# Mangools MCP Server > **Mangools MCP Server** is a hosted, multitenant Model Context Protocol (MCP) server run by **MewCP** (https://mewcp.com), giving AI agents managed access to Mangools. > > 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/mangools-mcp > MewCP docs: https://docs.mewcp.com > Full catalog: https://mewcp.com/llms.txt --- ## About Run keyword research, SERP analysis, rank tracking, and backlink audits directly from your AI chat. --- ## Details - Server ID: `mangools-mcp` - Version: 0.1.0 - Tools: 73 - 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 — Mangools has to be in the toolset first. In order: 1. Add Mangools to your toolset at https://mewcp.com/mcp/mangools-mcp 2. Connect your Mangools 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 (73) 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. - `mangools_search_locations` _(read)_ — Search the Mangools location catalog by free-text query (e.g. "London", "Czech Republic", "California"). Returns a list of locations with their numeric `id`… - `kwfinder_search_related_keywords` _(read)_ — [Consumes paid quota] Get keywords related to a seed keyword, with search volume, CPC, PPC and (cached) keyword difficulty, sorted by relevance. Keyword… - `kwfinder_get_keyword_details` _(read)_ — [Consumes paid quota] Get full metrics for a single keyword — keyword SEO difficulty, search volume, CPC/PPC — together with the organic SERP results and… - `kwfinder_get_competitor_keywords` _(read)_ — [Consumes paid quota] Get the keywords a given URL or domain ranks for in organic search, sorted by estimated organic visits (highest-impact keyword first).… - `kwfinder_find_competitor_domains` _(read)_ — [Consumes paid quota] Returns a list of domains that compete with the specified URL/domain for organic keywords. ### Limits Requires a GET or POST… - `kwfinder_get_url_keyword_suggestions` _(read)_ — [Consumes paid quota] Suggest keywords a URL, domain or subdomain could target, derived from the keywords it already ranks for (handy when setting up a new… - `kwfinder_get_url_kd_metrics` _(read)_ — Get keyword difficulty (KD) URL metrics for a specific URL — the URL authority score used as an input signal when calculating KWFinder's keyword difficulty.… - `kwfinder_get_quota_limits` _(read)_ — Get your current API usage and remaining limits across every Mangools resource — Keyword lookups, SERP lookups, Backlink rows, Tracked keywords, and more.… - `kwfinder_list_keyword_lists` _(read)_ — Get all keyword lists saved on your account, sorted newest first. Each list returns its id, name and the ids of the keywords it contains. Use kwfinder_get_list… - `kwfinder_import_keywords` _(read)_ — [Consumes paid quota] Look up SEO metrics for a caller-supplied set of keywords (up to 700 per request): keyword difficulty, search volume, CPC/PPC and SERP… - `kwfinder_get_keyword_gap_analysis` _(read)_ — [Consumes paid quota] Find the keywords your competitors rank for but your domain does not — the classic SEO content-gap analysis. Compare your domain against… - `kwfinder_get_keyword_trends` _(read)_ — [Deprecated — no fresh data since January 2025.] Previously returned monthly search-volume trends for a keyword (sourced from Google Trends). Cached results… - `kwfinder_list_kd_requests` _(read)_ — Get the history of your recent keyword difficulty URL lookups performed through `/kwfinder/kd/url-metrics`. Each entry includes the URL and the URL authority… - `kwfinder_list_requests` _(read)_ — Get your last 100 KWFinder lookups, oldest first. Each entry has a type t: 0 related keywords (with kw, language, rank, rank_ts and location), 1 competitor… - `kwfinder_export_keywords` _(read)_ — Fetch full keyword data for a set of keywords by their Mangools keyword_ids. Returns a JSON array of keyword objects (keys include kw, sv, lid, cpc, ppc, seo,… - `kwfinder_create_list` _(write)_ — [Modifies user data] Create a new keyword list on your account. Required fields: * `name` — list name * `keyword_ids` — array of keyword IDs to populate the… - `kwfinder_get_list` _(read)_ — Get a single saved keyword list together with the full keyword data (search volume, CPC, PPC, keyword difficulty, location) for every keyword in it. Returns a… - `kwfinder_update_list` _(write)_ — [Modifies user data] Rename an existing keyword list. Required field: * `name` — new list name Returns HTTP 204. (Pace requests: the Mangools API allows only a… - `kwfinder_delete_list` _(destructive)_ — [Irreversible] Delete a keyword list. The list is removed from your account; keyword data referenced by the list is unaffected and remains available in other… - `serpchecker_get_serp` _(read)_ — [Consumes paid quota] Get a detailed SERP for a keyword in a given location: the organic and paid results plus all detected SERP features (rich snippets). For… - `serpchecker_reset_serp` _(read)_ — [Consumes paid quota] Force a fresh re-parse of the SERP for a keyword/location instead of reusing the cached lookup, then return the same detailed SERP as… - `serpchecker_get_url_metrics` _(read)_ — [Consumes paid quota] Get SEO metrics for a specific URL — MOZ Domain Authority and Page Authority, plus Majestic Citation Flow and Trust Flow. Useful for… - `serpchecker_get_recent_requests` _(read)_ — Get the history of your recent SERP lookups performed through `/serpchecker/serps`. Each entry includes the queried keyword and location — useful for… - `serpchecker_get_serp_snapshot` _(read)_ — Get the rendered snapshot image of a SERP previously fetched with serpchecker_get_serp (or serpchecker_reset_serp). Pass the serp_snapshot_id from that… - `serpwatcher_create_tracking` _(write)_ — [Modifies user data] Create a rank tracking for one domain on a single search location and platform; its keywords are queued for crawl and default… - `serpwatcher_list_trackings` _(read)_ — List all rank trackings owned by your account (newest first), each with its location and current tracked-keyword count. Pass is_with_deleted=true to also… - `serpwatcher_create_multiple_trackings` _(write)_ — [Modifies user data] Create rank trackings for a single domain across multiple search locations and platforms in one call. For a single location/platform, use… - `serpwatcher_delete_tracking` _(destructive)_ — [Irreversible] Delete a rank tracking and all its tracked keywords. Irreversible. Returns HTTP 204. (Pace requests: the Mangools API allows only a few calls… - `serpwatcher_get_tracking_detail` _(read)_ — Get a lightweight snapshot of a tracking with its tracked-keyword list for the from/to range — each keyword with its id, text, currently ranking URL, tags and… - `serpwatcher_get_tracking_stats` _(read)_ — Get aggregated rank stats and per-keyword rank data for a tracking over a from/to range: current/best/average rank, rank and visit deltas, sampled rank… - `serpwatcher_list_tracked_keywords` _(read)_ — List all tracked keywords for a tracking, each enriched with search volume and monthly search volume. Pass is_with_deleted=true to include previously deleted… - `serpwatcher_create_tracked_keywords` _(write)_ — [Modifies user data] Add new keywords to an existing tracking. Request body: * `keywords` — array of keyword strings to add * `tag_ids` — optional array of tag… - `serpwatcher_delete_tracked_keywords` _(destructive)_ — [Irreversible] Remove one or more tracked keywords from a tracking; pass their IDs in tracked_keyword_ids (non-empty array). Irreversible; the tracking stats… - `serpwatcher_get_tracked_keyword` _(read)_ — Get the full rank detail for one tracked keyword: ranking URLs split across organic, Map Pack and Featured Snippet, the daily rank series over the from/to… - `serpwatcher_list_reports` _(read)_ — Get all scheduled email reports configured on a tracking (weekly, monthly, and rank-change alerts), sorted by creation date (newest first). Each report… - `serpwatcher_create_report` _(write)_ — [Modifies user data] Configure a new scheduled email report or rank-change alert for a tracking. Required fields: * `name` — human-readable report name *… - `serpwatcher_update_report` _(write)_ — [Modifies user data] Update the configuration of an existing scheduled email report — change its name, type, recipient emails list or triggers. Returns HTTP… - `serpwatcher_delete_report` _(destructive)_ — [Irreversible] Remove a scheduled email report from a tracking. Returns HTTP 204. (Pace requests: the Mangools API allows only a few calls per short period.) - `serpwatcher_create_annotation` _(write)_ — [Modifies user data] Create a user annotation pinned to a specific date on the tracking timeline. Annotations are rendered as markers on rank history charts… - `serpwatcher_update_annotation` _(write)_ — [Modifies user data] Update an existing user annotation on a tracking — change its text, date (`YYYY-MM-DD`) or `nonShareable` flag. Returns HTTP 204. (Pace… - `serpwatcher_delete_annotation` _(destructive)_ — [Irreversible] Delete a user annotation from a tracking's timeline. Returns HTTP 204. (Pace requests: the Mangools API allows only a few calls per short… - `serpwatcher_list_tags` _(read)_ — List all keyword tags owned by your account across every tracking (newest first). Tags are color-coded labels used to organize tracked keywords and filter rank… - `serpwatcher_list_tracking_tags` _(read)_ — List all tags scoped to a specific tracking (newest first). For a cross-tracking list, use serpwatcher_list_tags. (Pace requests: the Mangools API allows only… - `serpwatcher_create_tag` _(write)_ — [Modifies user data] Create a new tag on a tracking. Required fields: name (label) and color. Once created, attach tags to tracked keywords with… - `serpwatcher_update_tag` _(write)_ — [Modifies user data] Update an existing tag — change its `name` and/or `color`. The change is reflected everywhere the tag is rendered (keyword lists,… - `serpwatcher_assign_tags` _(write)_ — [Modifies user data] Attach one or more tags to one or more tracked keywords in a single call. Both `keyword_ids` (tracked keyword IDs) and `tag_ids` are… - `serpwatcher_unassign_tags` _(write)_ — [Modifies user data] Detach one or more tags from one or more tracked keywords in a single call. Both `keyword_ids` (tracked keyword IDs) and `tag_ids` are… - `linkminer_get_url_metrics` _(read)_ — [Consumes paid quota] Get SEO metrics for a specific URL, domain or subdomain — Citation Flow, Trust Flow, referring domain and backlink counts sourced from… - `linkminer_get_backlinks` _(read)_ — [Consumes paid quota] Get a list of backlinks for a specific URL, domain or URL path (up to 500 per page; paginate with the page parameter for more). Tip: set… - `linkminer_set_favorite_link` _(write)_ — [Modifies user data] Star or unstar a backlink in your favorites. Pass favorite=true to add or false to remove. link_id is the _id of a link from… - `linkminer_list_favorites` _(read)_ — Get all favorite-link lists saved on your account, sorted by last update (newest first). Favorite lists are per-target groupings of backlinks you have starred… - `linkminer_delete_favorite_list` _(destructive)_ — [Irreversible] Delete a favorite-link list from your account. Does not affect the underlying backlinks returned by linkminer_get_backlinks. Returns HTTP 204.… - `linkminer_get_requests` _(read)_ — Get the history of your recent backlink lookups performed through linkminer_get_backlinks. Each entry includes the target URL, source type (all / new / lost)… - `linkminer_list_exports` _(read)_ — Get all full backlink CSV exports you have created, sorted by creation date (newest first). Each entry describes the target URL, the filters that were applied,… - `linkminer_create_export` _(write)_ — [Modifies user data] Create a full-backlink CSV export job for a target URL, domain or subdomain. Call linkminer_suggest_export first to get the available… - `siteprofiler_get_overview` _(read)_ — [Consumes paid quota] Get the headline SEO metrics for a URL, domain or subdomain: Moz Domain Authority and Page Authority, Majestic Citation Flow and Trust… - `siteprofiler_get_backlink_profile` _(read)_ — Get the backlink profile for the URL, domain or subdomain passed in the `url` parameter (not a `domain` parameter); a domain request returns whole-domain… - `siteprofiler_get_top_content` _(read)_ — Get the top-performing pages (by backlink metrics) for the URL, domain or subdomain passed in the `url` parameter (not a `domain` parameter). Each page… - `siteprofiler_find_competitors` _(read)_ — Find the domains competing with the URL, domain or subdomain passed in the `url` parameter (not a `domain` parameter). Each competitor includes its TopRank… - `siteprofiler_list_requests` _(read)_ — Get the history of your recent SiteProfiler lookups from the last 30 days. Returns a list of the analyzed URLs or domains — useful for rebuilding a "recent… - `ai_search_watcher_list_models` _(read)_ — Get the list of AI models available for brand monitoring (ChatGPT, Gemini, Claude, and others). Each entry includes its numeric id, full model path… - `ai_search_watcher_list_monitors` _(read)_ — Get all AI Search Watcher brand monitors owned by your account. Each monitor describes a brand being tracked across AI answer engines — its name, domain,… - `ai_search_watcher_create_monitor` _(write)_ — [Modifies user data] Create a new AI Search Watcher brand monitor — a tracked setup measuring how often a brand is mentioned and cited by AI answer engines… - `ai_search_watcher_get_monitor` _(read)_ — Get analytics for a single AI brand monitor (by id from ai_search_watcher_list_monitors): how often the brand is mentioned across the configured AI models and… - `ai_search_watcher_delete_monitor` _(destructive)_ — [Irreversible] Delete an AI Search Watcher brand monitor from your account together with its prompts, reports and tags. The monitor stops collecting responses… - `ai_search_watcher_generate_prompts` _(write)_ — [Modifies user data] Generate suggested monitoring prompts and a brand-perception summary for a brand — useful during monitor onboarding so the user does not… - `ai_search_watcher_get_prompt` _(read)_ — Get metrics for a single monitoring prompt (by id from ai_search_watcher_list_monitor_prompts): how each configured AI model responds to it, brand mention… - `ai_search_watcher_delete_prompts` _(destructive)_ — [Irreversible] Delete one or more monitoring prompts across monitors in a single bulk call. Request body: * `prompt_ids` — non-empty array of prompt IDs to… - `ai_search_watcher_list_monitor_prompts` _(read)_ — Get the list of monitoring prompts attached to a monitor. Each prompt entry includes its id, text, tags, creation and update timestamps, its metrics for the… - `ai_search_watcher_add_monitor_prompts` _(write)_ — [Modifies user data] Add one or more new prompts to an existing AI brand monitor (by id from ai_search_watcher_list_monitors). Generate candidate prompts first… - `ai_search_watcher_get_monitor_settings` _(read)_ — Get the current configuration of a monitor — brand name, brand variations, domain, location, configured AI models, language, active email reports and… - `ai_search_watcher_update_monitor_settings` _(write)_ — [Modifies user data] Update the configuration of an existing monitor: brand name, brand variations, domain, AI model list and email reports. Location, platform… - `get_more_tools` _(read)_ — Check for additional tools whenever your task might benefit from specialized capabilities - even if existing tools could work as a fallback. --- ## 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)