Voice
Bland MCP connector
The Bland connector brings your AI phone calls, recordings, transcripts and voices into Claude, ChatGPT, Cursor and the Elaichi Agent, so your team can place, review and stop Bland calls from the tools they already use.
-
How it connects. Connects with an API key. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect Bland to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Bland once
-
Open Connections, choose Add connection, and pick Bland.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a Bland API key. One person generates a token in Bland and pastes it once. Everyone else works through Share with, and never sees it.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Connect Bland to Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Connect Bland to ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Connect Bland to Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Bland to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Bland through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Sales
Call a fresh lead the moment it arrives
Kick off a Bland call down an existing pathway to a new lead, then ask for the transcript and a summary of what they said once the call ends.
-
Support
Find out how a callback went
Pull up a specific Bland call, read the corrected transcript, and check whether the customer's issue was resolved or needs a human follow up.
-
Operations
See what is on the phones right now
List every active Bland call, listen in on one that looks stuck, transfer it to a person, or stop all active calls if a campaign was launched by mistake.
-
Quality
Review recordings without opening a dashboard
Ask for yesterday's Bland calls, run the analysis on the ones that ran long, and collect the recordings that need a second listen.
-
Marketing
Pick and tune the voice for a campaign
Compare the Bland voices available on your account, rate the ones you tested, rename the finalists, and adjust the settings before an outbound push.
-
Engineering
Keep post-call results flowing downstream
Check which Bland post-call webhooks are set up, add one for a new system, and resend a delivery that your CRM missed.
Try asking
- “Summarize yesterday's Bland calls by outcome.”
- “Pull the corrected transcript for last night's longest call.”
- “Which Bland calls are active right now?”
AI tools
Bland tools for your AI agents
133 tools are ready to call through Elaichi's MCP endpoint the moment you connect Bland, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting Bland gets you
6 screens from the product, each doing one job for your Bland account.
The agent
Ask about Bland calls in plain language.
Answers come from live Bland calls, transcripts and recordings, not stale exports.
- calls
- transcripts
- recordings
- webhooks
Ask Elaichi to work across your apps.
Summarize yesterday's Bland calls by outcome.
Pull the corrected transcript for last night's longest call.
Which Bland calls are active right now?
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor reach Bland.
One governed MCP endpoint for Bland, no SDK and no shared API key.
Copy the endpoint
Tool catalog
133 Bland tools land ready to call.
Calls, transcripts, recordings and webhooks are covered without a line of custom code.
- Bland calls send simple pathway
- Bland calls analyze
- Bland calls stop
- Bland calls listen
Toolboxes
Every team gets its own Bland toolbox.
Support, sales and compliance each work from a toolbox curated for their remit.
- Support
- Sales
- Quality
- Compliance
Shared connections
Teammates use Bland without touching credentials.
Each Bland connection shows who connected it and which teams and members share it.
- Support EMEA
- Sales US
- Quality review
- Compliance archive
Audit log
Every Bland call action is on record.
When, who, what happened, type and resource, appended for each Bland request.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule turns Bland calls into action.
Six steps fetch calls, group them, draft a digest, await approval, post back.
Bland digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch calls
Bland
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Bland
Queued
Collections and dashboards
Bland call health, counted not asked for.
Four metrics, fourteen days of calls created and a team breakdown, refreshed on schedule.
Bland health
Refreshed 4 minutes ago · every 15 minutes · from the calls collection
Calls
1,284 ↓ 12%
Transcripts
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Calls created
Last 14 days
By team
Share of activity
Support EMEA 34%
Sales US 27%
Quality review 21%
Compliance archive 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Bland to Claude?
Connect Bland in Elaichi first: choose the Bland connector, paste in your Bland API key, and it is ready. Then in Claude open Customize, then Connectors, then Add, and paste the Elaichi endpoint https://api.elaichi.ai/mcp. There is no OAuth application to register in Bland and no client ID or secret to generate.
Does Bland work with ChatGPT and Cursor as well as Claude?
Yes. Once Bland is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Bland once and every client picks it up.
What can an AI agent actually do with my Bland data?
An agent can place a Bland call down one of your pathways, list active and past calls, pull a recording or corrected transcript, run the call analysis, listen in, transfer a live call to a person, or stop a call. It can also manage your Bland voices and post-call webhooks and check your account details. Because Bland exposes a lot of actions, short concrete asks such as "stop all active calls" work better than long paragraphs.
Does connecting Bland give the AI my whole account?
The agent only gets what the Bland API key you connected can already reach, nothing more. Elaichi can then narrow that further, for example allowing your team to read Bland transcripts and recordings but not place or stop calls. Elaichi never widens access beyond what the key itself allows.
Can I stop an agent from deleting voices or stopping calls in Bland?
Yes. Restrictions in Elaichi work per action, so you can block deleting Bland voices, stopping calls or placing new ones while leaving transcripts and recordings open. A blocked action is never shown to Claude, ChatGPT or Cursor at all, so no prompt, however worded, can reach it.
What happens to a Bland connection when someone leaves?
When you offboard a person in Elaichi, their access to Bland through every AI client ends at once. If they had shared a Bland connection with a team, it keeps working for everyone else. If you want Bland gone entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client together.
Put Bland in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.