Which integrations are available for this server?

Enables sending WhatsApp messages to contacts as part of multi-step workflow automations and workflow campaigns.

How do I use Bolna MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Bolna MCP Server Create an AI voice agent to make outbound sales calls" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Bolna MCP Server

Official

by bolna-ai

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

Bolna MCP Server

Remote MCP server (Streamable HTTP) wrapping the Bolna voice AI REST API (https://api.bolna.ai): 116 tools covering nearly every documented Bolna endpoint, TypeScript, deployed on Vercel via mcp-handler.

Live at mcp.bolna.ai — that page has the same connect instructions below with copy-paste buttons for each client.

MCP is an open protocol, not Claude-specific — this server works with any MCP-compatible client: Claude, Codex, Cursor, Windsurf, Zed, and others.

Endpoint corrections found while verifying tool paths against the live Bolna docs are documented in the comment block at the top of src/tools/index.ts.

Two endpoints

Endpoint	Tools	For
`/api/mcp`	all 116	Anyone connecting the server themselves
`/api/connector/mcp`	9	The Claude connector directory listing

The directory surface is a fixed subset. A directory listing is reviewed as a whole, so every tool on it is surface area to justify. /api/connector/mcp serves the nine tools named in src/tools/directory-surface.ts and nothing else, while /api/mcp keeps growing. Adding a name to that list means adding it to what Anthropic reviews, so do it deliberately. Both routes are built by the same factory in src/lib/mcp-route.ts and share the same tool implementations.

The restriction is applied at registration time, not per call: tools off the list never enter the server's registry, so they are absent from tools/list and un-callable by name. Prompts are dropped the same way, so the connector answers prompts/list with "method not found" rather than advertising the four on /api/mcp.

Two things also differ on the connector, and only there:

No api_key parameter. Every tool on /api/mcp accepts an optional api_key to target another account for one call (see above). It is stripped from both the schema and the incoming arguments on the connector, so it always acts as the OAuth-authenticated user. The strip lives in the same wrapper as the allowlist — no tool implementation is touched.
Its own server instructions. SERVER_INSTRUCTIONS describes tools and prompts the connector doesn't register, so it sends CONNECTOR_INSTRUCTIONS from src/tools/prompts.ts instead.

OAuth is per-surface. RFC 9728 metadata must declare a resource equal to the URL the client connected to, and Claude rejects a mismatch, so a single hardcoded document can't serve two paths. /api/connector/mcp points at the path-insertion form /.well-known/oauth-protected-resource/api/connector/mcp, served by a catch-all route that answers only for known transport paths. /api/mcp keeps the bare /.well-known/oauth-protected-resource it has always handed out, so already-connected clients are unaffected. Both documents name the same Supabase authorization server, and verifyToken does no audience check of its own — the token is forwarded to api.bolna.ai either way — so the sign-in flow at the two URLs is identical.

Related MCP server: VoIPbin MCP Server

Sub-accounts and switching between accounts

Sub-account API keys (format sa-...) work exactly like a main account's key (bn-...) — connect a separate client/connector with a sub-account's key as the Bearer token to work entirely within that sub-account.

To switch accounts within a single connected session instead of reconnecting, every tool also accepts an optional api_key argument that overrides the connection's own credential for just that call. Get a sub-account's key from list_sub_accounts' api_key field, then pass it to any tool call to run that call against that sub-account instead of the main account — e.g. "list agents in sub-account X" resolves to calling list_sub_accounts, finding X's key, then list_agents with that key passed as api_key.

Available tools

116 tools across 17 categories. "Write" tools flagged Destructive modify, remove, or spend money and typically prompt for confirmation in MCP clients that respect tool annotations.

Agents & calls

Tool	Type	Description
`list_agents`	Read	List agents in the account (id, name, status, created_at). Paginated.
`get_agent`	Read	Full config of one agent by ID.
`create_agent`	Write	Create a new agent. Returns its ID.
`update_agent`	Write, Destructive	Patch an existing agent's name, prompts, welcome message, webhook, or voice settings.
`delete_agent`	Write, Destructive	Permanently delete an agent. Irreversible.
`stop_agent_queued_calls`	Write, Destructive	Cancel every queued call for an agent.
`start_outbound_call`	Write, Destructive	Place a real outbound call from an agent. Spends account balance.
`stop_call`	Write, Destructive	Cancel a queued or scheduled call.

Executions

Tool	Type	Description
`list_agent_executions`	Read	Call history for one agent. Paginated, defaults to the last 7 days.
`get_execution`	Read	Full details of one call: transcript, status, cost, telephony data.
`get_execution_raw_logs`	Read	Raw pipeline logs (transcriber/LLM/synthesizer) for a call.
`get_execution_debug`	Read	Everything needed to debug a call, in one compact request: execution, per-turn latency and transcript, logs with delta-encoded LLM requests.
`list_batch_executions`	Read	Every call execution within a batch. Paginated.

Batches

Tool	Type	Description
`create_batch`	Write	Create a batch of outbound calls from a list of recipients.
`get_batch`	Read	A batch's status, schedule, and contact counts.
`list_batches`	Read	Call batches for one agent.
`schedule_batch`	Write, Destructive	Schedule a batch to start calling. Spends account balance.
`stop_batch`	Write, Destructive	Halt a running or queued batch.
`delete_batch`	Write, Destructive	Permanently delete a batch.

Dispositions (structured call extraction)

Tool	Type	Description
`list_dispositions`	Read	List dispositions, optionally scoped to an agent.
`get_disposition`	Read	Retrieve a single disposition.
`create_disposition`	Write	Create a disposition linked to an agent.
`bulk_create_dispositions`	Write	Atomically create multiple dispositions for one agent.
`update_disposition`	Write, Destructive	Update a disposition (may fork a private copy — Bolna's copy-on-write).
`delete_disposition`	Write, Destructive	Permanently delete a disposition.
`test_dispositions`	Read	Run an agent's dispositions against a sample transcript.

Extraction categories

Tool	Type	Description
`list_extraction_categories`	Read	List an agent's extraction categories with their dispositions.
`create_extraction_category`	Write	Create an extraction category (name + model) on an agent.
`update_extraction_category`	Write, Destructive	Rename a category or change its model; renames rewrite the category text on its dispositions.
`delete_extraction_category`	Write, Destructive	Permanently delete a category and every disposition inside it.

Phone numbers & inbound

Tool	Type	Description
`list_phone_numbers`	Read	Phone numbers on the account.
`search_phone_numbers`	Read	Search phone numbers available for purchase.
`buy_phone_number`	Write, Destructive	Purchase a phone number. Real recurring charge.
`delete_phone_number`	Write, Destructive	Remove a phone number and stop its billing.
`setup_inbound_agent`	Write	Route inbound calls on a number to an agent, optionally with an IVR menu.
`unlink_inbound_agent`	Write, Destructive	Remove inbound routing from a number.

SIP trunks (bring your own carrier)

Tool	Type	Description
`list_trunks`	Read	SIP trunks on the account, with health, gateways, carrier IPs and numbers.
`get_trunk`	Read	Full details of one SIP trunk.
`create_trunk`	Write	Create a SIP trunk for your own carrier.
`update_trunk`	Write, Destructive	Partially update a trunk's settings or carrier credentials.
`delete_trunk`	Write, Destructive	Permanently delete a trunk with its gateways, carrier IPs and numbers.
`add_trunk_gateway`	Write	Add an outbound gateway (the carrier's SIP host).
`remove_trunk_gateway`	Write, Destructive	Remove an outbound gateway.
`add_trunk_carrier_ip`	Write	Allow a carrier signalling IP or CIDR to send inbound calls.
`remove_trunk_carrier_ip`	Write, Destructive	Stop accepting inbound calls from a carrier IP.
`add_number_to_trunk`	Write	Add an E.164 number the carrier routes to the trunk.
`remove_number_from_trunk`	Write, Destructive	Remove a number from a trunk.
`assign_trunk_number_agent`	Write, Destructive	Set or clear the agent that answers a number's inbound calls.
`list_trunk_calls`	Read	Recent calls on a trunk's numbers, with SIP codes.
`get_trunk_connection_details`	Read	Bolna's SIP domain, IPs, port, transports and RTP range to configure at the carrier.
`start_trunk_test_call`	Write, Destructive	Ring a phone through the trunk with an echo test.
`get_trunk_test_call`	Read	State 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 and how the inbound test went.
`disarm_trunk_inbound_test`	Write, Destructive	Cancel an inbound test.

Legacy SIP trunks (deprecated)

Kept for trunks that already exist on the legacy plane; new setups use the SIP trunk tools above.

Tool	Type	Description
`create_sip_trunk`	Write	Create a legacy SIP trunk with gateway and auth config. Use `create_trunk` instead.
`get_sip_trunk`	Read	Full details of a legacy SIP trunk. Use `get_trunk` instead.
`list_sip_trunks`	Read	All legacy SIP trunks on the account. Use `list_trunks` instead.
`update_sip_trunk`	Write, Destructive	Partially update a legacy SIP trunk. Use `update_trunk` instead.
`delete_sip_trunk`	Write, Destructive	Permanently delete a legacy trunk and its gateways/numbers. Use `delete_trunk` instead.
`add_trunk_number`	Write	Add a DID phone number to a legacy trunk. Use `add_number_to_trunk` instead.
`remove_trunk_number`	Write, Destructive	Remove a number from a legacy trunk. Use `remove_number_from_trunk` instead.
`list_trunk_numbers`	Read	Numbers assigned to a legacy trunk. Use `get_trunk` instead.

Sub-accounts (enterprise)

Tool	Type	Description
`create_sub_account`	Write	Create an isolated sub-account workspace. Requires org admin access.
`list_sub_accounts`	Read	All sub-accounts in the organization.
`update_sub_account`	Write, Destructive	Update a sub-account's name or concurrency limits.
`delete_sub_account`	Write, Destructive	Permanently delete a sub-account and all its data.
`get_sub_account_usage`	Read	Usage and cost breakdown for one sub-account.
`get_all_sub_accounts_usage`	Read	Usage and cost breakdown for every sub-account.

Voice & providers

Tool	Type	Description
`list_tts_providers`	Read	TTS providers and models Bolna supports.
`list_voices`	Read	Voices available for a TTS provider/model.
`list_providers`	Read	Third-party providers configured on the account (secrets masked).
`remove_provider`	Write, Destructive	Remove a configured provider by name.

Knowledgebase (RAG)

Tool	Type	Description
`create_knowledgebase`	Write	Create a knowledgebase by scraping a URL. PDF upload isn't supported here.
`get_knowledgebase`	Read	A knowledgebase's file name, status, and settings.
`list_knowledgebases`	Read	All knowledgebases on the account.
`delete_knowledgebase`	Write, Destructive	Permanently delete a knowledgebase.

Violations

Tool	Type	Description
`list_violations`	Read	List flagged call violations, optionally filtered by status. Paginated.

Workflows

Multi-step, per-contact automations (call an agent, branch on the outcome, wait, call an API, wait for a callback from your own system, 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
`create_workflow`	Write	Create a new (empty) workflow.
`list_workflows`	Read	List workflows, optionally filtered by name. Paginated.
`get_workflow`	Read	A workflow's status, settings (webhook header values masked), and full draft/published version history.
`rename_workflow`	Write, Destructive	Rename a workflow.
`update_workflow_settings`	Write, Destructive	Set, change, or remove the execution webhook (URL and headers) as a JSON merge patch. Takes effect immediately.
`test_workflow_webhook`	Write	POST one sample execution webhook to the saved URL and report the receiver's response.
`delete_workflow`	Write, Destructive	Permanently delete a workflow and every version.
`get_workflow_draft`	Read	The current editable draft definition and its revision number.
`save_workflow_draft`	Write, Destructive	Overwrite the draft's node graph. Requires the current revision to avoid clobbering concurrent edits.
`validate_workflow`	Read	Check the saved draft for errors before publishing.
`publish_workflow`	Write, Destructive	Freeze the draft as a new immutable published version.
`get_workflow_version`	Read	Retrieve a specific published version's node graph.
`run_workflow`	Write, Destructive	Run a single contact through the latest published version. Places real calls/messages.
`list_workflow_node_types`	Read	Every node type the engine supports, with its config parameters.
`get_workflow_callback`	Read	A callback node's URL and signing secret, optionally with the last payload it received.

Workflow campaigns

Runs many contacts through one workflow version as a batch.

Tool	Type	Description
`create_workflow_campaign`	Write	Create a campaign pinned to a workflow version.
`list_workflow_campaigns`	Read	List campaigns, optionally filtered by workflow, status, or kind. Paginated.
`get_workflow_campaign`	Read	A campaign's status and totals, plus entry/validation-error breakdowns.
`delete_workflow_campaign`	Write, Destructive	Delete an empty draft campaign.
`upload_workflow_campaign_entries`	Write	Add contacts to a campaign (CSV/JSON columns beyond the standard fields go in `custom_fields`).
`list_workflow_campaign_entries`	Read	List a campaign's uploaded contacts. Paginated.
`get_workflow_campaign_entries_template`	Read	The CSV header row the campaign's pinned version expects.
`start_workflow_campaign`	Write, Destructive	Start dispatching a campaign's pending entries. Spends account balance.
`pause_workflow_campaign`	Write, Destructive	Pause a running campaign's dispatching.
`resume_workflow_campaign`	Write, Destructive	Resume a paused campaign.
`abort_workflow_campaign`	Write, Destructive	Permanently terminate a campaign. Cannot be undone.
`list_workflow_campaign_executions`	Read	List a campaign's per-contact executions. Paginated.
`get_workflow_campaign_report`	Read	Aggregated execution/termination/per-node funnel counts.

Workflow executions

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

Tool	Type	Description
`get_workflow_execution`	Read	Current node, node-by-node history, and recent timeline events.
`cancel_workflow_execution`	Write, Destructive	Terminate a running execution.
`resend_workflow_webhook`	Write	Queue a finished execution's original webhook payload again, to the workflow's current URL and headers.

Graph agents

Node-based voice flows (llm_agent.agent_type: "graph_agent"). Create, edit, and validate the graph, and push events into live calls.

Tool	Type	Description
`create_graph_agent`	Write	Create a graph agent from nodes and edges. The graph is validated first; voice, transcriber, and telephony have defaults.
`get_graph_agent`	Read	A graph agent's nodes, edges, routing settings, and a validation report.
`update_graph_agent`	Write, Destructive	Replace the graph, or add/replace/remove nodes and change routing settings, keeping the rest of the agent. Validated before saving.
`validate_graph_agent`	Read	Check a graph (or a saved agent) against the graph editor's rules without saving.
`send_graph_agent_event`	Write	Push a named event into a live call; a matching event edge on the current node transitions and the agent speaks.

Account & documentation

Tool	Type	Description
`get_user_info`	Read	Account profile, wallet balance, concurrency limits.
`search_docs`	Read	Search the Bolna documentation site for matching pages.
`get_doc`	Read	Fetch the full markdown content of a Bolna documentation page.

Not exposed as a tool, all for the same reason — each needs either a raw file upload or a third-party secret as its request body, neither of which maps cleanly to a tool argument or belongs in a chat conversation:

POST /providers (add a provider) — takes a third-party credential (e.g. a Twilio auth token)
POST /knowledgebase with a PDF file (the URL variant is supported, above)
POST /violations/submit — takes an evidence screenshot/document

Install & use

Prerequisite: your own Bolna API key (from the Bolna dashboard). Every client below needs the same two things: the server URL (https://mcp.bolna.ai/api/mcp) and that key as a Bearer token.

Claude Code

One command:

./scripts/connect.sh

or the equivalent by hand:

claude mcp add --transport http bolna https://mcp.bolna.ai/api/mcp \
  --header "Authorization: Bearer <your BOLNA_API_KEY>" \
  --scope user

or by hand-editing ~/.claude.json (or .mcp.json for a project-scoped copy):

{
  "mcpServers": {
    "bolna": {
      "type": "http",
      "url": "https://mcp.bolna.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer <your BOLNA_API_KEY>"
      }
    }
  }
}

Claude Desktop

Desktop's config only understands locally-run (stdio) servers, so reaching a remote HTTP server with a custom header needs the mcp-remote bridge, which runs locally and forwards the header on your behalf. Add this to claude_desktop_config.json:

{
  "mcpServers": {
    "bolna": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.bolna.ai/api/mcp",
        "--header",
        "Authorization: Bearer <your BOLNA_API_KEY>"
      ]
    }
  }
}

Restart Claude Desktop after editing the config.

Codex CLI

Reads the key from an environment variable rather than the config file:

export BOLNA_API_KEY="<your BOLNA_API_KEY>"

codex mcp add bolna \
  --url https://mcp.bolna.ai/api/mcp \
  --bearer-token-env-var BOLNA_API_KEY

Cursor

Add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "bolna": {
      "url": "https://mcp.bolna.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer <your BOLNA_API_KEY>"
      }
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "bolna": {
      "serverUrl": "https://mcp.bolna.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer <your BOLNA_API_KEY>"
      }
    }
  }
}

Zed

Add to settings.json. Zed doesn't support environment-variable interpolation in headers yet, so the key goes in directly:

{
  "context_servers": {
    "bolna": {
      "url": "https://mcp.bolna.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer <your BOLNA_API_KEY>"
      }
    }
  }
}

Claude Desktop (extension)

Instead of the mcp-remote bridge above, you can install this as a proper Desktop Extension (.mcpb) — a local, stdio-based build of the same 116 tools, packaged with a manifest so Claude Desktop can install it with one click and prompt you for your API key itself (no config file editing).

Build it from source:

npm run package:mcpb   # bundles src/stdio.ts, packs mcpb/ into bolna-mcp.mcpb

Then double-click bolna-mcp.mcpb, or drag it into Claude Desktop's Settings → Extensions, and enter your Bolna API key when prompted.

This local build talks directly to api.bolna.ai using only the raw API key path in src/lib/auth.ts — OAuth is specific to the remote server and isn't used here.

Any other MCP client

Point it at:

URL:     https://mcp.bolna.ai/api/mcp
Header:  Authorization: Bearer <your BOLNA_API_KEY>

claude.ai web/mobile

This server now implements real OAuth (via Bolna's Supabase-backed authorization server), so claude.ai's own "Add custom connector" flow (Settings → Connectors) should work with just the URL — no manually pasted token needed, since claude.ai handles the login/consent redirect itself the same way Claude Code does. This hasn't been separately verified on claude.ai web/mobile specifically yet (only Claude Code's CLI flow has been tested end-to-end so far) — the CLI/config options above remain the proven paths in the meantime.

Try it

After connecting, start a new conversation and ask something like:

"List my Bolna agents"
"What's my Bolna wallet balance?"
"Call +1... using my [agent name] agent"

Auth

Two ways to connect:

OAuth — sign in through Bolna's own login (Supabase-backed). This is what claude.ai's custom-connector UI and Claude Code's Authenticate prompt use automatically; no manual token needed.
Raw API key — pass your own Bolna API key as a Bearer token in the Authorization header, per the client examples above.

Either credential is verified before being forwarded to api.bolna.ai — see the comment block at the top of src/lib/auth.ts for how.

For local development, set BOLNA_API_KEY in .env and omit the header — the server falls back to it automatically.

Local dev

npm install
cp .env.example .env   # then fill in BOLNA_API_KEY
npm run dev             # or: vercel dev

The MCP endpoint is served at http://localhost:3000/api/mcp.

Deploy

Deployed under the Bolna AI Vercel team, aliased to mcp.bolna.ai:

vercel deploy --prod --scope bolna-ai

Set BOLNA_API_KEY as a Vercel environment variable only if you want a server-wide fallback for testing; production callers should supply their own key via the Authorization header.

Test with MCP Inspector

npx @modelcontextprotocol/inspector

In the Inspector UI, connect with:

Transport: Streamable HTTP
URL: http://localhost:3000/api/mcp (or your deployed URL + /api/mcp)
Header: Authorization: Bearer <your Bolna API key> (optional locally if BOLNA_API_KEY is set in .env)

Then use the Inspector's "List Tools" and "Call Tool" panels to exercise each of the 13 core tools with valid and invalid input.

Privacy Policy

See mcp.bolna.ai/privacy.

License

MIT

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityActive

ResponsivenessUnresponsive

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

FlowraOAuth
io.github.flowradev
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Agent Orchestration Autonomous Agents
11
Backtest360 A
com.backtest360
MCP server exposing the Backtest360 engine API as tools for AI agents.
Finance Research & Data
202
supportsheep
io.github.pooriaarab
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Customer Support Content Management Systems Marketing
1
Superforms B
co.superforms
Human-input bridge for AI agents with voice-first answer links, MCP tools, and HTTP APIs.
Agent Orchestration Speech Processing App Automation
112

Related MCP Servers

bubblyphone-agents
Communication Agent Orchestration Customer Support
JobXDubai
A
license
A
quality
D
maintenance
MCP server for BubblyPhone that lets AI assistants make real phone calls, manage AI voice agents, buy phone numbers in 30+ countries, and track billing. Supports 20 tools for full telephony control.
Updated 7 months ago (2026-04-04 08:47 UTC)
20
4 npm
1
MIT
VoIPbin MCP Serverofficial
Communication Email
voipbin
A
license
B
quality
C
maintenance
An MCP server that enables AI assistants to interact with the VoIPbin CPaaS platform, exposing tools for managing calls, flows, messaging, conferencing, and more.
Updated 13 days ago (2026-10-10 04:11 UTC)
66
35 PyPI
1
MIT
libredesk-mcp
Customer Support Communication
metanmai
A
license
C
quality
D
maintenance
MCP server that exposes the complete Libredesk REST API (54 endpoints) as tools, enabling natural language management of conversations, contacts, agents, teams, and more for the open-source customer support desk.
Updated 5 months ago (2026-06-06 08:28 UTC)
54
5 npm
4
MIT
utel-mcp
Communication
muhammadyusuf-kurbonov
F
license
A
quality
C
maintenance
An MCP server that wraps the UTEL IP-telephony REST API as MCP tools, enabling LLM agents to make authenticated HTTP requests to the UTEL API via a simple tool interface.
Updated 2 months ago (2026-08-26 10:49 UTC)
1
1
-

Bolna MCP Server

Two endpoints

Sub-accounts and switching between accounts

Available tools

Agents & calls

Executions

Batches

Dispositions (structured call extraction)

Extraction categories

Phone numbers & inbound

SIP trunks (bring your own carrier)

Legacy SIP trunks (deprecated)

Sub-accounts (enterprise)

Voice & providers

Knowledgebase (RAG)

Violations

Workflows

Workflow campaigns

Workflow executions

Graph agents

Account & documentation

Install & use

Claude Code

Claude Desktop

Codex CLI

Cursor

Windsurf

Zed

Claude Desktop (extension)

Any other MCP client

claude.ai web/mobile

Try it

Auth

Local dev

Deploy

Test with MCP Inspector

Privacy Policy

License

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

bubblyphone-agents

VoIPbin MCP Serverofficial

libredesk-mcp

utel-mcp