# Hunter.io MCP Server > **Hunter.io MCP Server** is a hosted, multitenant Model Context Protocol (MCP) server run by **MewCP** (https://mewcp.com), giving AI agents managed access to Hunter.io. > > 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/hunter-io-mcp > MewCP docs: https://docs.mewcp.com > Full catalog: https://mewcp.com/llms.txt --- ## About Ask your AI to find companies, verify email addresses, and build leads lists with Hunter’s MCP. --- ## Details - Server ID: `hunter-io-mcp` - Version: 0.11.0 - Tools: 102 - Authentication: OAuth, managed by MewCP - Calls served: 4 - 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 — Hunter.io has to be in the toolset first. In order: 1. Add Hunter.io to your toolset at https://mewcp.com/mcp/hunter-io-mcp 2. Connect your Hunter.io 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 (102) 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. - `Find-Companies` _(read)_ — Use this when the user wants to search for companies that match natural-language criteria such as location, industry, size, type, or technologies. Returns up… - `Domain-Search` _(write)_ — Use this when the user wants the contacts published for a domain — emails with names, positions, and confidence scores. Optional filters: type, seniority,… - `Domain-Search-Found` _(write)_ — Use this when the user wants the contacts published for a domain but guaranteed non-inferred — this returns ONLY found (published) email addresses Hunter has… - `Email-Finder` _(write)_ — Use this when the user wants a specific person's email address at a company. Provide the person's full name and the company's domain. Uses Hunter credits,… - `Email-Verifier` _(write)_ — Use this when the user wants to check whether an email address is deliverable. Returns a status (valid, invalid, accept_all, etc.) and a confidence score. Uses… - `Email-Count` _(read)_ — Use this when the user wants the count of email addresses Hunter has indexed for a domain, optionally split by personal vs generic. Free to call. Do not use… - `Person-Enrichment` _(write)_ — Use this when the user wants to look up a person by email address and see their name, job title, employer, location, phone number, and social profiles. Uses… - `Company-Enrichment` _(write)_ — Use this when the user wants to look up a company by domain and see its industry, size, location, technologies, funding rounds, and social profiles. Does not… - `Combined-Enrichment` _(write)_ — Use this when the user provides an email address or LinkedIn handle and wants both the person's profile and their company's profile in a single response. Uses… - `Get-Account-Details` _(read)_ — Use this when the user asks about their Hunter account, plan, team, or remaining credits. Returns plan name, team info, and per-product credit balances… - `List-Email-Accounts` _(read)_ — List the email accounts (sending inboxes) connected to your Hunter account. This is the first step before creating or starting a sequence — every account… - `Get-Email-Account` _(read)_ — Get the full configuration of one sending email account — the pre-check to run before suggesting changes to an account's settings. On top of the… - `List-Email-Account-Sequences` _(read)_ — List the sequences that send from a given email account — the dependency check to run before pausing, reconfiguring, or disconnecting an account. Pairs with… - `List-Sequence-Follow-Ups` _(read)_ — List the follow-up steps of a sequence, ordered by step. Step 0 is the introduction message and steps 1 and up are follow-ups; each step reports its… - `Pause-Sequence` _(write)_ — Pause a started sequence so it stops sending outbound emails until it is resumed. Only a started, non-archived sequence can be paused: pausing a draft (not yet… - `Resume-Sequence` _(destructive)_ — Resume a paused sequence so it starts sending outbound emails again. Resuming runs the full validation pipeline (unlike pausing), so it can fail with an… - `Archive-Sequence` _(destructive)_ — Archive a started sequence to file it once it is finished. Only a started sequence (active or paused) can be archived: archiving a draft (a sequence that was… - `Get-Sequence-Stats` _(read)_ — Use this when the user wants to see how a sequence is performing. Reports recipient-based stats for a sequence plus a per-follow-up breakdown. The top-level… - `List-Sequences` _(read)_ — List the sequences in your Hunter account with name, lifecycle booleans (started/archived/paused), recipient count, and owner, most recent first. Optionally… - `Get-Sequence` _(read)_ — Get one sequence's full configuration. Returns the lifecycle `status` (draft, planned, active, paused, completed, preparing, error, or archived) plus the raw… - `Create-Sequence` _(write)_ — Create a new outreach sequence. Only `name` is required; the sequence is created as a DRAFT that sends nothing until it is started. Lifecycle: draft → started… - `Update-Sequence` _(destructive)_ — Update an existing sequence's name, schedule, senders, or settings; omitted fields are left unchanged. On a draft every field is editable. Once the sequence… - `Delete-Sequence` _(destructive)_ — Delete a DRAFT sequence permanently. Deletion is drafts-only: a started or archived sequence cannot be deleted (invalid_input error, id… - `Get-Sequence-Follow-Up` _(read)_ — Get a single step of a sequence by its follow-up ID (from List-Sequence-Follow-Ups). Returns the step number (0 is the introduction email), `wait_days`,… - `Create-Sequence-Follow-Up` _(write)_ — Create a new email step in a sequence. Author the sequence step-by-step in conversation: draft the `subject` and `body` with the user, set `wait_days` (days… - `Update-Sequence-Follow-Up` _(destructive)_ — Rewrite an existing step of a sequence — the only tool that can author the introduction email (step 0). Create-Sequence makes step 0 with an empty subject and… - `Delete-Sequence-Follow-Up` _(destructive)_ — Delete a step from a sequence. Only the LAST step can be deleted — to redo an earlier step, delete steps from the end back down to it, then re-create them.… - `List-Sequence-Recipients` _(read)_ — List recipients in a sequence. Free (no credits). - `Add-Sequence-Recipients` _(destructive)_ — Add recipients to a sequence by email addresses or lead IDs. Max 50 per request — batch larger lists. For a draft sequence this only stages recipients and runs… - `Remove-Sequence-Recipients` _(destructive)_ — Remove recipients from a sequence by email addresses. Pending (not-yet-sent) messages scheduled for the removed recipients are cancelled; messages already sent… - `Start-Sequence` _(destructive)_ — Use this when the user wants to start an existing sequence, which begins sending real emails to its recipients. The sequence must have a subject, message body,… - `List-Leads` _(read)_ — List leads in your Hunter account with optional filters. Free (no credits). Returns up to 100 leads per page — use offset to paginate. - `Get-Lead` _(read)_ — Get a single lead by ID. Free (no credits). - `Create-Lead` _(write)_ — Create a new lead in your Hunter account. Free (no credits). Provide at least an email address. Use leads_list_id to add directly to a list. - `Update-Lead` _(destructive)_ — Update an existing lead by ID. Free (no credits). - `Delete-Lead` _(destructive)_ — Delete a lead by ID. Free (no credits). - `Create-Or-Update-Lead` _(destructive)_ — Use this when the user explicitly wants to create a lead or overwrite an existing lead's fields by email. If a lead with the email exists, its fields are… - `Create-Lead-If-Missing` _(write)_ — Use this when the user wants to save a verified contact as a new lead without modifying any existing lead. If a lead with the email already exists, returns the… - `Lead-Exists` _(read)_ — Check if a lead with a given email address exists. Free (no credits). - `Save-Company` _(write)_ — Save a company as a lead in your Hunter account. Free (no credits). - `List-Leads-Lists` _(read)_ — List all leads lists in your Hunter account. Free (no credits). - `Get-Leads-List` _(read)_ — Get a single leads list by ID. Free (no credits). - `Create-Leads-List` _(write)_ — Create a new leads list. Free (no credits). - `Update-Leads-List` _(destructive)_ — Rename an existing leads list. Overwrites the existing list name; the previous name cannot be recovered from the API. If the user declines the rename, offer to… - `Delete-Leads-List` _(destructive)_ — Delete a leads list by ID. Lists with more than 10 leads are deleted asynchronously (status 202). Free (no credits). - `Merge-Leads-Lists` _(destructive)_ — Merge one leads list into another. All leads from the source list are moved to the destination list, and the source list is deleted. Free (no credits). - `List-Company-Lists` _(read)_ — List the company lists in your Hunter account, ordered with the most recently created first. Each list reports its `type` — `static` (a fixed set of companies… - `Get-Company-List` _(read)_ — Get a single company list by ID, including its `name`, `type` (static or dynamic), `filters` (for dynamic lists), `company_list_folder_id`, `created_at`, and… - `Create-Company-List` _(write)_ — Create a new company list. Provide a `name`. By default the list is `static` (you add companies to it yourself). To create a `dynamic` list that automatically… - `Update-Company-List` _(destructive)_ — Update a company list, identified by ID. You can rename it (`name`), move it to a different folder (`company_list_folder_id`), and — for a dynamic list —… - `Delete-Company-List` _(destructive)_ — Delete a company list by ID. Empty lists and dynamic lists are deleted immediately (status 204). A static list that still contains companies is deleted… - `List-Company-List-Folders` _(read)_ — List the company-list folders in your Hunter account, ordered with the most recently created first. Folders group company lists; each folder reports its… - `Create-Company-List-Folder` _(write)_ — Create a new company-list folder. Provide a `name` and a `color`. `color` must be one of the allowed Hunter folder colors (hex without a leading '#'): 374151,… - `Update-Company-List-Folder` _(destructive)_ — Update a company-list folder, identified by ID. You can rename it (`name`) and change its `color`. `color` must be one of the allowed Hunter folder colors (hex… - `Delete-Company-List-Folder` _(destructive)_ — Delete a company-list folder by ID. Deleting a folder does not delete the company lists filed in it — each affected list keeps existing and simply becomes… - `Favorite-Company-List` _(write)_ — Mark a company list as a favorite, identified by ID. Favoriting is a reversible flag (you can unfavorite it later); it does not change the list's contents. The… - `Unfavorite-Company-List` _(write)_ — Remove the favorite flag from a company list, identified by ID. This only clears the favorite marker; the list and its contents are untouched, and you can… - `Add-Company-To-List` _(write)_ — Add a company to a static company list (save the company to the list). Identify the list by `company_list_id` and the company by `company_id` (a company… - `Remove-Company-From-List` _(write)_ — Remove a company from a static company list. Identify the list by `company_list_id` and the company by `company_id`. This removes only the membership link… - `List-Connected-Apps` _(read)_ — List the connected apps (third-party integrations such as HubSpot, Pipedrive, Google Sheets, or a custom SMTP/IMAP inbox) linked to your Hunter account. Each… - `Get-Connected-App` _(read)_ — Get a single connected app by ID, including its `attribute_mappings` — the list of `target_field` ↔ `source_field` pairs that map Hunter fields to the… - `List-Custom-Attributes` _(read)_ — List all custom attributes for leads. Free (no credits). - `Get-Custom-Attribute` _(read)_ — Get a single custom attribute by ID. Free (no credits). - `Create-Custom-Attribute` _(write)_ — Create a new custom attribute for leads. Free (no credits). - `Update-Custom-Attribute` _(destructive)_ — Rename an existing custom attribute. Overwrites the existing label everywhere the attribute is used; the previous label cannot be recovered from the API. If… - `Delete-Custom-Attribute` _(destructive)_ — Delete a custom attribute by ID. Free (no credits). - `List-Message-Templates` _(read)_ — List the saved message templates in the user's Hunter account. When the user is drafting a sequence step (an introduction message or a follow-up), list the… - `Get-Message-Template` _(read)_ — Retrieve a single saved message template by ID — its full `subject`, `body`, and `message_format` — for example to preview it before reusing it in a sequence… - `Create-Message-Template` _(write)_ — Create a reusable message template — including saving a message draft written in chat (e.g. a sequence introduction or follow-up the user liked) as a new… - `Update-Message-Template` _(destructive)_ — Update a saved message template's name, subject, body, or message format. Only the fields provided are changed; the previous values are overwritten and cannot… - `Delete-Message-Template` _(destructive)_ — Delete a saved message template by ID. Deleting is permanent and cannot be undone from the API. Sequence steps already created from this template keep their… - `List-Lead-Tags` _(read)_ — List the lead tags in your Hunter account — call this BEFORE tagging leads or creating a new tag, so an existing tag can be reused instead of creating a… - `Create-Lead-Tag` _(write)_ — Create a new lead tag. Before creating one, call List-Lead-Tags and prefer reusing an existing tag with the same meaning (e.g. "Customers" vs "customer")… - `Update-Lead-Tag` _(destructive)_ — Update a lead tag, identified by ID: rename it (`name`) or change its `color`. Renaming overwrites the previous name everywhere the tag is applied, and the old… - `Delete-Lead-Tag` _(destructive)_ — Delete a lead tag by ID. Deleting a tag removes it from EVERY lead it is applied to (the tag's assignments are destroyed with it); the leads themselves are… - `Add-Tag-To-Lead` _(write)_ — Add a tag to a lead, identified by `lead_id`. Provide either `tag_id` (an existing tag) or `tag_name`; with `tag_name`, a tag that does not exist yet is… - `Remove-Tag-From-Lead` _(write)_ — Remove a tag from a single lead, identified by `lead_id` and `tag_id`. This only detaches the tag from that lead; the tag itself is not deleted and stays… - `List-Leads-List-Folders` _(read)_ — List the leads-list folders in your Hunter account, ordered with the most recently created first. Folders group leads lists and are visible to the whole team —… - `Create-Leads-List-Folder` _(write)_ — Create a new leads-list folder to group leads lists — worth suggesting once the account has many lists. Provide a `name`; `color` is optional and must be one… - `Update-Leads-List-Folder` _(destructive)_ — Update a leads-list folder, identified by ID. You can rename it (`name`) and change its `color`. `color` must be one of the allowed Hunter folder colors (hex… - `Delete-Leads-List-Folder` _(destructive)_ — Delete a leads-list folder by ID. Deleting a folder does not delete the leads lists filed in it — each affected list keeps existing and simply becomes unfiled… - `Favorite-Leads-List` _(write)_ — Mark a leads list as a favorite, identified by ID. Favorites are a personal flag for the current user, and a favorited list is a strong signal of their… - `Unfavorite-Leads-List` _(write)_ — Remove the favorite flag from a leads list, identified by ID. This only clears the current user's personal favorite marker; the list and its contents are… - `Bulk-Move-Leads` _(destructive)_ — Move many leads at once from one static leads list to another. Both lists must be static (not dynamic) and different; `lead_ids` optionally narrows the move to… - `Bulk-Delete-Leads` _(destructive)_ — Delete many leads at once, selected by explicit `lead_ids` and/or by a whole `leads_list_id`. Deleting leads is permanent and cannot be undone. Selections of… - `Bulk-Move-Companies` _(destructive)_ — Move many companies at once from one static company list to another. Both lists must be static (not dynamic) and different; `company_ids` optionally narrows… - `Bulk-Copy-Companies` _(destructive)_ — Copy many companies at once into a static company list, leaving the source selection untouched. Select the companies by explicit `company_ids` and/or by a… - `Bulk-Delete-Companies` _(destructive)_ — Delete many companies at once, selected by explicit `company_ids` and/or by a whole `company_list_id`. Deleting companies is permanent and cannot be undone; a… - `Find-People` _(read)_ — Count the people that can be extracted from companies — the bridge from Find-Companies to actual contacts; call it right after a Find-Companies result when the… - `List-Saved-Searches` _(read)_ — List the Discover searches saved in your Hunter account — a good opening move at the start of a prospecting conversation ('want to rerun one of your saved… - `Get-Saved-Search` _(read)_ — Get one saved Discover search by ID — typically to rerun it. Read the stored `filters` payload and describe it back to the user as a natural-language `query`… - `Create-Saved-Search` _(write)_ — Create a saved Discover search: store the current filter set under a name so the search can be rerun later. Stores the `filters` payload verbatim and returns… - `Delete-Saved-Search` _(destructive)_ — Delete a saved Discover search by ID, permanently. Deletion cannot be undone through the API. Because saved searches have no update endpoint,… - `Push-Leads-To-CRM` _(destructive)_ — Push Hunter leads into the CRM behind a connected app (lead-syncing providers: HubSpot, Pipedrive, Salesforce, Zapier, and Zoho). List targets with… - `List-Webhooks` _(read)_ — List the webhooks configured on the Hunter account — useful for integration debugging: is my webhook configured, which event does it listen to, and where does… - `Update-Webhook` _(destructive)_ — Update an existing webhook, re-pointing it to a different `target_url` (the endpoint Hunter POSTs to) and/or subscribing it to a different `event` (one of… - `Get-Usage` _(read)_ — Report the team's quota usage for the current billing period. Call this proactively BEFORE any large credit-consuming action (a Domain-Search loop over many… - `List-API-Keys` _(read)_ — List the Hunter API keys of the connected user. Keys are scoped to the requesting user, not the team — another team member's keys are never visible here. Key… - `Create-API-Key` _(destructive)_ — Create a new Hunter API key for the connected user, optionally with a name (names must be unique among the user's keys; a user can have at most 100 keys).… - `Delete-API-Key` _(destructive)_ — Delete one of the connected user's Hunter API keys by ID, permanently. Deletion is immediate and irreversible: anything still authenticating with the key —… - `Plan-Prospecting-Flow` _(read)_ — Use this when the user gives a natural-language prospecting brief (e.g. "Find 20 marketing leads at fintech companies in Berlin") and wants a step-by-step plan… - `Report-API-Feedback` _(write)_ — Report any problem you hit while using Hunter's API or tools — use this PROACTIVELY and liberally. Call it whenever: a tool or endpoint you expected doesn't… --- ## 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: 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__ 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)