _(read)_ — Perform fast Google web searches. Returns organic search results, related searches, and pagination. Suitable for quick information retrieval when advanced…
- `google_shopping_search` _(read)_ — Search for products on Google Shopping. Returns product listings with prices, sellers, ratings, and comparison shopping data. Use google_product tool with…
- `google_travel_explore_destination` _(read)_ — Drill into a specific destination from `google_travel_explore` results — returns detailed flight options for that destination. Get `arrival_id` from…
- `google_travel_explore` _(read)_ — Discover flight destinations from a departure point — use when the user has a departure but no specific destination. Returns destinations with `name`, `kgmid`,…
- `google_vacation_rentals` _(read)_ — Search for vacation rentals using Google Hotels. Provides pricing, ratings, amenities, and availability for vacation rental properties like apartments, villas,…
- `instagram_comments` _(read)_ — Fetch the comments on a public Instagram post. The first page also returns the post itself (caption, type, likes, author, full-size media links, carousel…
- `instagram_post` _(read)_ — Fetch a public Instagram photo, video, reel, or carousel from its shortcode. Returns the caption, author profile with avatar, like and comment counts,…
- `instagram_profile` _(read)_ — Fetch public profile information from Instagram. Returns bio, follower/following counts, post count, list of posts, verification status, business category, and…
- `linkedin_ads_search` _(read)_ — Search for ads in LinkedIn's Ad Library. Returns sponsored content, ads, and campaigns. At least one parameter is required. You can combine: q (keyword),…
- `meta_ads_page_search` _(read)_ — Search for advertiser pages and locations in Meta's Ad Library (Facebook, Instagram). Returns page IDs, location IDs, and keyword suggestions matching your…
- `meta_ads_search` _(read)_ — Search for ads in Meta's Ad Library (Facebook, Instagram). Returns ad creatives, page info, and engagement data. At least one of `q` or `page_id` is required.…
- `perplexity` _(read)_ — Get Perplexity's AI-generated answer to a question. Returns AI-synthesized text with cited source reference links.
- `tiktok_ads_search` _(read)_ — Search for ads in TikTok's Ad Library. Returns video, image and carousel ads with advertiser info and estimated audience. `format` is `video` or `image`;…
- `tiktok_advertiser_search` _(read)_ — Search for advertisers by name in TikTok's Ad Library. Returns advertiser suggestions and keyword matches. Use with tiktok_ads_search to find ads from a…
- `tiktok_autocomplete` _(read)_ — Autocomplete a TikTok search query. Returns the suggestions TikTok's search box shows for a typed prefix as `suggestions`, in TikTok's ranking order, each with…
- `tiktok_profile` _(read)_ — Fetch public profile information from TikTok. Returns bio, follower/following counts, total likes (hearts), video count, verification status, and bio links.
- `tiktok_profile_videos` _(read)_ — Fetch a public TikTok creator's video feed (their posts), paginated. Returns each video's caption, publish time, duration, dimensions, thumbnails,…
- `tiktok_search` _(read)_ — Search TikTok by keyword and get the matching profiles, videos, and photos. Each video and photo returns its caption, publish time, engagement counts (views,…
- `tiktok_transcript` _(read)_ — Extract the transcript (captions) from a single TikTok video. Identify the video by url, or by video_id together with username; exactly one of these two forms…
- `tiktok_video` _(read)_ — Fetch structured data for a single public TikTok video (or photo carousel). Identify the post by url, or by video_id together with username; exactly one of…
- `tripadvisor_forums_search` _(read)_ — Search TripAdvisor forum threads (community Q&A and discussions). Returns `forum_results` with thread `forum_id`, title, and link. For places (hotels,…
- `tripadvisor_place` _(read)_ — Detailed information about a specific TripAdvisor place (hotel, restaurant, attraction, attraction product, destination, or airline). Returns description,…
- `tripadvisor_reviews` _(read)_ — Reviews for a specific TripAdvisor place (hotel, restaurant, attraction, attraction product, geo). Returns review text, rating, date, user info, and photos.…
- `tripadvisor` _(read)_ — Search TripAdvisor for places — hotels, restaurants, attractions, destinations, and airlines. Returns results with a TripAdvisor `place_id` (numeric). For…
- `walmart_product` _(read)_ — Get detailed product information from Walmart. Requires a product_id obtained from walmart_search results. Returns comprehensive product details including…
- `walmart_reviews` _(read)_ — Get customer reviews for a Walmart product. Returns individual reviews (rating, text, author, date) plus an overall rating summary. Optionally filter by star…
- `walmart_search` _(read)_ — Search for products on Walmart. Returns product listings with prices, ratings, and availability. Use the walmart_product tool with the product_id or id field…
- `walmart_stores` _(read)_ — Find Walmart store IDs near a US location. Provide a 5-digit ZIP code (most precise) or a city/state in "City, ST" format. Returns nearby Walmart stores with…
- `youtube_channel_posts` _(read)_ — List the community posts of a YouTube channel from its Posts tab, about 10 per page. Posts can include text, likes, comments, poll or quiz results,…
- `youtube_hashtag` _(read)_ — Get the videos or shorts YouTube lists under a hashtag. Returns the hashtag with its approximate video and channel counts, and up to 36 videos (title, channel,…
- `youtube_post` _(read)_ — Get a single YouTube community post from its URL or post ID. Returns the post text with resolved links and hashtags, exact like count, channel details, poll…
- `youtube_search` _(read)_ — Search YouTube for videos. Returns video results with titles, channels, view counts, and thumbnails. Use this to find videos on any topic. Requires a search…
- `youtube_transcript` _(read)_ — Extract transcripts from YouTube videos. By default returns combined plain text (best for reading and summarization). Set output_format to 'json' for…
- `youtube_video` _(read)_ — Get detailed information about a YouTube video. Returns video metadata including title, description, channel info, view count, comments, and related videos.
- `zillow_property` _(read)_ — Get detailed information about a specific Zillow property or building. Returns address, pricing, Zestimate, photos, facts and features, schools,…
- `zillow_search` _(read)_ — Search for real estate listings on Zillow. Returns properties for sale, for rent, or recently sold with pricing, property details, and photos. Supports…

---

## Connect

Gateway URL: https://gateway.mewcp.com/personal/mcp

Every request carries one header:

    Authorization: Bearer <API_KEY>

Replace `API_KEY` with your own key from the dashboard (Developer).

## Apps

### Claude Desktop

Mac & Windows app

- macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
- Windows: `%APPDATA%\Claude\claude_desktop_config.json`

```json
{
  "mcpServers": {
    "mewcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://gateway.mewcp.com/personal/mcp",
        "--header",
        "Authorization: Bearer API_KEY"
      ]
    }
  }
}
```

Already have an "mcpServers" section in your config? Just add the server entry inside it.

1. Open Claude Desktop → Settings → Developer → "Edit Config"
2. Paste the snippet inside the outer { } of the config file (merge with your existing "mcpServers" section if you have one)
3. Save the file and restart Claude Desktop
4. Start a new conversation — your tool will be available

### VS Code

Copilot / Cline

- Command Palette → "MCP: Open User Configuration" (opens mcp.json). For one project only, use .vscode/mcp.json instead.

```json
{
  "mcp.servers": {
    "mewcp": {
      "type": "http",
      "url": "https://gateway.mewcp.com/personal/mcp",
      "headers": {
        "Authorization": "Bearer API_KEY"
      }
    }
  }
}
```

Already have a "servers" section in your mcp.json? Just add the server entry inside it.

1. Open VS Code → Command Palette (Cmd+Shift+P / Ctrl+Shift+P)
2. Run "MCP: Open User Configuration" to open your mcp.json
3. Paste the snippet and save
4. Start the server when prompted (or from the MCP servers view) and use it in Copilot Chat

### Cursor

AI-first editor

- macOS: `~/.cursor/mcp.json`
- Windows: `%USERPROFILE%\.cursor\mcp.json`

```json
{
  "mcpServers": {
    "mewcp": {
      "url": "https://gateway.mewcp.com/personal/mcp",
      "headers": {
        "Authorization": "Bearer API_KEY"
      }
    }
  }
}
```

Already have an "mcpServers" section in your mcp.json? Just add the server entry inside it.

1. Open Cursor → Settings → Cursor Settings → MCP
2. Click "Add new global MCP server"
3. Paste the snippet and save
4. Restart Cursor

### Codex

OpenAI's CLI agent

- Add the snippet to your Codex MCP config or your standard MCP config file for the CLI tool you use.

```json
{
  "mcpServers": {
    "mewcp": {
      "type": "http",
      "url": "https://gateway.mewcp.com/personal/mcp",
      "headers": {
        "Authorization": "Bearer API_KEY"
      }
    }
  }
}
```

Codex generally reads a standard MCP server block, so you can add this alongside your other configured servers.

1. Open your Codex MCP config or project-level config file
2. Paste the MewCP server block inside the config JSON/TOML structure your tool expects
3. Save the file and restart Codex
4. Verify the tool is available inside a fresh session

### Claude Code

Anthropic's CLI agent

- ~/.claude.json (user scope) or .mcp.json in your project root — create it if it doesn't exist. Or skip the file and use the CLI command below.

```json
{
  "mcpServers": {
    "mewcp": {
      "type": "http",
      "url": "https://gateway.mewcp.com/personal/mcp",
      "headers": {
        "Authorization": "Bearer API_KEY"
      }
    }
  }
}
```

Already have an "mcpServers" section in your config? Just add the server entry inside it.

1. Open ~/.claude.json (or .mcp.json in your project root) in a text editor
2. Paste the snippet inside the outer { } (merge with your existing "mcpServers" section if you have one)
3. Save the file and start (or restart) Claude Code
4. Or skip the file entirely and run the CLI command below instead

### OpenCode

Open-source terminal agent

- ~/.config/opencode/opencode.json (global) or opencode.json in your project root — create it if it doesn't exist.

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mewcp": {
      "type": "remote",
      "url": "https://gateway.mewcp.com/personal/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer API_KEY"
      }
    }
  }
}
```

Already have an "mcp" section in your opencode.json? Just add the server entry inside it.

1. Open ~/.config/opencode/opencode.json (or opencode.json in your project root) in a text editor
2. Paste the snippet inside the outer { } (merge with your existing "mcp" section if you have one)
3. Save the file and start (or restart) OpenCode

### OpenClaw

Self-hosted agent gateway

- ~/.openclaw/openclaw.json — create it if it doesn't exist.

```json
{
  "mcp": {
    "servers": {
      "mewcp": {
        "transport": "streamable-http",
        "url": "https://gateway.mewcp.com/personal/mcp",
        "enabled": true,
        "headers": {
          "Authorization": "Bearer API_KEY"
        }
      }
    }
  }
}
```

Already have an "mcp" section in your openclaw.json? Just add the server entry inside "servers".

1. Open ~/.openclaw/openclaw.json in a text editor
2. Paste the snippet inside the outer { } (merge with your existing "mcp" section if you have one)
3. Save the file and restart OpenClaw

### Antigravity

Google's agentic IDE

- ~/.gemini/config/mcp_config.json (global) or .agents/mcp_config.json (workspace-local) — create it if it doesn't exist.

```json
{
  "mcpServers": {
    "mewcp": {
      "serverUrl": "https://gateway.mewcp.com/personal/mcp",
      "headers": {
        "Authorization": "Bearer API_KEY"
      }
    }
  }
}
```

Already have an "mcpServers" section in your config? Just add the server entry inside it. Remote servers must use the "serverUrl" field — the legacy "url"/"httpUrl" fields aren't supported.

1. In the editor's agent side panel, click "…" → "MCP Servers" → "Manage MCP Servers" → "View raw config" (Antigravity CLI: type /mcp instead to open the Interactive MCP Manager)
2. Paste the snippet inside the outer { } (merge with your existing "mcpServers" section if you have one)
3. Save the file — the server connects automatically

### Hermes

Nous Research's CLI agent

- config.yaml in your Hermes config directory (~/.hermes) — add this under a top-level "mcp_servers:" key.

```yaml
mcp_servers:
  mewcp:
    url: "https://gateway.mewcp.com/personal/mcp"
    headers:
      Authorization: "Bearer API_KEY"
```

Already have an "mcp_servers" section in your config.yaml? Just add the server entry inside it.

1. Open config.yaml in your Hermes config directory
2. Paste the snippet under the top-level "mcp_servers:" key (merge with existing entries if you have any)
3. Save the file, then run /reload-mcp in Hermes (or start a fresh session)
4. Ask Hermes "Tell me which MCP-backed tools are available right now" to confirm it connected

### DeepSeek Harness

DeepSeek's agent harness

- cordis.yml in your DSH project — or the patch file you mount plugins from.

```yaml
- id: mcp-mewcp
  name: '@deepseek-ai/dsh-mcp-client'
  config:
    serverName: mewcp
    transport: streamable-http
    url: https://gateway.mewcp.com/personal/mcp
    headers:
      Authorization: "Bearer API_KEY"
```

One plugin instance = one MCP server. Add this entry to your plugin list; don't nest it inside another entry.

1. Open cordis.yml (or your patch file) in your DSH project
2. Paste the entry into your plugin list, keeping the leading dash and indentation
3. Restart DSH (or let HMR reload) — tools register as mcp__mewcp__<tool_name>
4. Verify with: dsh web --dump-config | grep -A3 mcp

## SDKs

### Python

fastmcp client

```python
import asyncio
from fastmcp import Client
from fastmcp.client.transports import StreamableHttpTransport

SERVER_URL = "https://gateway.mewcp.com/personal/mcp"
API_KEY = "API_KEY"

transport = StreamableHttpTransport(
    url=SERVER_URL,
    headers={
        "Authorization": f"Bearer {API_KEY}",
    }
)

async def main():
    client = Client(transport)
    async with client:
        tools = await client.list_tools()
        print(tools)

asyncio.run(main())
```

1. Install fastmcp: pip install fastmcp
2. Copy the snippet into your project
3. Replace API_KEY with your key from the dashboard
4. Run your script

### TypeScript

MCP SDK

```typescript
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";

const SERVER_URL = "https://gateway.mewcp.com/personal/mcp";
const API_KEY = "API_KEY";

const transport = new StreamableHTTPClientTransport(new URL(SERVER_URL), {
  requestInit: {
    headers: {
      Authorization: `Bearer ${API_KEY}`,
    },
  },
});

const client = new Client({ name: "mewcp-client", version: "1.0.0" });
await client.connect(transport);

const tools = await client.listTools();
console.log(tools.tools.map((t) => t.name));
```

1. Install: npm install @modelcontextprotocol/sdk
2. Copy the snippet into your project
3. Replace API_KEY with your key from the dashboard
4. Run with Node 18+ as an ES module (e.g. npx tsx script.ts)