# Seamless MCP MCP Server > **Seamless MCP MCP Server** is a hosted, multitenant Model Context Protocol (MCP) server run by **MewCP** (https://mewcp.com), giving AI agents managed access to Seamless 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/seamless-mcp > MewCP docs: https://docs.mewcp.com > Full catalog: https://mewcp.com/llms.txt --- ## About Seamless.AI combines a database of 1.3B+ verified professional contacts and 121M+ companies with B2B prospecting and outreach automation. Find decision-makers, discover verified business emails and direct phone numbers, enrich contact and company records, build targeted lead lists, research prospects, and create personalized email campaigns. --- ## Details - Server ID: `seamless-mcp` - Version: 1.0.0 - 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 — Seamless MCP has to be in the toolset first. In order: 1. Add Seamless MCP to your toolset at https://mewcp.com/mcp/seamless-mcp 2. Connect your Seamless 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 (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. - `search_contacts` _(read)_ — Search the Seamless.AI database for contacts matching filters like company, title, seniority, and location. At least one filter (or savedSearchId) is required;… - `search_companies` _(read)_ — Search the Seamless.AI database for companies matching filters like name, domain, industry, size, and revenue. Returns a paginated table of matching companies.… - `lookup_locations` _(read)_ — Search the location vocabulary for the exact spellings a location filter will match, most common first. Use this whenever you are unsure how the data spells a… - `research_contacts` _(write)_ — Research (enrich) contacts to get verified emails, phone numbers, job history, and other data. Consumes credits. Provide searchResultIds from a previous… - `poll_contact_research` _(read)_ — Poll for contact research results. Pass requestIds from research_contacts. Returns each result with a status: done, error, missing, or not found. Poll again if… - `research_companies` _(write)_ — Research (enrich) companies to get verified details like revenue, size, and technologies. Consumes credits. Provide searchResultIds from a previous search OR a… - `poll_company_research` _(read)_ — Poll for company research results. Pass requestIds from research_companies. Returns each result with a status: done, error, or missing. Poll again if any… - `start_autopilot` _(write)_ — Consumes credits upfront for every requested result; unused credits are restored when the run finishes or is cancelled. Before calling, confirm with the user… - `get_autopilot_status` _(read)_ — Returns status and progress for an Autopilot (automated search) run. Prefer tasks/get for runs started as an MCP task. - `get_autopilot_results_url` _(read)_ — Returns presigned download URLs for Autopilot result CSV files. URLs expire in 300 seconds; call again for fresh links. Never streams file content. - `cancel_autopilot` _(destructive)_ — Cancel a running Autopilot. Irreversible; the current batch may finish before the run stops. Already-researched records are kept and unused credits are… - `get_credits` _(read)_ — Get current credit balance and usage for the authenticated user. The seamless://credits resource provides the same data. When linking to the Seamless web app,… - `get_my_contacts` _(read)_ — Retrieve previously saved/researched contacts for the authenticated user within a date range (max 30 days). Defaults to the last 30 days if no dates are… - `update_my_contact` _(destructive)_ — Update saved contacts. Currently manages which lists they belong to: listAction "add" (default) keeps existing lists, "remove" drops only the supplied lists,… - `get_my_companies` _(read)_ — Retrieve previously saved/researched companies for the authenticated user within a date range (max 30 days). Defaults to the last 30 days if no dates are… - `update_my_company` _(destructive)_ — Update saved companies. Currently manages which lists they belong to: listAction "add" (default) keeps existing lists, "remove" drops only the supplied lists,… - `list_saved_searches` _(read)_ — List saved searches, or get a specific saved search by ID. When id is provided, returns that saved search with its filter values. Otherwise returns a table of… - `create_saved_search` _(write)_ — Save a set of search filters as a named saved search for later reuse. Returns the created saved search with its ID. - `update_saved_search` _(destructive)_ — Update an existing saved search name, filters, or sort options. Returns the updated saved search. When values is provided it replaces the saved filters… - `delete_saved_search` _(destructive)_ — Permanently delete a saved search by its ID. This cannot be undone. Use list_saved_searches to find saved search IDs. - `get_lists` _(read)_ — List all contact lists, or get a specific list by ID. When listId is provided, returns that list with contact count. Otherwise returns a table of all lists. To… - `create_list` _(write)_ — Create a new contact list. Returns the created list with its ID. Lists organize saved contacts: add contacts that are already saved by passing the new list ID… - `update_list` _(destructive)_ — Rename an existing contact list. Returns the updated list. - `delete_list` _(destructive)_ — Permanently delete a contact list. This removes the list but does not delete the contacts in it. Use get_lists to find list IDs. - `list_campaigns` _(read)_ — List campaigns, or get a specific campaign by ID/identifier. When campaignId or campaignIdentifier is provided, returns detailed campaign info including steps,… - `create_campaign` _(write)_ — Create a new campaign. The recommended approach is to include `steps` and `contactIds` inline rather than making separate create_campaign_step and… - `add_contacts_to_campaign` _(destructive)_ — Add saved contacts to an EXISTING campaign. Prefer passing contactIds inline via create_campaign when building a new campaign. Use this tool only when adding… - `list_campaign_steps` _(read)_ — List all steps in a campaign, including their type, status, delay, and template content. Returns a table of step details. - `create_campaign_step` _(write)_ — Add a new step to an EXISTING campaign. Prefer passing steps inline via create_campaign when building a new campaign. Use this tool only when adding steps to a… - `update_campaign_step` _(destructive)_ — Update an existing campaign step. Modify its name, delay, content, or position. Content can be switched to a saved template (templateId), static inline content… - `delete_campaign_step` _(destructive)_ — Delete a draft step from a campaign. Remaining steps are automatically renumbered. Returns the deleted step and the remaining steps with their new step… - `start_campaign` _(destructive)_ — Start a draft campaign so it begins working its contacts and sending its email steps. Only a draft campaign can be started. The campaign must have: (1) a… - `pause_campaign` _(destructive)_ — Pause an active campaign. No further steps run or emails send until it is resumed with resume_campaign. Returns the campaign ID and new status. - `resume_campaign` _(destructive)_ — Resume a paused campaign so it continues working its contacts and sending its email steps. Only a paused campaign can be resumed. The campaign must have: (1) a… - `complete_campaign` _(destructive)_ — Mark an active campaign as completed, ending it for all contacts. A completed campaign cannot be started, resumed, or archived again. Confirm with the user… - `archive_campaign` _(destructive)_ — Archive a draft, active, or paused campaign, stopping it and hiding it from the active campaign list. Restore it to draft with unarchive_campaign. Returns the… - `unarchive_campaign` _(destructive)_ — Restore an archived campaign to draft. It does not resume sending; call start_campaign afterward to run it again. Returns the campaign ID and new status. - `list_campaign_contacts` _(read)_ — List contacts in a campaign with their engagement status and current step. Returns a paginated table. - `remove_contacts_from_campaign` _(destructive)_ — Remove specific contacts from a campaign. Returns the updated campaign and contactsRemoved, the number of contacts actually removed — this is 0 when none of… - `get_campaign_metrics` _(read)_ — Get per-step engagement metrics for a campaign. Returns emails sent, opened, bounced, replied, and calls made per step. - `pause_campaign_step` _(destructive)_ — Pause an in-progress step of a campaign. Its tasks stop running until the step is resumed with resume_campaign_step. The campaign must not be completed,… - `resume_campaign_step` _(destructive)_ — Resume a paused campaign step so its tasks run again, including any email sends. The campaign must not be completed, archived, or deleted. Confirm with the… - `skip_campaign_step` _(destructive)_ — Skip an in-progress or paused campaign step, so its remaining tasks are skipped for every contact. The campaign must not be completed, archived, or deleted.… - `clone_campaign` _(write)_ — Create a copy of an existing campaign with a new name. Copies steps and configuration but not contacts. Email account links may need to be re-added via… - `update_campaign` _(destructive)_ — Update an existing campaign name, visibility settings, linked email accounts, per-account daily send limits, per-day task limits, or the daily task limit… - `delete_campaign` _(destructive)_ — Permanently delete a campaign and all its associated steps and tasks. This cannot be undone. Use list_campaigns to find campaign IDs. - `list_templates` _(read)_ — List email templates, or get a specific template by ID. When templateId is provided, returns that template with subject, body, and metadata. Otherwise returns… - `create_template` _(write)_ — Create a new email template with subject and body content. Use template variables like {first_name}, {company}, {title} for personalization — read… - `update_template` _(destructive)_ — Update an existing email template name, subject, or body. Use template variables like {first_name}, {company} for personalization (see… - `delete_template` _(destructive)_ — Permanently delete an email template by its ID. This cannot be undone. Use list_templates to find template IDs. - `list_email_accounts` _(read)_ — List connected email accounts for the authenticated user. Returns available sender addresses that can be used for sending emails and campaigns. The… - `create_email_draft` _(write)_ — Create an email draft for a contact. The draft is saved but not sent until you call send_email_draft. Returns the draft with its ID. Use list_email_accounts or… - `get_email_draft` _(read)_ — Retrieve a previously created email draft by its ID. Returns the draft content and metadata. - `update_email_draft` _(destructive)_ — Update the content of an existing email draft before sending. Returns the updated draft. MCP REINFORCEMENTS (these override and clarify the base rules — read… - `send_email_draft` _(destructive)_ — Send a previously created email draft. The email will be sent immediately. Does not consume search/research credits. Use create_email_draft first to create the… - `send_email` _(destructive)_ — Send an email directly to a contact in one step (creates and sends immediately). Does not consume search/research credits. Use template variables like… - `send_bulk_email` _(destructive)_ — Send emails to multiple contacts matching filter criteria. filters must include at least one of lists, contactIds, campaignIds, or a text query — an empty… - `log_call` _(write)_ — Log a call outcome for a contact. Records the result of a call made outside the platform (not a click-to-call feature). Use list_call_dispositions and… - `list_call_dispositions` _(read)_ — List available call disposition options (e.g. "Left Voicemail", "Connected") for the organization. Use the returned IDs when calling log_call. - `list_call_sentiments` _(read)_ — List available call sentiment options (e.g. "Positive", "Neutral", "Negative") for the organization. Use the returned IDs when calling log_call. - `get_activity_feed` _(read)_ — Get the engagement activity feed showing email opens, replies, bounces, calls, and other events. Returns a paginated list of activity events. - `list_tasks` _(read)_ — List tasks, or get a specific task by ID. When taskId is provided, returns detailed task info including status, contact, and campaign details. Otherwise… - `start_task` _(destructive)_ — Run a to-do or scheduled task now. For an automatic email task this sends the email immediately. Confirm with the user before calling. Returns the task ID and… - `pause_task` _(destructive)_ — Pause a to-do, scheduled, or errored task so it does not run until it is unpaused with unpause_task. Returns the task ID and the action taken. - `unpause_task` _(destructive)_ — Unpause a paused task so it is due again. A campaign email task can send once it is due. Confirm with the user before calling. Returns the task ID and the… - `complete_task` _(destructive)_ — Mark a to-do, paused, scheduled, or errored task as completed, for example after the user made the call or did the work themselves. This does not send… - `skip_task` _(destructive)_ — Skip a to-do, paused, pending, scheduled, or errored task so it is not done for this contact. Confirm with the user before calling. Returns the task ID and the… - `cancel_task` _(destructive)_ — Cancel a task that has not finished, so it never runs. Confirm with the user before calling. Returns the task ID and the action taken. - `create_task` _(write)_ — Create a standalone task (email, call, or custom action) for a contact. This is separate from campaign steps — use create_campaign_step for campaign workflows.… - `update_task` _(destructive)_ — Update an existing task. Modify its name, due date, description, priority, or status. Returns the updated task. - `delete_task` _(destructive)_ — Permanently delete a task. This cannot be undone. Use list_tasks to find task IDs. - `list_email_footers` _(read)_ — List email footers available to the authenticated user for use in campaigns and templates. Returns a paginated list of footers with their IDs. The… - `send_email_preview` _(destructive)_ — Send a preview of an email to a specified address for review before launching a campaign. Typically used to send to yourself. Does not send to contacts or… --- ## 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)