Tool list

115 tools. 113 are backed one-to-one by the Bolna REST API and act on your account. The remaining 2 (search_docs, get_doc) read Bolna’s public documentation instead — no account data involved.

Type	Meaning
`Read`	Looks something up. No side effects.
`Write`	Creates or changes something. Reversible or low-risk (e.g. `create_agent` just adds a new agent).
`Write ⚠`	Flagged destructive in the tool’s own definition (`destructiveHint: true`) — irreversible, or has a real-world effect like spending balance or breaking something still in use. Most clients pause for your confirmation before running these.

The 43 ⚠ tools are update_agent, delete_agent, stop_agent_queued_calls, start_outbound_call, stop_call, schedule_batch, stop_batch, delete_batch, update_disposition, delete_disposition, update_extraction_category, delete_extraction_category, buy_phone_number, delete_phone_number, unlink_inbound_agent, update_trunk, delete_trunk, remove_trunk_gateway, remove_trunk_carrier_ip, remove_number_from_trunk, assign_trunk_number_agent, start_trunk_test_call, disarm_trunk_inbound_test, update_sip_trunk, delete_sip_trunk, remove_trunk_number, update_sub_account, delete_sub_account, remove_provider, delete_knowledgebase, rename_workflow, update_workflow_settings, delete_workflow, save_workflow_draft, publish_workflow, run_workflow, delete_workflow_campaign, start_workflow_campaign, pause_workflow_campaign, resume_workflow_campaign, abort_workflow_campaign, cancel_workflow_execution, and update_graph_agent — see each one’s row below for what makes it destructive.

Calling tools with a different account

Every tool below also accepts an optional api_key argument. Pass it on any single call to run that call against a different account than the one your client connected with — without reconnecting. This is for sub-accounts: call list_sub_accounts to get a sub-account’s key (sa-...), then pass it as api_key on any later tool call to act as that sub-account for just that call. A sub-account key also works as the primary connection credential from the start, exactly like a main account’s bn-... key — see the Quickstart.

Agents

Tool	Type	Description	API
`list_agents`	Read	List agents in the account — ID, name, status, created date	List Agents
`get_agent`	Read	Full config of one agent — prompts, LLM, voice, telephony, tools	Get Agent
`create_agent`	Write	Create a new agent, returns its ID	Create Agent
`update_agent`	Write ⚠	Patch an agent’s name, prompts, welcome message, webhook, or voice	Patch Update
`delete_agent`	Write ⚠	Permanently delete an agent and its history	Delete Agent
`stop_agent_queued_calls`	Write ⚠	Cancel every queued or scheduled call for one agent	Stop Agent Queued Calls

Calls & executions

Tool	Type	Description	API
`start_outbound_call`	Write ⚠	Place a real outbound call, spends account balance	Make Call
`stop_call`	Write ⚠	Cancel a single queued or scheduled call	Stop Call
`list_agent_executions`	Read	Call history for one agent, defaults to the last 7 days	Get Executions
`get_execution`	Read	Full call detail — transcript, status, cost, telephony data	Get Execution
`get_execution_raw_logs`	Read	Raw per-component pipeline logs for one call — transcriber, LLM, synthesizer timing	Raw Logs
`list_batch_executions`	Read	Every call execution within one batch	Batch Executions

Batches

Tool	Type	Description	API
`list_batches`	Read	Batch campaigns for one agent — status and schedule	Get Batches
`create_batch`	Write	Create a batch of outbound calls from a recipient list	Create Batch
`get_batch`	Read	One batch’s status, schedule, and contact counts	Get Batch
`schedule_batch`	Write ⚠	Start calling every recipient in a batch, spends account balance	Schedule Batch
`stop_batch`	Write ⚠	Halt a running or scheduled batch	Stop Batch
`delete_batch`	Write ⚠	Permanently delete a batch and its recipient list	Delete Batch

Dispositions

Dispositions turn a call transcript into structured, typed data — lead qualified, appointment time, sentiment — surfaced as extracted_data on executions and webhook payloads.

Tool	Type	Description	API
`list_dispositions`	Read	Dispositions configured for one agent	List Dispositions
`get_disposition`	Read	One disposition’s field type, validation, and prompt	Get Disposition
`create_disposition`	Write	Add a single disposition to an agent	Create Disposition
`bulk_create_dispositions`	Write	Add several dispositions to an agent in one call	Bulk Create Dispositions
`update_disposition`	Write ⚠	Change a disposition’s field, validation, or prompt	Update Disposition
`delete_disposition`	Write ⚠	Permanently delete a disposition	Delete Disposition
`test_dispositions`	Write	Run an agent’s dispositions against a sample transcript and preview the extracted output	Test Dispositions

Extraction categories

A category is the set of dispositions evaluated together in one LLM pass per call, run on the category’s model. Each disposition belongs to one category.

Tool	Type	Description	API
`list_extraction_categories`	Read	An agent’s extraction categories, with the dispositions inside each	List Extraction Categories
`create_extraction_category`	Write	Add a category to an agent, with the model that runs its LLM pass	Create Extraction Category
`update_extraction_category`	Write ⚠	Rename a category or change its model	Update Extraction Category
`delete_extraction_category`	Write ⚠	Permanently delete a category and every disposition inside it	Delete Extraction Category

Knowledgebase (RAG)

Tool	Type	Description	API
`list_knowledgebases`	Read	Every knowledgebase on the account	List All Knowledgebases
`get_knowledgebase`	Read	One knowledgebase’s file name, status, and settings, by ID	Get Knowledgebase
`create_knowledgebase`	Write	Create a knowledgebase by scraping a URL for RAG. Processing is async — check progress with `get_knowledgebase`	Create Knowledgebase
`delete_knowledgebase`	Write ⚠	Permanently delete a knowledgebase	Delete Knowledgebase

create_knowledgebase only accepts a URL to scrape — the Bolna API also supports uploading a PDF directly, but a raw file doesn’t map cleanly to a chat tool argument. For PDF-based knowledgebases, use the dashboard or call the Create Knowledgebase API directly.

Phone numbers & inbound

Tool	Type	Description	API
`list_phone_numbers`	Read	Phone numbers on the account and their linked agent	Get All
`search_phone_numbers`	Read	Search available numbers to buy, by country or pattern	Search Phone Numbers
`buy_phone_number`	Write ⚠	Purchase a phone number, spends account balance (flat $5/month)	Buy Phone Numbers
`delete_phone_number`	Write ⚠	Permanently release a phone number back to the pool	Delete Phone Numbers
`setup_inbound_agent`	Write	Route inbound calls on a number to an agent, with an optional IVR	Set Inbound Agent
`unlink_inbound_agent`	Write ⚠	Remove the inbound routing from a phone number	Remove Inbound Agent

SIP trunks

For connecting your own carrier over a SIP trunk — Plivo, Telnyx, Twilio, Exotel, Vobiz, Vonage, or any standards-based SIP carrier.

Tool	Type	Description	API
`list_trunks`	Read	SIP trunks on the account, with health, gateways, carrier IPs and numbers	List SIP Trunks
`get_trunk`	Read	One trunk’s settings, health, active calls, gateways, carrier IPs and numbers	Get SIP Trunk
`create_trunk`	Write	Create a SIP trunk for your own carrier, optionally with its gateways and carrier IPs	Create SIP Trunk
`update_trunk`	Write ⚠	Change a trunk’s settings or carrier credentials; can switch off every call on the trunk	Update SIP Trunk
`delete_trunk`	Write ⚠	Permanently delete a trunk with its gateways, carrier IPs and numbers	Delete SIP Trunk
`add_trunk_gateway`	Write	Add an outbound gateway, the carrier SIP host Bolna sends calls to	Add Gateway
`remove_trunk_gateway`	Write ⚠	Remove an outbound gateway, so outbound calls stop using it	Remove Gateway
`add_trunk_carrier_ip`	Write	Allow a carrier signalling IP or CIDR to send inbound calls	Add Carrier IP
`remove_trunk_carrier_ip`	Write ⚠	Stop accepting inbound calls from a carrier IP	Remove Carrier IP
`add_number_to_trunk`	Write	Add a number your carrier routes to the trunk, optionally with the agent that answers it	Add Number
`remove_number_from_trunk`	Write ⚠	Remove a number from a trunk; inbound calls to it are refused	Remove Number
`assign_trunk_number_agent`	Write ⚠	Set or clear the agent that answers a trunk number’s inbound calls	Assign Agent
`list_trunk_calls`	Read	Recent calls on a trunk’s numbers, with outcome and SIP code	List Calls
`get_trunk_connection_details`	Read	Bolna’s SIP domain, IPs, port, transports and RTP port range to configure at your carrier	Connection Details
`start_trunk_test_call`	Write ⚠	Ring a real phone through the trunk with an echo test, no agent involved; your carrier may bill it	—
`get_trunk_test_call`	Read	State, SIP status and hangup cause of an outbound test call	—
`arm_trunk_inbound_test`	Write	Answer the trunk’s next inbound call with an echo test instead of an agent	—
`get_trunk_inbound_test`	Read	Whether the trunk is armed for an inbound test, and how the test call went	—
`disarm_trunk_inbound_test`	Write ⚠	Cancel an inbound test; a test call already in progress is marked failed	—

Legacy SIP trunks (deprecated)

These tools keep working for Legacy SIP trunks. Use the SIP trunk tools for new setups, and see Migrate to SIP trunks to move an existing trunk.

Tool	Type	Description	API
`create_sip_trunk`	Write	Register a legacy SIP trunk with its gateway and auth settings. For new setups use `create_trunk`	Create SIP Trunk
`get_sip_trunk`	Read	One legacy trunk’s gateway, auth, and transport config. For new setups use `get_trunk`	Get SIP Trunk
`list_sip_trunks`	Read	Legacy SIP trunks on the account. For new setups use `list_trunks`	List SIP Trunks
`update_sip_trunk`	Write ⚠	Change a legacy trunk’s gateway, auth, or transport settings. For new setups use `update_trunk`	Update SIP Trunk
`delete_sip_trunk`	Write ⚠	Permanently delete a legacy SIP trunk. For new setups use `delete_trunk`	Delete SIP Trunk
`add_trunk_number`	Write	Attach a DID number to a legacy trunk. For new setups use `add_number_to_trunk`	Add Number to Trunk
`remove_trunk_number`	Write ⚠	Detach a DID number from a legacy trunk. For new setups use `remove_number_from_trunk`	Remove Number from Trunk
`list_trunk_numbers`	Read	DID numbers attached to one legacy trunk. For new setups use `get_trunk`	List Numbers on Trunk

Sub-accounts

Enterprise feature — isolated workspaces with their own auto-provisioned API key (sa-...), agents, calls, and phone numbers, for agencies, multi-tenant platforms, or regulated data boundaries.

Tool	Type	Description	API
`create_sub_account`	Write	Create a sub-account and provision its API key	Create Sub-Account
`list_sub_accounts`	Read	Sub-accounts on the account, including their API keys	List Sub-Accounts
`update_sub_account`	Write ⚠	Patch a sub-account’s name or settings	Patch Update
`delete_sub_account`	Write ⚠	Permanently delete a sub-account and everything inside it	Delete Sub-Account
`get_sub_account_usage`	Read	Call volume and cost for one sub-account	Track Usage
`get_all_sub_accounts_usage`	Read	Usage for every sub-account on the account, in one call	All Usage

Voice & providers

Tool	Type	Description	API
`list_tts_providers`	Read	Text-to-speech providers and models available to the account	List TTS Providers and Models
`list_voices`	Read	Voices available across connected TTS providers	List Voices
`list_providers`	Read	Telephony, LLM, transcriber, and TTS providers connected to the account	List Providers
`remove_provider`	Write ⚠	Disconnect a provider’s credentials — breaks any agent still using it	Remove a Provider

Violations

Tool	Type	Description	API
`list_violations`	Read	Flagged call violations — content policy, regulatory, or fraud — optionally filtered by status (`pending`/`accepted`/`rejected`/`submitted`), paginated	List Violations

Workflows

Multi-step, per-contact automations — call an agent, branch on the outcome, wait, call an API, message over WhatsApp, retry, and so on — distinct from a single agent’s own conversation. A workflow is edited as a draft, then published as an immutable version before it can run.

Tool	Type	Description	API
`create_workflow`	Write	Create a new, empty, unpublished workflow — returns its ID	Create Workflow
`list_workflows`	Read	List workflows in the account, optionally filtered by name	List Workflows
`get_workflow`	Read	A workflow’s status plus its full draft and published version history	Get Workflow
`rename_workflow`	Write ⚠	Rename an existing workflow	Update Workflow
`update_workflow_settings`	Write ⚠	Set, change or remove the workflow’s execution webhook URL and headers — a merge patch, so header values come back masked and you only send what changes	Update Workflow
`test_workflow_webhook`	Write	Send one sample execution webhook to the saved URL and report how the receiver answered	Test Webhook
`delete_workflow`	Write ⚠	Permanently delete a workflow, including its draft and every published version	Delete Workflow
`get_workflow_draft`	Read	The current editable draft node graph and its revision number	Get Workflow Draft
`save_workflow_draft`	Write ⚠	Overwrite the draft’s node graph — requires the current revision, to avoid clobbering concurrent edits	Save Workflow Draft
`validate_workflow`	Read	Check the saved draft for errors before publishing	Validate Workflow
`publish_workflow`	Write ⚠	Freeze the draft as a new immutable published version	Publish Workflow
`get_workflow_version`	Read	A specific published version’s full node graph	Get Workflow Version
`run_workflow`	Write ⚠	Run a single contact through the latest published version — places real calls or messages	Run Workflow
`list_workflow_node_types`	Read	Every node type the workflow engine supports, with its config parameters	Workflow Node Types

Workflow campaigns

Runs many contacts through one pinned, published workflow version — the workflow equivalent of a batch running many contacts through one agent.

Tool	Type	Description	API
`create_workflow_campaign`	Write	Create a campaign pinned to a workflow’s published version, starting in draft with no entries	Create Workflow Campaign
`list_workflow_campaigns`	Read	List campaigns, optionally filtered by workflow, status, or kind	List Workflow Campaigns
`get_workflow_campaign`	Read	A campaign’s status and totals, plus entry and validation-error breakdowns	Get Workflow Campaign
`delete_workflow_campaign`	Write ⚠	Delete an empty draft campaign that hasn’t started	Delete Workflow Campaign
`upload_workflow_campaign_entries`	Write	Add contacts to a campaign — anything beyond the standard fields goes in `custom_fields`	Upload Campaign Entries
`list_workflow_campaign_entries`	Read	List a campaign’s uploaded contacts, optionally filtered by status	List Campaign Entries
`get_workflow_campaign_entries_template`	Read	The CSV header row the campaign’s pinned version expects for entry uploads	Campaign Entries Template
`start_workflow_campaign`	Write ⚠	Start dispatching a campaign’s pending entries as real calls or messages, spends account balance	Start Workflow Campaign
`pause_workflow_campaign`	Write ⚠	Pause a running campaign’s dispatching	Pause Workflow Campaign
`resume_workflow_campaign`	Write ⚠	Resume a paused campaign’s dispatching	Resume Workflow Campaign
`abort_workflow_campaign`	Write ⚠	Permanently terminate a campaign — cannot be undone	Abort Workflow Campaign
`list_workflow_campaign_executions`	Read	List a campaign’s per-contact executions, optionally filtered by status or outcome	List Campaign Executions
`get_workflow_campaign_report`	Read	Aggregated execution, termination, and per-node funnel counts for a campaign	Workflow Campaign Report

Workflow executions

A single contact’s run through a workflow, created by run_workflow or a campaign.

Tool	Type	Description	API
`get_workflow_execution`	Read	Current node, node-by-node history, and recent timeline events for one contact’s run	Get Workflow Execution
`cancel_workflow_execution`	Write ⚠	Terminate a running execution for a single contact	Cancel Workflow Execution
`resend_workflow_webhook`	Write	Queue a finished execution’s webhook again, with the payload it originally sent	Resend Webhook

Graph agents

Graph agents are node-based voice flows: each node is one step of the conversation, and edges route between nodes by intent, by rules on context variables, or on events your backend sends during the call. There’s no separate graph-agent API. A graph agent is a regular agent whose graph lives under tools_config.llm_agent.llm_config, so these tools are typed wrappers over the Agent API, plus the event-injection endpoint. create_graph_agent and update_graph_agent check the graph against the same rules as the editor’s Validation before saving, and send nothing to Bolna if there are errors. Warnings come back with the result.

Tool	Type	Description	API
`create_graph_agent`	Write	Create a graph agent from nodes and edges. Transcriber, voice, and telephony default to Deepgram nova-3, ElevenLabs turbo v2.5, and Plivo, and can be overridden	Create Agent
`get_graph_agent`	Read	A graph agent’s nodes, edges, and routing settings, plus a validation report	Get Agent
`update_graph_agent`	Write ⚠	Replace the graph, or add, replace, and remove nodes and change routing settings. Voice, transcriber, and telephony are kept	Update Agent
`validate_graph_agent`	Read	Check a graph, or a saved agent, against the editor’s validation rules without saving	—
`send_graph_agent_event`	Write	Push a named event into a live call. If the current node has a matching event edge, the agent moves to the next node and speaks without waiting for the caller	Event injection

update_graph_agent saves by replacing the agent’s full config (PUT), because a partial update can’t change the graph. If someone edits the agent in the dashboard between the tool reading it and saving it, their edit is overwritten.

Account

Tool	Type	Description	API
`get_user_info`	Read	Account profile, wallet balance, concurrency limits	User Info

Documentation

These two don’t touch your account at all — they read Bolna’s own docs, so the assistant can look things up instead of guessing.

Tool	Type	Description	Source
`search_docs`	Read	Searches Bolna’s documentation index (`llms.txt`) and returns ranked matches with title, URL, and description	`llms.txt`
`get_doc`	Read	Fetches a documentation page’s full Markdown content, given a bare path (e.g. `/docs/mcp`) or a full URL	`www.bolna.ai/docs/*.md`

Not connected yet? See the Quickstart for setup and troubleshooting.

Bolna MCP server repository

Full source, endpoint-verification notes, and issue tracker

Bolna MCP

Bolna Skills

SDKs

Bolna CLI

AI-readable docs

Calling tools with a different account

Agents

Calls & executions

Batches

Dispositions

Extraction categories

Knowledgebase (RAG)

Phone numbers & inbound

SIP trunks

Legacy SIP trunks (deprecated)

Sub-accounts

Voice & providers

Violations

Workflows

Workflow campaigns

Workflow executions

Graph agents

Account

Documentation

Bolna MCP server repository

​Calling tools with a different account

​Agents

​Calls & executions

​Batches

​Dispositions

​Extraction categories

​Knowledgebase (RAG)

​Phone numbers & inbound

​SIP trunks

​Legacy SIP trunks (deprecated)

​Sub-accounts

​Voice & providers

​Violations

​Workflows

​Workflow campaigns

​Workflow executions

​Graph agents

​Account

​Documentation

Bolna MCP server repository

Calling tools with a different account

Agents

Calls & executions

Batches

Dispositions

Extraction categories

Knowledgebase (RAG)

Phone numbers & inbound

SIP trunks

Legacy SIP trunks (deprecated)

Sub-accounts

Voice & providers

Violations

Workflows

Workflow campaigns

Workflow executions

Graph agents

Account

Documentation