APIFleet MCP server

• Registry namedev.apifleet/apifleetverified in the MCP registry

The registry name sits under apifleet.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-29
• Tools67
• Server calls itselfapifleet
• Server version1.2.0
• Protocol version2025-06-18

On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 602 ms.

• Its tools do every use case we checked: configure voice assistants in a dashboard or via REST API; bind phone numbers from carriers to voice agents; estimate call cost before placing conversations.
• Checked on 4 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
• What an agent can do with it3 of 3 use cases
• Answeredmeasuring4 of the 7 daily checks it takes to print a share
• Median first answer523 ms
• Space in an agent's context≈ 8,880 tokensthe definitions of all its tools (67), which an agent carries on every turn
• Tool definitionsA · 99 of 100
• Typed results0 of 67 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 4 of 67

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• apifleet_get_provider_matrix

  Public, no key: discover implemented voice and carrier integrations, setup boundaries, platform pricing and documentation. No provider request or call is made.

• apifleet_estimate_call_cost

  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.

• apifleet_check_assistant_config

  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.

• check_entitlements

  Read the workspace prepaid balance and funding path. Does not start a checkout or call.

• list_assistants

  List assistants in the authenticated workspace.

• get_assistant

  Get one assistant belonging to this workspace.

• create_assistant

  Create a assistant. Saving configuration does not place a call. The REST response includes revision, configuration and attached resource identifiers.

• update_assistant

  Update selected assistant fields. Omitted fields retain their values.

• delete_assistant

  Delete this assistant. Review the identifier before deleting; the change cannot be undone.

• set_assistant_tools

  Replace all attached HTTP tools with existing tools owned by this workspace. Empty tool_ids detaches every tool.

• set_assistant_knowledge

  Replace all attached knowledge documents. Each document must belong to this workspace.

• create_browser_test_token

  Issue a short-lived browser voice-test URL. Opening its WebSocket can incur usage. Never publish the returned token.

• list_numbers

  List number bindings. This does not buy phone numbers from a carrier.

• bind_number

  Bind an existing carrier number to a workspace assistant. This changes incoming call routing; configure the carrier webhook separately.

• unbind_number

  Remove the routing binding. This does not release or cancel the carrier number.

• list_calls

  Read call logs, summary statistics and pagination. Each row may contain transcript, analysis, costs and recording links; recordings require separate authentication.

• create_outbound_call

  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.

• get_waveform

  Read recording waveform metadata and available audio channels.

• delete_recording

  Permanently remove a call recording. The call log remains. Confirm the identifier before deleting.

• list_tools

  List http tools in the authenticated workspace.

• get_tool

  Get one tool belonging to this workspace.

• create_tool

  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.

• update_tool

  Update selected tool fields. Omitted fields retain their values.

• delete_tool

  Delete this tool. Review the identifier before deleting; the change cannot be undone.

• list_knowledge_documents

  List knowledge in the authenticated workspace.

• get_knowledge_document

  Get one knowledge document belonging to this workspace.

• create_knowledge_document

  Create a knowledge document. Attach documents separately to use them in an assistant. Total injected knowledge has a 200 KiB limit.

• update_knowledge_document

  Update selected knowledge document fields. Omitted fields retain their values.

• delete_knowledge_document

  Delete this knowledge document. Review the identifier before deleting; the change cannot be undone.

• list_webhooks

  List webhooks in the authenticated workspace.

• create_webhook

  Create a webhook. Creation returns a signing secret once; verify delivery signatures against the raw body. Events may be retried.

• update_webhook

  Update selected webhook fields. Omitted fields retain their values.

• delete_webhook

  Delete this webhook. Review the identifier before deleting; the change cannot be undone.

• list_simulation_personas

  List simulation personas in the authenticated workspace.

• get_simulation_persona

  Get one simulation persona belonging to this workspace.

• create_simulation_persona

  Create a simulation persona.

• update_simulation_persona

  Update selected simulation persona fields. Omitted fields retain their values.

• delete_simulation_persona

  Delete this simulation persona. Review the identifier before deleting; the change cannot be undone.

• list_simulation_scenarios

  List simulation scenarios in the authenticated workspace.

• get_simulation_scenario

  Get one simulation scenario belonging to this workspace.

• create_simulation_scenario

  Create a simulation scenario.

• update_simulation_scenario

  Update selected simulation scenario fields. Omitted fields retain their values.

• delete_simulation_scenario

  Delete this simulation scenario. Review the identifier before deleting; the change cannot be undone.

• list_simulations

  List simulations in the authenticated workspace.

• get_simulation

  Get one simulation belonging to this workspace.

• create_simulation

  Create a simulation.

• update_simulation

  Update selected simulation fields. Omitted fields retain their values.

• delete_simulation

  Delete this simulation. Review the identifier before deleting; the change cannot be undone.

• list_simulation_runs

  List simulation runs and pagination; inspect status before starting another run.

• get_simulation_run

  Read a run, its evaluations and linked call when available.

• delete_simulation_run

  Delete a completed simulation result. Running runs may reject deletion.

• start_simulation_run

  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.

• start_simulation_batch

  Queue every simulation for one assistant. This can incur multiple test runs; approve the batch first.

• list_tts_rates

  Read configured voice-cost reference rates. These are not an invoice or a complete call price.

• list_tts_voices

  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.

• list_voice_presets

  Read configured runnable voice presets. Provider catalog requests may reach a vendor.

• get_assistant_voice_presets

  Read voices compatible with this assistant configuration.

• get_tts_settings

  Read supported provider voice settings and validation ranges.

• list_provider_credentials

  List which provider credentials are configured. Returns metadata only, never provider secret values.

• list_api_keys

  List this workspace API-key metadata. Full key values cannot be retrieved.

The first 60 of 67, as the server listed them.