Atoms MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ATOMS_API_KEY | Yes | Your Atoms API key | |
| ATOMS_API_URL | No | Override the API base URL | https://atoms-api.smallest.ai/api/v1 |
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 | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_call_logsA | Get call logs for your organization. Filter by status, type, date range, agent name, or phone number. Returns call metadata, duration, cost, errors, and transcript summary. |
| get_agentsA | List AI agents in your organization. Returns agent configuration including voice, LLM model, language settings, and call statistics. |
| get_usage_statsB | Get call usage statistics for your organization — total calls, duration, costs, and status breakdown. Useful for understanding usage patterns and costs. |
| debug_callA | Deep-dive into a single call for debugging. Returns full transcript, errors, timing, cost breakdown, post-call analytics, and agent config at time of call. Use a callId (e.g. CALL-1234567890-abc123). |
| get_campaignsA | List outbound calling campaigns for your organization. Shows campaign status, progress, agent used, and audience size. |
| create_agentA | Create a new AI agent in your organization. Returns the created agent's ID. The agent prompt is set separately via update_agent_prompt after creation. |
| update_agent_promptB | Update an agent's system prompt / instructions. Pass the full new prompt text. This updates the agent's workflow with the new prompt. |
| update_agent_configA | Update an agent's configuration (name, language, first message, voice settings, etc.). Only provided fields are updated. To update the agent's prompt/instructions, use update_agent_prompt instead. |
| delete_agentA | Archive (soft-delete) an agent by its ID. The agent will no longer be active but can be recovered. |
| make_callB | Initiate an outbound phone call using a specific agent. The agent will call the provided phone number and follow its configured prompt. |
| get_phone_numbersA | List phone numbers acquired by your organization. Shows number, country, capabilities, and which agent it's assigned to. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| platform-overview | Overview of the Atoms platform, key concepts, and terminology |
TDQS
Scored across 11 tools
Each tool maps to a distinct resource or action—agent CRUD, call logs, aggregate usage, single-call debugging, campaigns, phone numbers, and outbound calls. The call-related tools are clearly separated by scope (list vs. aggregate vs. single-call deep-dive), so an agent can reliably select the right one.
All names follow a consistent snake_case verb_noun pattern: get_* for read operations, create_/update_/delete_ for agent mutations, and make_call/debug_call for actions. There are no mixed conventions or vague verbs.
11 tools is well-scoped for an AI-calling platform: enough to cover meaningful agent and call workflows without redundancy. The set feels deliberately chosen rather than bloated or thin.
Agent lifecycle is fully covered with create, list, config update, prompt update, and delete, and call workflows are covered via make_call, get_call_logs, debug_call, and get_usage_stats. Campaigns and phone numbers are read-only, and there is no singular get_agent by ID, but these are minor gaps that agents can typically work around.