# Ahrefs MCP MCP Server > **Ahrefs MCP MCP Server** is a hosted, multitenant Model Context Protocol (MCP) server run by **MewCP** (https://mewcp.com), giving AI agents managed access to Ahrefs 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/ahrefs-mcp > MewCP docs: https://docs.mewcp.com > Full catalog: https://mewcp.com/llms.txt --- ## About Official Ahrefs MCP server that lets AI agents securely access Ahrefs SEO data, site metrics, keyword research, and competitor analysis through the Ahrefs API. --- ## Details - Server ID: `ahrefs-mcp` - Version: 1.0.0 - Tools: 135 - 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 — Ahrefs MCP has to be in the toolset first. In order: 1. Add Ahrefs MCP to your toolset at https://mewcp.com/mcp/ahrefs-mcp 2. Connect your Ahrefs 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 (135) 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. - `site-explorer-organic-competitors` _(read)_ — Retrieves a list of organic search competitors for a specified website or URL, providing comparative SEO metrics such as common keywords, traffic estimations,… - `social-media-activity-history` _(read)_ — Get the activity history log for posts (published, scheduled, failed, etc.). Use doc tool first to get the real input schema. - `site-explorer-crawled-pages` _(read)_ — Returns a list of pages crawled by Ahrefs for a specified domain or URL, including the page URLs. When analyzing a domain name, you must use mode=subdomains.… - `web-analytics-source-channels-chart` _(read)_ — Returns time-series chart data grouped by source channel (e.g., organic, paid, social, direct) for a Web Analytics project, showing metrics over time. Use doc… - `serp-overview` _(read)_ — Returns an overview of the top search results (SERP) for a specified keyword and country, including detailed metrics about each result like position,… - `site-explorer-refdomains-history` _(read)_ — Provides historical data on referring domains linking to a specified target (domain or URL) over a defined date range, with customizable grouping and analysis… - `gsc-metrics-by-country` _(read)_ — Returns Google Search Console click metrics grouped by country for a project. Use doc tool first to get the real input schema. - `doc` _(read)_ — Full documentation for Ahrefs API v3 and the corresponding MCP tools. You must use this tool to get the input schema for any other tool. The documentation is… - `subscription-info-limits-and-usage` _(read)_ — Retrieves subscription information including limits and usage statistics for API units, workspace quotas, and API key details. This endpoint is free and does… - `web-analytics-languages` _(read)_ — Returns visitor data grouped by browser language for a Web Analytics project, showing visitor counts for each language. Use doc tool first to get the real… - `web-analytics-countries` _(read)_ — Returns visitor data grouped by country for a Web Analytics project, showing visitor counts for each location. Use doc tool first to get the real input schema. - `site-explorer-pages-by-internal-links` _(read)_ — Retrieves a site's or page's internal link metrics, allowing analysis of how pages within the given domain or URL are interconnected and which pages receive… - `gsc-performance-by-position` _(read)_ — Returns Google Search Console performance metrics (clicks, impressions, keyword count) grouped by position ranges (1-3, 4-10, 11-20, 21-50, 51+) for a project.… - `web-analytics-source-channels` _(read)_ — Returns traffic grouped by source channel (e.g., organic, paid, social, direct) for a Web Analytics project, including visitor counts, bounce rates, and… - `site-audit-issues` _(read)_ — Returns all issues from your Site Audit crawl. By default, it provides data from the latest available crawl, but you can also specify a crawl date and time to… - `rank-tracker-competitors-domains` _(read)_ — Provides an overview of competitor domains and their share of voice for a specified project and date in Ahrefs Rank Tracker, allowing comparison between… - `rank-tracker-competitors-stats` _(read)_ — Provides an overview of competitor metrics for a specified project and date in Ahrefs Rank Tracker. Metrics include: share of voice, share of traffic value,… - `web-analytics-utm-params-chart` _(read)_ — Returns time-series chart data grouped by a specified UTM param for a Web Analytics project, showing visitor counts, bounce rates, and session durations over… - `web-analytics-referrers-chart` _(read)_ — Returns time-series chart data grouped by referrer for a Web Analytics project, showing visitor counts, bounce rates, and session durations over time. Use doc… - `web-analytics-continents-chart` _(read)_ — Returns time-series chart data grouped by continent for a Web Analytics project, showing visitor counts over time for each region. Use doc tool first to get… - `brand-radar-cited-pages-entities` _(read)_ — Provides the pages cited in AI-generated responses that mention your brand or competitors' brands in an LLM you specify, including how many responses… - `web-analytics-operating-systems` _(read)_ — Returns operating system statistics for a Web Analytics project, showing visitor counts, bounce rates, and session durations grouped by OS. Use doc tool first… - `web-analytics-top-pages` _(read)_ — Returns the most visited pages for a Web Analytics project, including pageview counts, visitor counts, bounce rates, and average page visit durations. Use doc… - `brand-radar-ai-responses` _(read)_ — Provides questions asked to AI assistants and the corresponding AI-generated responses that mention your brand or competitors’ brands, including cited sources… - `web-analytics-operating-systems-versions-chart` _(read)_ — Returns time-series chart data grouped by OS version for a Web Analytics project, showing visitor counts, bounce rates, and session durations over time. Use… - `site-explorer-url-rating-history` _(read)_ — Retrieves the historical URL rating data for a specified domain or URL over a defined date range, grouped by a chosen time interval. Requests will not consume… - `management-keyword-list-keywords` _(read)_ — Retrieves keywords from a keyword list. Requests to this endpoint are free and do not consume any API units. Use doc tool first to get the real input schema. - `public-crawler-ip-ranges` _(read)_ — Returns the IP ranges used by the Ahrefs public web crawler, typically for allowlisting or firewall configuration. Use doc tool first to get the real input… - `site-explorer-metrics` _(read)_ — Provides SEO performance metrics for a specified domain, URL, or site section as of a given date, with options to customize search scope, protocol, country,… - `site-explorer-referring-domains` _(read)_ — Retrieves detailed information about referring domains that link to a specified target domain or URL, with flexible filtering, selection, and sorting of… - `social-media-channel-metrics` _(read)_ — Get historical follower count data for connected channels. Use doc tool first to get the real input schema. - `site-explorer-all-backlinks` _(read)_ — Retrieves detailed information about all backlinks pointing to a specified URL or domain, with extensive filtering, sorting, selection, and aggregation… - `site-explorer-total-search-volume-history` _(read)_ — Returns historical totals of search volume for keywords that the specified domain or URL ranks for in the top 10 or top 100 results, across all countries or… - `site-explorer-linked-anchors-external` _(read)_ — Retrieves data about external anchor text (the clickable words in outbound links) used on a specified domain, subdomain, or URL, including metrics like… - `site-explorer-linked-anchors-internal` _(read)_ — Retrieves internal anchor text data for a given website or URL, detailing how anchor texts are used in links between pages on the same site. When analyzing a… - `site-explorer-organic-keywords` _(read)_ — Retrieves detailed organic keyword data for a given domain, URL, or path, including rankings, search intent, SERP features, traffic and CPC metrics, with the… - `web-analytics-browsers` _(read)_ — Returns browser statistics for a Web Analytics project, showing visitor counts, bounce rates, and session durations grouped by browser. Use doc tool first to… - `public-domain-rating-free` _(read)_ — Retrieves the domain rating for a specified domain or URL as of today. Use doc tool first to get the real input schema. - `management-project-keywords` _(read)_ — Returns all tracked keywords for a specific Rank Tracker project, including associated tracking metadata. Use doc tool first to get the real input schema. - `management-locations` _(read)_ — Retrieves a list of management locations filtered by country code and optionally by US state. Use doc tool first to get the real input schema. - `gsc-anonymous-queries` _(read)_ — Returns organic keywords that rank for the project but are not reported by Google Search Console (anonymized queries), with position, traffic, volume, and CPC… - `gsc-performance-history` _(read)_ — Returns Google Search Console performance chart data (clicks, impressions, CTR, position) for a project over time, grouped by daily, weekly, or monthly… - `render-scorecard` _(read)_ — Render a scorecard widget showing key metrics as a card grid. Accepts metric cards with labels, raw numeric values, optional unit, optional change indicators,… - `site-audit-page-content` _(read)_ — Returns the HTML and extracted text content of a page from your Site Audit crawl. By default, it provides the latest available snapshot, but you can also… - `brand-radar-impressions-history` _(read)_ — Provides the historical number of impressions for your and competitors's brands in an LLM you specify. Prefer using the equivalent… - `site-explorer-top-pages` _(read)_ — Returns a list of the top-performing pages for a specified website or URL, including detailed SEO metrics (such as organic rankings, traffic, top keyword, and… - `social-media-channels` _(read)_ — List social media channels with their connection status and metadata. Use doc tool first to get the real input schema. - `gsc-positions-history` _(read)_ — Returns Google Search Console keyword count data grouped by position ranges (1-3, 4-10, 11-20, 21-50, 51+) over time for a project. Use doc tool first to get… - `gsc-pages-history` _(read)_ — Returns Google Search Console pages chart data showing total indexed pages over time for a project. Use doc tool first to get the real input schema. - `web-analytics-countries-chart` _(read)_ — Returns time-series chart data grouped by country for a Web Analytics project, showing visitor counts over time for each location. Use doc tool first to get… - `site-explorer-metrics-history` _(read)_ — Retrieves historical data on key organic and paid search traffic and cost metrics for a specified domain, URL, or path over a selectable date range and… - `brand-radar-mentions-overview-entities` _(read)_ — Provides the number of mentions for your and competitors's brands in an LLM you specify, with filters for locations, query text, URL, and more. Prefer using… - `content-helper-topics` _(read)_ — Analyse the pages currently ranking for a keyword and return the core topics they cover, with per-page coverage scores and supporting extracts. Use it to find… - `brand-radar-citations-history-entities` _(read)_ — Provides the historical number of citations for your and competitors' brand URLs in an LLM you specify. Every entity provided in `brands` (and `competitors`,… - `web-analytics-utm-params` _(read)_ — Returns statistics for a specified UTM paramater for a Web Analytics project, showing visitor counts, bounce rates, and session durations grouped by… - `web-analytics-cities-chart` _(read)_ — Returns time-series chart data grouped by city for a Web Analytics project, showing visitor counts over time for each location. Use doc tool first to get the… - `web-analytics-browsers-chart` _(read)_ — Returns time-series chart data grouped by browser for a Web Analytics project, showing visitor counts, bounce rates, and session durations over time. Use doc… - `site-audit-page-explorer` _(read)_ — Returns detailed information about pages discovered in a Site Audit project, including URLs, crawl metadata, and selected on-page metrics. Use doc tool first… - `web-analytics-browser-versions` _(read)_ — Returns browser version statistics for a Web Analytics project, showing visitor counts, bounce rates, and session durations grouped by browser version. Use doc… - `site-explorer-pages-history` _(read)_ — Retrieves historical data about pages from a specified domain, URL, or section of a site, grouped by a chosen time interval. When analyzing a domain name, you… - `keywords-explorer-volume-by-country` _(read)_ — Retrieves search volume metrics for a specified keyword broken down by country. Requests will not consume API units if you use only "ahrefs" or "wordcount" in… - `management-projects` _(read)_ — Retrieves information about existing projects, including ownership, access type, presence of Rank Tracker keywords, and project ID. Use doc tool first to get… - `site-explorer-pages-by-traffic` _(read)_ — Returns the distribution of pages by estimated organic traffic buckets for a specified domain or URL, across all locations or for a specified country. When… - `rank-tracker-serp-overview` _(read)_ — Returns SERP overview for a specified keyword in a Rank Tracker project, showing detailed information about each position including title, URL, type, backlink… - `management-project-competitors` _(read)_ — Retrieves the list of competitors associated with a specific Rank Tracker project in Ahrefs, using the project's unique identifier. Use doc tool first to get… - `web-analytics-operating-systems-chart` _(read)_ — Returns time-series chart data grouped by operating system for a Web Analytics project, showing visitor counts, bounce rates, and session durations over time.… - `web-analytics-devices` _(read)_ — Returns device type statistics for a Web Analytics project, showing visitor counts, bounce rates, and session durations grouped by device type. Use doc tool… - `site-explorer-paid-pages` _(read)_ — Returns detailed metrics about pages on a specified site or URL that are ranking in paid search results, including traffic, keyword data, ad presence, and… - `web-analytics-browser-versions-chart` _(read)_ — Returns time-series chart data grouped by browser version for a Web Analytics project, showing visitor counts, bounce rates, and session durations over time.… - `brand-radar-cited-domains` _(read)_ — Provides domains cited in AI-generated responses that mention your brand or competitors' brands in an LLM you specify, including how many responses referenced… - `web-analytics-referrers` _(read)_ — Returns referrer statistics for a Web Analytics project, showing visitor counts, bounce rates, and session durations grouped by referrer URL. Use doc tool… - `site-explorer-domain-rating-history` _(read)_ — Retrieves the historical domain rating data for a specified domain or URL over a defined date range and grouping interval. Requests will not consume API units… - `brand-radar-cited-domains-entities` _(read)_ — Provides domains cited in AI-generated responses that mention your brand or competitors' brands in an LLM you specify, including how many responses referenced… - `rank-tracker-overview` _(read)_ — Provides an overview of tracked keyword rankings and related search metrics for a specified project and date, with support for historical comparison,… - `brand-radar-mentions-history` _(read)_ — Provides the historical number of mentions for your and competitors's brands in an LLM you specify. Prefer using the equivalent… - `brand-radar-impressions-overview` _(read)_ — Provides the number of impressions for your and competitors's brands in an LLM you specify, with filters for locations, query text, URL, and more. Prefer using… - `brand-radar-citations-overview-entities` _(read)_ — Provides the number of citations for your and competitors's brands in an LLM you specify, with filters for locations, query text, URL, and more. Every entity… - `web-analytics-entry-pages` _(read)_ — Returns entry page statistics for a Web Analytics project, showing which pages visitors land on first, including visitor counts and entry rates. Use doc tool… - `brand-radar-ai-responses-entities` _(read)_ — Provides questions asked to AI assistants and the corresponding AI-generated responses that mention your brand or competitors’ brands, including cited sources… - `social-media-posts` _(read)_ — List social media posts with filtering by channel, status, and author. Use doc tool first to get the real input schema. - `keywords-explorer-volume-history` _(read)_ — Retrieves historical search volume data for a specified keyword within a given country and date range. Requests will not consume API units if you use only… - `brand-radar-sov-history` _(read)_ — Provides the historical share of voice for your and competitors's brands in an LLM you specify. Prefer using the equivalent 'brand-radar-sov-history-entities'… - `rank-tracker-competitors-pages` _(read)_ — Provides an overview of competitor pages and keyword metrics for a specified project and date in Ahrefs Rank Tracker, allowing comparison between current and… - `brand-radar-cited-pages` _(read)_ — Provides the pages cited in AI-generated responses that mention your brand or competitors' brands in an LLM you specify, including how many responses… - `gsc-performance-by-device` _(read)_ — Returns Google Search Console performance metrics (clicks, impressions, CTR, position) broken down by device type (desktop, mobile, tablet) for a project. Use… - `public-crawler-ips` _(read)_ — Returns the list of individual IP addresses currently used by the Ahrefs public web crawler. Use doc tool first to get the real input schema. - `web-analytics-exit-pages` _(read)_ — Returns exit page statistics for a Web Analytics project, showing which pages visitors leave from, including visitor counts and exit rates. Use doc tool first… - `gsc-page-history` _(read)_ — Returns Google Search Console performance history chart data (clicks, impressions, CTR, position) for specific pages over time, grouped by daily, weekly, or… - `site-explorer-outlinks-stats` _(read)_ — Retrieves statistical data about the outbound links (outlinks) from a specified URL, domain, or site section. When analyzing a domain name, you must use… - `social-media-authors` _(read)_ — List users who have created posts in the account. Use doc tool first to get the real input schema. - `web-analytics-cities` _(read)_ — Returns visitor data grouped by city for a Web Analytics project, showing visitor counts for each location. Use doc tool first to get the real input schema. - `brand-radar-mentions-overview` _(read)_ — Provides the number of mentions for your and competitors's brands in an LLM you specify, with filters for locations, query text, URL, and more. Prefer using… - `brand-radar-sov-history-entities` _(read)_ — Provides the historical share of voice for your and competitors's brands in an LLM you specify. Prefer using this tool instead of the non '*-entities' tool,… - `site-explorer-broken-backlinks` _(read)_ — Retrieves a list of broken backlinks (i.e., links pointing to non-functioning pages) for a specified domain or URL, with customizable filtering, field… - `web-analytics-entry-pages-chart` _(read)_ — Returns time-series chart data for entry pages of a Web Analytics project, showing visitor counts and entry rates over time. Use doc tool first to get the real… - `web-analytics-stats` _(read)_ — Returns aggregate statistics for a Web Analytics project, including total visitors, bounce rate, and average session duration without any dimension grouping.… - `site-explorer-backlinks-stats` _(read)_ — Provides backlink statistics for a specified URL or domain as of a given date, with options to control protocol and scope. When analyzing a domain name, you… - `social-media-post-metrics` _(read)_ — Get engagement metrics (views, likes, etc.) for a specific post. Use doc tool first to get the real input schema. - `web-analytics-devices-chart` _(read)_ — Returns time-series chart data grouped by device type for a Web Analytics project, showing visitor counts, bounce rates, and session durations over time. Use… - `web-analytics-chart` _(read)_ — Returns time-series chart data for aggregate statistics of a Web Analytics project, with metrics like pageviews, visitors, visits, bounce rate, and session… - `keywords-explorer-overview` _(read)_ — Provides an overview of keyword metrics—including search volume, CPC, ranking difficulty, traffic potential, and intent—for specified keywords, domains, or… - `web-analytics-sources-chart` _(read)_ — Returns time-series chart data for traffic sources of a Web Analytics project, showing how visitor counts, bounce rates, and session durations change over time… - `brand-radar-impressions-history-entities` _(read)_ — Provides the historical number of impressions for your and competitors's brands in an LLM you specify. Prefer using this tool instead of the non '*-entities'… - `management-brand-radar-reports` _(read)_ — Retrieves the list of custom brand radar reports. Requests to this endpoint are free and do not consume any API units. Use doc tool first to get the real input… - `gsc-keyword-history` _(read)_ — Returns Google Search Console performance history chart data (clicks, impressions, CTR, position) for specific keywords over time, grouped by daily, weekly, or… - `render-time-series-chart` _(read)_ — Render an interactive time series line chart. Accepts one or more named data series. Supports multi-series with automatic dual Y-axis when 2 series have… - `site-explorer-metrics-by-country` _(read)_ — Provides organic and paid search performance metrics for a specified website, broken down by country, for a specific date. When analyzing a domain name, you… - `web-analytics-exit-pages-chart` _(read)_ — Returns time-series chart data for exit pages of a Web Analytics project, showing visitor counts and exit rates over time. Use doc tool first to get the real… - `gsc-keywords` _(read)_ — Returns Google Search Console keywords table data with metrics (clicks, impressions, CTR, position) and associated URLs for a project. Use doc tool first to… - `web-analytics-sources` _(read)_ — Returns traffic source breakdown for a Web Analytics project, showing visitor counts, bounce rates, and session durations grouped by referral source. Use doc… - `management-brand-radar-prompts` _(read)_ — Retrieves custom prompts for a specific brand radar report. Requests to this endpoint are free and do not consume any API units. Use doc tool first to get the… - `keywords-explorer-related-terms` _(read)_ — Returns keyword metrics and related terms—such as "also rank for" keywords and "also talk about" keywords—for a given keyword or keyword list, with filtering… - `web-analytics-languages-chart` _(read)_ — Returns time-series chart data grouped by browser language for a Web Analytics project, showing visitor counts over time for each language. Use doc tool first… - `keywords-explorer-matching-terms` _(read)_ — Retrieves keyword ideas and their associated SEO metrics by matching input terms or phrases in a specified country, with extensive support for filtering,… - `brand-radar-sov-overview` _(read)_ — Provides the share of voice for your and competitors's brands in an LLM you specify, with filters for locations, query text, URL, and more. Prefer using the… - `brand-radar-impressions-overview-entities` _(read)_ — Provides the number of impressions for your and competitors's brands in an LLM you specify, with filters for locations, query text, URL, and more. Prefer using… - `site-explorer-ai-responses-count` _(read)_ — Returns how often AI search platforms cite the target, with the number of citation links and distinct cited pages per platform as of a given date. When… - `gsc-ctr-by-position` _(read)_ — Returns Google Search Console CTR (click-through rate) data by keyword position, showing each keyword's average position, CTR percentage, and click count. Use… - `keywords-explorer-search-suggestions` _(read)_ — Provides keyword search suggestions and related keyword metrics (e.g., search volume, difficulty, CPC) for specified queries or keyword lists, with options to… - `web-analytics-top-pages-chart` _(read)_ — Returns time-series chart data for the most visited pages of a Web Analytics project, showing how pageviews, visitors, and other metrics change over time. Use… - `render-data-table` _(read)_ — Render an interactive data table widget with sorting, search, and pagination. Accepts column definitions (key and label) and row data. Column types are… - `site-explorer-keywords-history` _(read)_ — Retrieves historical data on the number of organic keywords a specified website or URL has ranked for, segmented by various search position ranges and grouped… - `site-explorer-anchors` _(read)_ — Retrieves anchor text and associated backlink metrics for a specified domain or URL, with filtering and selection options. When analyzing a domain name, you… - `rank-tracker-competitors-overview` _(read)_ — Provides an overview of competitor rankings and keyword metrics for a specified project and date in Ahrefs Rank Tracker, allowing comparison between current… - `brand-radar-mentions-history-entities` _(read)_ — Provides the historical number of mentions for your and competitors's brands in an LLM you specify. Prefer using this tool instead of the non '*-entities'… - `site-explorer-pages-by-backlinks` _(read)_ — Returns a list of a site's or URL's best-performing pages, ranked by the number of referring external links, with flexible filtering and sorting options. When… - `site-explorer-domain-rating` _(read)_ — Retrieves the domain rating and related metrics for a specified domain or URL as of a specific date. Requests will not consume API units if you use the… - `brand-radar-sov-overview-entities` _(read)_ — Provides the share of voice for your and competitors's brands in an LLM you specify, with filters for locations, query text, URL, and more. Prefer using this… - `public-domain-rating-top-domains` _(read)_ — Returns the top 1M domains ranked by Ahrefs Domain Rating, together with each domain's current Domain Rating. Use doc tool first to get the real input schema. - `web-analytics-operating-systems-versions` _(read)_ — Returns OS version statistics for a Web Analytics project, showing visitor counts, bounce rates, and session durations grouped by OS version. Use doc tool… - `site-audit-projects` _(read)_ — Returns Site Audit project summaries (all projects or a specific project), including health scores, issue counts, and crawled page counts for the latest crawl… - `batch-analysis` _(read)_ — Performs a batch analysis of multiple URLs, domains, or subdomains to retrieve selected SEO, backlink, organic, and paid traffic metrics. When analyzing a… - `gsc-pages` _(read)_ — Returns Google Search Console pages table data with metrics (clicks, impressions, CTR, position) and associated keywords for a project. Use doc tool first to… - `site-explorer-linked-domains` _(read)_ — Retrieves information about external domains that are linked from a specified target domain or URL, allowing for filtering, field selection, and various scopes… - `web-analytics-continents` _(read)_ — Returns visitor data grouped by continent for a Web Analytics project, showing visitor counts for each region. Use doc tool first to get the real input schema. --- ## Connect Gateway URL: https://gateway.mewcp.com/personal/mcp Every request carries one header: Authorization: Bearer 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:${AUTH_HEADER}" ], "env": { "AUTH_HEADER": "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, then quit Claude Desktop completely and reopen it 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__ 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)