APIFleet
Server Details
Build and run AI phone agents: provider matrix, call-cost estimates, config checks, call management.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 67 tools
Most tools target a clear resource+action pair (get_/list_/create_/update_/delete_ per entity), but voice-related tools overlap confusingly: get_assistant_voice_presets, list_voice_presets, list_tts_voices, get_tts_settings and list_tts_rates require careful reading to distinguish, and the simulation family (simulation, persona, scenario, run, batch) is dense. An agent can eventually pick right but boundaries are not crisp.
Two conventions coexist: a public-tools block prefixed apifleet_ (snake_case) and the rest bare verb_noun snake_case. Within each group the pattern holds, but the mixed prefixing plus irregular names like start_simulation_batch and set_assistant_knowledge break predictability.
67 tools is far above the 3-15 sweet spot and heavy even for a broad voice-agent platform. The simulation sub-domain alone spans 15+ tools, and numerous read-only billing/voice metadata tools could be consolidated.
Core lifecycle coverage is strong: assistants, knowledge, tools, webhooks, simulations/personas/scenarios/runs, numbers, keys, billing and calls all have list/get/create/update/delete variants. Minor gaps exist (no get_call or cancel_simulation_run, no standalone get_number), but agents have workarounds.
Available Tools
67 toolsapifleet_check_assistant_configARead-onlyIdempotentInspect
Public, no key: seven static configuration checks. Send a redacted configuration without secrets or customer data. No save, credential verification, full API validation or call-quality certification occurs.
Inputs: config (required).
apifleet_estimate_call_costARead-onlyIdempotentInspect
Public, no key: calculate USD platform fees plus caller-supplied blended provider/carrier rates. An estimate, not a provider quote or invoice. Does not place a call.
Inputs: seconds (required), carrier_usd_per_minute, provider_usd_per_minute.
apifleet_get_provider_matrixARead-onlyIdempotentInspect
Public, no key: discover implemented voice and carrier integrations, setup boundaries, platform pricing and documentation. No provider request or call is made.
Inputs: no named parameters.
bind_numberAInspect
Bind an existing carrier number to a workspace assistant. This changes incoming call routing; configure the carrier webhook separately.
Inputs: data (required), number (required).
check_entitlementsARead-onlyIdempotentInspect
Read the workspace prepaid balance and funding path. Does not start a checkout or call.
Inputs: no named parameters.
create_api_keyAInspect
Create a new full workspace key. The secret is returned once. Store it privately; never put it in public client code.
Inputs: data (required).
create_assistantBInspect
Create a assistant. Saving configuration does not place a call. The REST response includes revision, configuration and attached resource identifiers.
Inputs: data (required).
create_browser_test_tokenAInspect
Issue a short-lived browser voice-test URL. Opening its WebSocket can incur usage. Never publish the returned token.
Inputs: id (required), data (required).
create_knowledge_documentAInspect
Create a knowledge document. Attach documents separately to use them in an assistant. Total injected knowledge has a 200 KiB limit.
Inputs: data (required).
create_outbound_callADestructiveInspect
Place a real telephone call. Ask the user to approve recipient, caller number and expected usage first. Billing/provider/carrier checks are the same as REST. No automatic retry or universal idempotency guarantee.
Inputs: data (required), confirm (required).
create_simulationCInspect
Create a simulation.
Inputs: data (required).
create_simulation_personaCInspect
Create a simulation persona.
Inputs: data (required).
create_simulation_scenarioCInspect
Create a simulation scenario.
Inputs: data (required).
create_toolBInspect
Create a tool. Creating a tool returns its signing secret once. Configuring a tool does not invoke its URL; attached tools can call it during conversations.
Inputs: data (required).
create_webhookAInspect
Create a webhook. Creation returns a signing secret once; verify delivery signatures against the raw body. Events may be retried.
Inputs: data (required).
delete_assistantADestructiveIdempotentInspect
Delete this assistant. Review the identifier before deleting; the change cannot be undone.
Inputs: id (required), if_revision.
delete_knowledge_documentBDestructiveIdempotentInspect
Delete this knowledge document. Review the identifier before deleting; the change cannot be undone.
Inputs: id (required).
delete_recordingADestructiveIdempotentInspect
Permanently remove a call recording. The call log remains. Confirm the identifier before deleting.
Inputs: id (required).
delete_simulationBDestructiveIdempotentInspect
Delete this simulation. Review the identifier before deleting; the change cannot be undone.
Inputs: id (required).
delete_simulation_personaADestructiveIdempotentInspect
Delete this simulation persona. Review the identifier before deleting; the change cannot be undone.
Inputs: id (required).
delete_simulation_runADestructiveIdempotentInspect
Delete a completed simulation result. Running runs may reject deletion.
Inputs: id (required).
delete_simulation_scenarioADestructiveIdempotentInspect
Delete this simulation scenario. Review the identifier before deleting; the change cannot be undone.
Inputs: id (required).
delete_toolBDestructiveIdempotentInspect
Delete this tool. Review the identifier before deleting; the change cannot be undone.
Inputs: id (required).
delete_webhookADestructiveIdempotentInspect
Delete this webhook. Review the identifier before deleting; the change cannot be undone.
Inputs: id (required).
get_assistantARead-onlyIdempotentInspect
Get one assistant belonging to this workspace.
Inputs: id (required).
get_assistant_voice_presetsBRead-onlyIdempotentInspect
Read voices compatible with this assistant configuration.
Inputs: id (required).
get_billing_policyARead-onlyIdempotentInspect
Read the actual workspace policy. Internal exempt workspaces can differ from the public tariff.
Inputs: no named parameters.
get_knowledge_documentARead-onlyIdempotentInspect
Get one knowledge document belonging to this workspace.
Inputs: id (required).
get_metricsBRead-onlyIdempotentInspect
Read the authenticated workspace metrics snapshot. Metrics may reset with the application process and are not a complete billing ledger.
Inputs: no named parameters.
get_simulationBRead-onlyIdempotentInspect
Get one simulation belonging to this workspace.
Inputs: id (required).
get_simulation_personaBRead-onlyIdempotentInspect
Get one simulation persona belonging to this workspace.
Inputs: id (required).
get_simulation_runBRead-onlyIdempotentInspect
Read a run, its evaluations and linked call when available.
Inputs: id (required).
get_simulation_scenarioBRead-onlyIdempotentInspect
Get one simulation scenario belonging to this workspace.
Inputs: id (required).
get_tts_settingsBRead-onlyIdempotentInspect
Read supported provider voice settings and validation ranges.
Inputs: provider.
get_walletARead-onlyIdempotentInspect
Read available, reserved and total prepaid funds, policy, funding availability and runtime enforcement. Amounts ending in microusd are integer millionths of a USD.
Inputs: no named parameters.
get_waveformBRead-onlyIdempotentInspect
Read recording waveform metadata and available audio channels.
Inputs: id (required).
list_api_keysARead-onlyIdempotentInspect
List this workspace API-key metadata. Full key values cannot be retrieved.
Inputs: no named parameters.
list_assistantsBRead-onlyIdempotentInspect
List assistants in the authenticated workspace.
Inputs: no named parameters.
list_balance_activityBRead-onlyIdempotentInspect
Read balance activity and pagination cursor. Funding is credited only after verified payment processing.
Inputs: limit, before.
list_callsARead-onlyIdempotentInspect
Read call logs, summary statistics and pagination. Each row may contain transcript, analysis, costs and recording links; recordings require separate authentication.
Inputs: page, sort, limit, model, +9 more.
list_knowledge_documentsCRead-onlyIdempotentInspect
List knowledge in the authenticated workspace.
Inputs: no named parameters.
list_numbersARead-onlyIdempotentInspect
List number bindings. This does not buy phone numbers from a carrier.
Inputs: no named parameters.
list_paymentsARead-onlyIdempotentInspect
Read confirmed and pending workspace payment records for the configured live/test environment.
Inputs: no named parameters.
list_provider_credentialsARead-onlyIdempotentInspect
List which provider credentials are configured. Returns metadata only, never provider secret values.
Inputs: no named parameters.
list_simulation_personasARead-onlyIdempotentInspect
List simulation personas in the authenticated workspace.
Inputs: no named parameters.
list_simulation_runsBRead-onlyIdempotentInspect
List simulation runs and pagination; inspect status before starting another run.
Inputs: page, limit, status, batch_id, +2 more.
list_simulationsBRead-onlyIdempotentInspect
List simulations in the authenticated workspace.
Inputs: assistant_id.
list_simulation_scenariosARead-onlyIdempotentInspect
List simulation scenarios in the authenticated workspace.
Inputs: no named parameters.
list_toolsARead-onlyIdempotentInspect
List http tools in the authenticated workspace.
Inputs: no named parameters.
list_tts_ratesARead-onlyIdempotentInspect
Read configured voice-cost reference rates. These are not an invoice or a complete call price.
Inputs: no named parameters.
list_tts_voicesARead-onlyIdempotentInspect
Read a provider voice catalog using configured server-side credentials. Catalog failure may return an empty list and error; it is not evidence the provider has no voices.
Inputs: provider.
list_voice_presetsBRead-onlyIdempotentInspect
Read configured runnable voice presets. Provider catalog requests may reach a vendor.
Inputs: model, provider, realtime_provider.
list_webhooksBRead-onlyIdempotentInspect
List webhooks in the authenticated workspace.
Inputs: no named parameters.
revoke_api_keyADestructiveIdempotentInspect
Revoke a workspace API key immediately. Revoking the key in use disconnects this MCP client on its next request.
Inputs: id (required).
set_assistant_knowledgeAIdempotentInspect
Replace all attached knowledge documents. Each document must belong to this workspace.
Inputs: id (required), data (required).
set_assistant_toolsAIdempotentInspect
Replace all attached HTTP tools with existing tools owned by this workspace. Empty tool_ids detaches every tool.
Inputs: id (required), data (required).
start_simulation_batchADestructiveInspect
Queue every simulation for one assistant. This can incur multiple test runs; approve the batch first.
Inputs: data (required), confirm (required).
start_simulation_runADestructiveInspect
Queue an asynchronous test. Models and speech can incur usage. Approve the run first and poll the returned identifier; do not enqueue again while it is running.
Inputs: id (required), data (required), confirm (required).
unbind_numberADestructiveIdempotentInspect
Remove the routing binding. This does not release or cancel the carrier number.
Inputs: number (required).
update_assistantAInspect
Update selected assistant fields. Omitted fields retain their values.
Inputs: id (required), data (required), if_revision.
update_knowledge_documentAInspect
Update selected knowledge document fields. Omitted fields retain their values.
Inputs: id (required), data (required).
update_simulationAInspect
Update selected simulation fields. Omitted fields retain their values.
Inputs: id (required), data (required).
update_simulation_personaAInspect
Update selected simulation persona fields. Omitted fields retain their values.
Inputs: id (required), data (required).
update_simulation_scenarioBInspect
Update selected simulation scenario fields. Omitted fields retain their values.
Inputs: id (required), data (required).
update_toolAInspect
Update selected tool fields. Omitted fields retain their values.
Inputs: id (required), data (required).
update_webhookAInspect
Update selected webhook fields. Omitted fields retain their values.
Inputs: id (required), data (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Build, test, deploy and run AI phone agents: agents, numbers, calls, tests, knowledge, campaigns.
Build, call and manage AI voice agents on real phone calls.
Build and run AI voice agents for phone calls: agents, numbers, campaigns, calls. Hebrew, English.
Build and manage voice AI agents for real phone lines: assistants, calls, numbers and campaigns.
Related MCP Servers
- AlicenseAqualityDmaintenanceManage voice AI agents, make calls, run campaigns, and control phone numbers through natural language.5827 npm1MIT
- AlicenseAqualityBmaintenanceLet your AI agent make phone calls and join Zoom, Microsoft Teams and Google Meet meetings for you. Smitline talks in real time, can get through phone menus, stays inside your brief, and returns the outcome, action items and transcript. Connect the hosted version (beta) at https://app.smitline.com/mcp, or self-host it: it's open source. Works with Claude Code, Codex, Cursor and any MCP client.15151Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to initiate and control outbound telephone calls and answer inbound calls through Telnyx and LiveKit, with realtime voice conversations powered by Gemini Live or OpenAI Realtime.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to make real-world phone calls with AI voice technology and provides tools to track call status, transcripts, and summaries. It supports automated communication with both live numbers and simulated businesses for testing and demonstration purposes.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.