swarmix-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SWARMIX_API_KEY | Yes | Your Swarmix API JWT token | |
| SWARMIX_API_URL | No | The Swarmix API URL | https://swarmix.co |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_agentsA | List all AI outreach agents with their status, platform, and last run time |
| get_agent_statsA | Get performance statistics for a specific agent (connections, emails sent, open rates, etc.) |
| run_agentB | Trigger an immediate execution of an agent. The agent will run all enabled actions once. |
| pause_agentA | Pause an active agent. It will stop running scheduled actions. |
| resume_agentA | Resume a paused agent. It will start running scheduled actions again. |
| search_leadsA | Search and filter leads in the database. Returns paginated results with name, email, company, status, and channel history. |
| get_funnelA | Get the prospect funnel for an agent showing conversion at each stage (discovered -> contacted -> engaged -> replied -> converted) |
| get_activityB | Get recent activity log entries for an agent or all agents. Shows what actions were taken and their results. |
| get_dashboardB | Get an overview of all products, agents, and lead counts across the entire Swarmix account |
| setup_businessA | Set up a complete outreach autopilot for a business. Creates a product and deploys AI agents for the recommended channels based on business type. Available types: coach, agency, realestate, recruitment, freelancer, other. |
| create_productB | Create a new product/business to manage outreach for. The AI will analyze the website to learn the value proposition and audience. |
| create_agentA | Create a new AI outreach agent for a specific channel. Requires a product ID. Available platforms: linkedin, email, x, instagram, blog. |
| list_templatesA | List available business templates for the setup_business tool. Shows business types with their default channels and descriptions. |
| get_creditsB | Get current credit balance, monthly spending cap, and usage for the account. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Tools have clearly distinct purposes with minimal overlap. While create_agent and setup_business both create agents (one manual, one automated), descriptions clearly differentiate them. Similarly, get_activity (logs), get_agent_stats (metrics), get_funnel (conversion stages), and get_dashboard (overview) target different aspects of monitoring without confusion.
Perfectly consistent verb_noun snake_case pattern throughout: create_agent, create_product, get_credits, list_agents, pause_agent, search_leads, etc. All 14 tools follow the same structural convention with clear action-oriented verbs.
14 tools is ideal for an outreach automation platform—covering business setup, agent lifecycle management (CRUD equivalents), execution controls, analytics/monitoring, and lead management without bloat. Each tool earns its place in the workflow.
Strong coverage of the outreach domain: business/product setup, agent deployment, execution (run/pause/resume), multi-layered analytics (activity logs, stats, funnel, dashboard), and lead search. Minor gaps like missing explicit update_agent or delete_agent operations prevent a perfect score.