Bland AI MCP integration for AI agents.

Connect AI agents to Bland AI through 5 structured actions, including get account, get call, and get voice. Review authentication, inputs, workflows, and saf…

ACTION CONTRACTS
5
AUTHENTICATION
API key
SOURCE STATUS
Provider-backed

CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE

CAPABILITY PROFILE

What the Bland AI integration exposes

The Bland AI Agent App exposes 5 provider-backed actions for ai and communication work. Its current contract lets an authorized agent retrieve bland ai account status, billing balance, and total call count, retrieve detailed information and transcript phrases for a bland ai call, and retrieve details for a specific bland ai voice by uuid or curated voice name. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.

A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.

For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Bland AI account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.

VERIFIED ACTION SAMPLE

Real Bland AI capabilities.

Showing 5 of 5 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.

get_accountREAD

Retrieve Bland AI account status, billing balance, and total call count.

get_callREAD

Retrieve detailed information and transcript phrases for a Bland AI call.

INPUTS: callId

get_voiceREAD

Retrieve details for a specific Bland AI voice by UUID or curated voice name.

INPUTS: voiceId

list_callsREAD

List Bland AI calls with optional official filters and result-window controls.

INPUTS: fromNumber / toNumber / from / to / limit

list_voicesREAD

List every Bland AI voice available to the authenticated account.

INPUT CONTRACTS

Know what the action needs before it runs.

get_call

callIdOPTIONAL
Unique id of the call to retrieve.

get_voice

voiceIdOPTIONAL
Voice UUID or curated voice name.

list_calls

fromNumberOPTIONAL
Filter calls by the number that initiated the call.
toNumberOPTIONAL
Filter calls by the number that answered the call.
fromOPTIONAL
Starting index, inclusive, for the call result window.
toOPTIONAL
Ending index for the call result window.
limitOPTIONAL
Maximum number of calls to return.

PROVIDER-SPECIFIC WORKFLOWS

Jobs this Agent App can support

Inspect Get Account

Retrieve Bland AI account status, billing balance, and total call count. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.

get_account

Verify with Get Call

Retrieve detailed information and transcript phrases for a Bland AI call. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.

get_call

SAFETY BOUNDARY

Operate Bland AI with explicit limits

  • Authorize Bland AI with API key and grant only the provider access required by the selected actions.
  • The current action names appear read-oriented, but returned Bland AI data may still be sensitive and should be minimized before it enters model context.
  • Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
  • No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Bland AI rather than assuming unrestricted access.
  • After a call, inspect the structured result and execution record before reporting that the Bland AI task completed successfully.

CONNECTION MODEL

API key

Bland AI API key sent in the authorization header. Create or view API keys in the Bland dashboard under Settings > API Keys: https://app.bland.ai/dashboard/settings/api-keys.

Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.

READ SIGNALS
5
WRITE SIGNALS
0
HIGH IMPACT
0
REVIEW SIGNALS
0

EVIDENCE AND AVAILABILITY

Provider reference

Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Bland AI.

Official Bland AI website

ONE CONNECTION. REAL WORK.

Give your agent software it can use.

Connect through MCP or explore the Agent App catalog and choose only the capabilities your workflow needs.

EXPLORE AGENT APPS