Bland AI MCP. Automate voice outreach and analyze every call's outcome.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Bland AI MCP Server manages high-fidelity, automated voice workflows. It lets your AI client initiate outbound calls to 200+ countries, manage persistent AI personas, and handle full call lifecycle data retrieval.
Use it to automate lead qualification, appointment reminders, and customer support outreach without manual dialing.
What your AI agents can do
Analyze call transcript
Analyzes a finished call's transcript to extract variables, sentiment, or summaries.
Create voice agent
Creates a new, persistent AI agent persona with defined prompts and voice settings.
Delete voice agent
Removes an existing AI persona from the system.
Your AI client initiates outbound calls to specific numbers, and you can tell it to stop a call mid-stream if needed.
You create, update, and delete persistent AI agents, setting their core prompts, voice, and personality so they sound consistent.
You get the complete transcript, recording link, and status for any call that happened.
You run post-call analysis on a transcript to extract specific data points, like sentiment or lead status.
You list all available phone numbers and high-fidelity AI voices purchased in your account.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
019dd0c2analyze call transcript
Analyzes a finished call's transcript to extract variables, sentiment, or summaries.
019dd0c2create voice agent
Creates a new, persistent AI agent persona with defined prompts and voice settings.
019dd0c2delete voice agent
Removes an existing AI persona from the system.
019dd0c2get agent config
Retrieves the current configuration and settings for a specific AI agent.
019dd0c2get call details
Fetches the transcript, recording link, and status for a specific phone call ID.
019dd0c2list available voices
Lists all high-fidelity AI voices you have purchased and can use.
019dd0c2list phone numbers
Retrieves a list of all purchased phone numbers associated with your account.
019dd0c2list recent calls
Shows a list of your most recently completed phone interactions.
019dd0c2list voice agents
Lists all AI personas you have already configured and deployed.
019dd0c2send phone call
Initiates an outbound phone call using a specified AI agent and phone number.
019dd0c2stop active call
Stops a phone call that is currently in progress.
019dd0c2update agent config
Modifies the settings, prompts, or voice of an existing AI agent.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Bland AI, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Bland AI MCP Server gives your AI client full control over automated, high-fidelity voice workflows. Your agent can initiate outbound calls to over 200 countries, manage persistent AI personas, and grab all the data after a call finishes. You use this to automate everything from qualifying leads to sending out appointment reminders or running customer support outreach without needing anyone to dial a phone.
Start and manage calls
Your AI client sends the signal to start an outbound call using a specified AI agent and phone number (send_phone_call). You can tell your agent to stop a call mid-stream if you need to (stop_active_call). You can also check the list of your most recent phone interactions (list_recent_calls) and pull up all your purchased phone numbers (list_phone_numbers).
Control AI personas
Your agent builds and maintains its own identity with Bland AI. You create new, persistent AI agents (create_voice_agent), defining their core prompts, voice settings, and personality so they sound consistent. You can modify an existing agent's settings, prompts, or voice (update_agent_config), and when you're done with a persona, you can wipe it clean (delete_voice_agent).
You can also check the list of all AI personas you've set up (list_voice_agents) and pull up the current configuration for any specific agent (get_agent_config).
Retrieve call data
When a call happens, you get the full rundown. You can fetch the transcript, the recording link, and the status for any specific call ID (get_call_details). You also get a list of every high-fidelity AI voice you bought and can use (list_available_voices).
Analyze call outcomes
After the call ends, you run post-call analysis on the transcript to pull out specific data points. You can use analyze_call_transcript to extract variables, sentiment, or summaries from the finished conversation.
Manage phone resources
Your agent handles the whole setup. You can pull up all your purchased phone numbers (list_phone_numbers) and list all your configured AI personas (list_voice_agents).
How Bland AI MCP Works
- 1 Your AI client calls
create_voice_agentto define the agent's name, voice, and core instructions. - 2 The agent uses
send_phone_callto initiate the call, following the defined script and targeting a specific number. - 3 After the call ends, your client calls
get_call_detailsto retrieve the transcript and recording link, which you can then pass toanalyze_call_transcript.
The bottom line is that your AI client manages the entire call lifecycle—from setup and execution to data extraction—using a sequence of tool calls.
Who Is Bland AI MCP For?
The Sales Operations Lead who spends too much time manually following up on cold leads. The Customer Success Manager who needs to send appointment reminders across multiple time zones without logging into a separate calling system. The Developer who needs to integrate high-speed, conversational voice actions into a custom internal workflow.
Uses send_phone_call to qualify leads instantly and uses analyze_call_transcript to monitor conversion trends without manual reporting.
Uses list_voice_agents to manage automated appointment reminders and uses list_recent_calls to check customer sentiment immediately.
Integrates the full call lifecycle into a custom system, using tools like get_call_details and update_agent_config to build complex, stateful business logic.
What Changes When You Connect
- Automate outreach instantly. Instead of manually dialing, use
send_phone_callto trigger calls to any number in 200+ countries, letting your agent handle the script. - Ensure brand consistency. Use
create_voice_agentto build AI personas with fixed prompts and voices. Every call sounds like your brand, every time. - Stop manually compiling data. After a call, run
get_call_detailsto get the full transcript and recording link. Then, feed that data toanalyze_call_transcriptfor instant insights. - Manage your voice infrastructure. Use
list_phone_numbersandlist_available_voicesto check your purchased resources without logging into a dashboard. - Maintain control over agents. If a script needs tweaking, use
update_agent_configorget_agent_configto adjust the agent's core instructions without rebuilding the whole thing.
Real-World Use Cases
Lead Qualification After Hours
A sales rep needs to qualify 50 cold leads between 6 PM and 8 PM. Instead of spending hours manually calling and taking notes, the rep uses send_phone_call to run the agent. The agent handles the conversation, and the rep later calls analyze_call_transcript to pull a summary of every lead's interest level.
Automating Appointment Confirmations
A CSM needs to remind 30 clients about a meeting next week. They use create_voice_agent to build a 'Reminder Bot' persona. Then, they loop through the contacts and use send_phone_call to execute the reminders, getting confirmation details via get_call_details.
Handling Support Triage
The support team gets a sudden influx of inquiries. Instead of having agents manually answer basic questions, they set up an AI persona with create_voice_agent. This agent uses the system to guide basic triage, leaving complex issues for human staff.
Auditing Agent Behavior
A manager needs to check if agents are sticking to script or if they are deviating. They use list_voice_agents to see who is active, and then use get_call_details to retrieve the raw transcript and recording for review.
The Tradeoffs
Manual Dialing & Logging
A sales rep calls 10 people, writes down notes, and uploads the call recording to a spreadsheet. This takes an hour and introduces transcription errors.
→
Set up an agent with create_voice_agent and use send_phone_call to automate the calls. After the batch is done, call analyze_call_transcript to get a structured summary of all interactions.
Hardcoding Call Flows
Relying on complex, multi-step internal logic within the agent's core prompt, forcing it to fail if the user deviates even slightly.
→
Use update_agent_config to fine-tune the agent's guardrails, keeping the core logic simple. Let the AI handle the conversation flow, and use the tools to manage the inputs and outputs.
Ignoring Call Data
The call ends, the recording saves, and the team never checks the transcript. All the effort is wasted, and no insights are gathered.
→
Always call get_call_details immediately after a call. Then, use analyze_call_transcript to extract specific metrics like sentiment or key variables.
When It Fits, When It Doesn't
Use this server if your core need is managing and automating the full lifecycle of phone calls—from initiating the call to extracting structured data from the conversation. You need a single source of truth for call data, which tools like get_call_details and analyze_call_transcript provide. You should use it if you need to scale calling operations across multiple time zones or languages.
Don't use this if your primary problem is managing internal documents (use a document retrieval tool) or if you only need to send simple SMS messages (use a dedicated messaging tool). If you just need to trigger a single, one-off API call, a simple function wrapper might be enough, but this server handles the whole conversation context.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Bland AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 12 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Handling phone calls used to be a nightmare of manual logging and follow-up.
Today, if a sales rep needs to qualify a lead, they manually dial the number. They listen, take notes on a pad, and then copy-paste key takeaways into the CRM. If they're calling fifty people, that process takes all day and the data is messy.
With the Bland AI MCP Server, you let your agent do the calling. You initiate the call using `send_phone_call`, and when it's done, you use `analyze_call_transcript`. You get clean, structured data on sentiment and lead status, not messy notes.
Bland AI MCP Server: Automate the entire voice workflow
The manual steps that vanish are: dialing the number, staying on the line, transcribing the conversation, and then manually summarizing the outcomes. You no longer have to manage multiple systems just to get a summary.
Now, you use a sequence of tool calls—from `create_voice_agent` to `send_phone_call`—to manage the entire process. It’s a single, programmable workflow that handles the complexity.
Common Questions About Bland AI MCP
How do I use `send_phone_call` with a specific script? +
You must first use create_voice_agent to define the agent's personality and core instructions. Then, send_phone_call executes the call using those saved agent settings.
Can I get a transcript for a call I made using `get_call_details`? +
Yes, get_call_details retrieves the full transcript, the recording link, and the call status for the specified call ID.
What does `analyze_call_transcript` actually do? +
It takes a call transcript and runs post-processing analysis, allowing you to pull out structured data like sentiment or specific variables from the text.
How do I manage my AI agents with `list_voice_agents`? +
You use list_voice_agents to see all your existing AI personas. You can then use get_agent_config to view the detailed prompt settings for any of them.
Is `send_phone_call` synchronous? +
No. The tool initiates the call and returns a job ID. You must use subsequent calls (like get_call_details) to check the status and retrieve the final data.
How do I modify an existing AI persona using `update_agent_config`? +
You use update_agent_config to adjust settings for an active agent. This lets you change the core prompt, personality details, or voice assignment without recreating the entire persona.
What is the difference between `list_voice_agents` and `get_agent_config`? +
Listing agents shows a summary of all configured personas. Use get_agent_config when you need the specific, detailed prompt structure or settings for one agent you've already selected.
If a call fails, how do I check the status using `list_recent_calls`? +
The list_recent_calls tool provides metadata for past interactions. You check the status fields returned by the API to see if the call connected, failed, or was dropped.
How do I find my Bland AI API Key? +
Log in to your account, navigate to Settings > API Keys, and generate a new key for your integration.
Can I use specific AI voices via agent? +
Yes! The send_phone_call and create_voice_agent tools allow you to specify voice IDs (e.g., 'maya', 'mason') programmatically.
How do I retrieve call transcripts? +
Use the get_call_details tool with a specific call ID to retrieve the high-fidelity transcript and recording link directly from the platform.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Home Assistant
Control smart home devices and automations via Home Assistant REST API — lights, climate, media, covers, sensors, and more.
ArcGIS
Automate mapping and spatial analysis via ArcGIS — perform geocoding, route solving, vehicle routing, and calculate origin-destination matrices from any AI agent.
Volvo Cars Connected
Monitor and manage your connected Volvo vehicle — check fuel levels, battery status, door locks, and trip statistics directly via AI.
You might also like
Persona
Manage identity verification workflows via Persona — handle inquiries, manage accounts, and inspect verifications directly from your AI agent.
OMDb API
Search movies & TV shows, get ratings, cast, plot details, and IMDb data via the Open Movie Database API.
Google Calendar
Sync and orchestrate your agenda securely — scan, schedule, and manipulate Google Calendar events natively in chat.