SMALLEST TOOLS

70 tools from the Smallest MCP Server, categorised by risk level.

View the Smallest policy →

READ TOOLS

51
compare_version_metrics A/B compare call performance metrics between two published versions. Shows total calls, answered calls, average duration, completion rate, total co... debug_call Get detailed info about a single call — use this to check call status, debug failures, or get transcripts. Returns call status, failure reasons, er... diff_versions Compare two published versions side-by-side to see exactly what changed between them. Shows unchanged sections and detailed diffs for modified conf... duplicate_agent Duplicate an existing agent, creating a new agent with the same configuration. The new agent is created in the target organization (defaults to you... get_agent Get full details for a single agent by ID, including voice config, model, prompt, language, call behavior settings, and workflow type. get_agent_performance Compare agent performance — shows each agent's total calls, average duration, completion rate, and cost. Use to find top and bottom performers. get_agent_prompt Read the current system prompt / instructions for an agent. Returns the prompt text and any configured tools. get_agents List AI agents in your organization. Returns agent configuration including voice, LLM model, language settings, and call statistics. Supports pagin... get_attempt_cohorts Get attempt cohort analysis — shows volume and success rate by attempt number (1st attempt, 2nd attempt, etc.). Useful for optimizing retry strateg... get_audience Get details for a specific audience by ID, including name, description, and phone number column name. get_audience_members List members (contacts) in an audience with pagination. Each member has a data object containing their phone number and any other fields from the o... get_audiences List all audiences in your organization. Shows audience name, member count, linked campaigns, and the phone number column name. Audiences are conta... get_auto_reload Get the current auto-reload configuration for your organization. Auto-reload automatically adds credits when your balance drops below a threshold. get_billing_alerts Get the current billing alert configuration for your organization. Billing alerts notify you when credit usage reaches specified thresholds. get_call_counts_by_day Get call count per day as a simple histogram. Shows { day, count } pairs. get_call_outcomes Get call outcome distribution over time — daily breakdown of completed, failed, and no-answer calls, plus totals. get_call_start_distribution Get call start distribution by hour for a specific date — shows how many calls started in each hour (0-23). Useful for scheduling and capacity plan... get_call_volume Get call volume over time as a daily timeseries. Shows how many calls were made each day in the date range. get_campaign Get detailed information about a specific campaign, including status, execution progress, events timeline, and metrics (participants, contacts call... get_campaigns List outbound calling campaigns for your organization. Shows campaign status, progress, agent used, audience, retry config, and execution details. get_concurrency Get concurrent call counts for a specific date — minute-by-minute concurrency data plus per-agent max concurrency. Shows how many calls were runnin... get_credit_balance Get the current credit balance for your organization, including plan information and enterprise status. get_credit_ledger Get the credit transaction history (ledger) for your organization. Shows purchases, usage deductions, bonuses, admin adjustments, coupon credits, a... get_credit_usage Get daily credit/cost usage over time — shows credits consumed each day and total for the period. Useful for billing and budget tracking. get_daily_summary Get summary statistics for a specific date — total calls, completed, failed, no-answer, in-progress, in-queue, average duration, and total cost. get_dashboard Get the full analytics dashboard in a single call — includes summary KPIs, call volume timeseries, call outcomes, pickup rates by number, hourly pe... get_draft Get detailed information about a specific draft, including its latest revision, edit history (which sections changed per revision), and resolved co... get_draft_diff Compare a draft against its source version (or a specific published version) to see what changed. Shows unchanged sections and detailed diffs for m... get_duration_stats Get call duration statistics — average, median, min, max, and p95 duration. Shows how long calls typically last. get_hourly_performance Get performance metrics by hour of day (0-23). Shows call count, average duration, and cost per hour. Useful for identifying peak hours. get_invoices List all invoices for your organization from Stripe. Shows invoice details including amounts, status, and dates. get_payment_methods List all payment methods (cards) configured for your organization. Shows card brand, last 4 digits, expiry, and which is the default. get_phone_number_trends Get per-phone-number daily trends — calls, pickup rate, and average duration per day for each number. get_phone_numbers List phone numbers acquired by your organization. Shows product ID (needed for make_call's from_product_id), number, country, provider, and which a... get_pickup_rates Get pickup rate by phone number — shows total calls, answered calls, and pickup rate for each outbound number. Useful for optimizing caller IDs. get_plans List available plans and optionally get the features included in a specific plan. Use this to understand plan pricing, included features, and credi... get_usage_breakdown Get a breakdown of credit usage by feature and product scope for your organization. Shows how credits are being consumed across different services ... get_usage_stats Get call usage statistics for your organization — total calls, pickup rate, duration, costs, and unique users reached. Each metric includes current... get_version Get full details for a specific published version, including its resolved configuration across all sections (voice, LLM, language, prompt, detectio... get_voices List available voices for agents. Returns voice IDs, names, gender, language, and supported models. Use the voiceId with update_agent_config's synt... get_weekly_trends Get weekly aggregated metrics — calls, average duration, and cost per week. Good for spotting week-over-week trends. list_calls Search and list calls across your organization. Use this to browse calls with filters (by status, type, date range, agent, phone number, campaign).... list_drafts List all active (unpublished) drafts for a versioned agent. Shows draft name, revision count, last editor, and last edit time. Useful to see what c... list_versions List all published versions for a versioned agent, sorted by version number (newest first). Shows version number, label, who published it, whether ... make_call Initiate an outbound phone call using a specific agent. The agent will call the provided phone number and follow its configured prompt. Only teleph... pause_campaign Pause a running campaign. Active calls in progress will complete, but no new calls will be initiated. Use start_campaign to resume. search_audience_members Search for members in an audience. Supports general search across all fields, or field-specific search (e.g. by phone number or name). Returns up t... test_draft Initiate a test call using a draft's configuration (before publishing). Supports webcall, chat, and telephony modes. Use this to verify draft chang... test_version Initiate a test call using a specific published version's configuration. Supports webcall, chat, and telephony modes. Use this to test a non-active... transcribe_audio Transcribe an audio file to text using Smallest AI's Pulse STT. Supports 32+ languages. IMPORTANT: Always ask the user what language the audio is i... validate_coupon Check if a coupon code is valid and see how many credits it would give. Does not redeem the coupon — use redeem_coupon to actually apply it.

WRITE TOOLS

14
activate_version Activate a specific published version, making it the live configuration for the agent. Use this to roll back to a previous version or switch betwee... add_audience_members Add members (contacts) to an existing audience. Each member must include the phone number column defined when the audience was created (use get_aud... create_agent Create a new AI agent in your organization. The agent is created as a single_prompt agent with gpt-4.1 model and daniel voice (waves_lightning_v3_1... create_campaign Create a new outbound calling campaign. Requires an agent and an audience (contact list). The campaign is created in draft status unless a schedule... export_campaign_logs Export call logs for a campaign. Returns detailed call data grouped by audience member, including call status, duration, recording URL, transcript,... invite_member Invite one or more users to your organization by email. They'll receive an invitation email to join. Requires admin role on the organization. You c... publish_draft Publish a draft as a new version and activate it, making changes live. Use after update_agent_config or update_agent_prompt creates a draft on a ve... redeem_coupon Redeem a coupon code to add credits to your organization's balance. Use validate_coupon first to check the code before redeeming. rename_draft Rename a draft to give it a more descriptive name. Useful when working with multiple drafts to keep them organized. text_to_speech Convert text to speech audio using Smallest AI's Lightning TTS. Saves the audio file to the specified path. IMPORTANT: Always ask the user where to... update_agent_config Update an agent's configuration (name, language, first message, voice settings, model, variables, etc.). Only provided fields are updated. To updat... update_agent_prompt Update an agent's system prompt / instructions. Pass the full new prompt text. Only works for single_prompt agents. Optionally update the first mes... update_billing_alerts Configure billing alert settings. Set up to 3 credit usage thresholds that trigger email notifications. Alerts can be sent to additional email addr... update_version Update metadata on a published version — label, description (release notes), or pin status. Pinned versions are highlighted in the version list for...

DESTRUCTIVE TOOLS

4

EXECUTE TOOLS

1
How many tools does the Smallest MCP server have? +

The Smallest MCP server exposes 70 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Smallest tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Smallest server.

What risk categories do Smallest tools fall into? +

Smallest tools are categorised as Read (51), Write (14), Destructive (4), Execute (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.