CALL-E Integrations

CALL-E is your AI agent for getting phone work done.

Tell CALL-E your goal, and it handles the phone task end-to-end: it plans, calls, adapts in real time, follows through, and improves along the way.

Use CALL-E directly, or integrate it into agents, platforms, and business systems through Skills, Plugins, SDKs, or APIs.

New users get 20 free calls to get started. Sign up now!

Website · Docs · Try on ClawHub · Discord

Quick Start

The fastest path — paste this into any AI agent (Claude Code, Codex, Cursor, and more):

Install CALL-E for me: https://open.heycall-e.com/document/mcp-archive/CALL-E-installation-guide.md

Your agent handles the rest.

SDK — five lines to your first call:

import{CalleClient}from"@call-e/calle";// pnpm add @call-e/calleconstclient=newCalleClient({apiKey: "your_api_key"});constcall=awaitclient.calls.createAndWait({task: "Call +15550123456 and confirm tomorrow's 9am appointment.",});console.log(call.status,call.taskCompleted);

What is CALL-E?

CALL-E automates goal-driven phone tasks that scripted voice bots cannot handle.

Traditional calling platforms use prebuilt bots optimized for high-volume, repetitive scripts. CALL-E is different: you describe a goal, and CALL-E figures out how to achieve it over the phone. It handles natural conversation, adapts to unexpected responses, and returns a structured result when the call ends.

This makes CALL-E practical for tasks where a rigid script would fail — appointment confirmations, research calls, follow-ups, lead qualification.

Call lifecycle:

flowchart LR
A["Goal + phone number"] --> B["Plan"]
B --> C{"Details\ncomplete?"}
C -- "Missing info" --> D["Clarify"]
D --> B
C -- "Confirmed" --> E["Dial"]
E --> F["Live conversation"]
F --> G["Structured result\n+ transcript\n+ summary"]

Capabilities

Capability	Description
Live Task Progress	Track a call from planning to completion: status, activity history, outcomes, and next steps
Smart Goal Clarification	CALL-E asks for missing details — recipient, timing, language, success criteria — before dialing
Managed Call Execution	Handles number setup, outbound dialing, monitoring, and result capture
Structured Results	Returns summaries, transcripts, and schema-validated structured data you can act on directly
Scheduled and Batch Calling	Schedule individual calls or send a batch task to multiple recipients
In-Task Optimization	Adapts call strategy based on prior attempts within the same task
Real-World Voice Handling	Manages live pickup, voicemail, call screening, hold, transfers, silence, and interruptions
Multiple Integration Paths	Agent plugins, MCP, SDKs, APIs, and enterprise systems
Safety and Governance	Number governance, rate limits, concurrency controls, blocklists, kill switches, redacted logs, and audit trails

In Development

Goal-Driven Long Tasks — CALL-E plans a multi-step task end-to-end: it designs the calling approach, executes the calls, learns from real outcomes, and continuously improves its strategy over time. This goes beyond single calls — CALL-E learns how to achieve each phone-based goal more reliably across attempts. This feature is under active development and not yet generally available.

Get Started

Choose the integration path that fits your use case:

Use case	Integration	Start here
Use CALL-E inside Claude Code, Codex, Cursor, OpenClaw, Hermes, or any skills.sh agent	Agent install	Agent Install
Connect any Streamable HTTP MCP client	MCP	MCP
Call CALL-E from a TypeScript or Python SDK	SDK	SDK
Call CALL-E from any backend	Developer API	API

Agent Install

Paste this single prompt into your agent for automatic setup:

Install CALL-E for me: https://open.heycall-e.com/document/mcp-archive/CALL-E-installation-guide.md

Works in Claude Code, Codex, Cursor, and any agent that can run shell commands. The linked guide stays up to date, so the prompt never changes.

For manual setup, expand the table below or see the full install guide.

MCP

CALL-E exposes a Streamable HTTP MCP endpoint. Any compatible MCP client can connect, authorize via OAuth, and run CALL-E with three tools.

Endpoint:

https://seleven-mcp-sg.airudder.com/mcp/openagent_oauth

Transport: Streamable HTTP

Tool flow:

sequenceDiagram
participant Client as MCP Client
participant CE as CALL-E
participant Phone
Client->>CE: plan_call(goal, phone)
CE-->>Client: plan_id, confirm_token, ready_to_run=true
Note over Client: User confirms intent
Client->>CE: run_call(plan_id, confirm_token)
CE-->>Client: run_id
CE-)Phone: Outbound call
Note over Client,CE: Wait ~60s, then poll while call is in progress
loop Until terminal status
Client->>CE: get_call_run(run_id)
CE-->>Client: status, activity, transcript
end

Tools:

Tool	What it does
`plan_call`	Creates or refines a call plan. Does not place a call. Returns `plan_id`, `confirm_token`, and `ready_to_run`.
`run_call`	Starts the planned call. Requires the exact `plan_id` and `confirm_token` from the preceding `plan_call`. Can place a real phone call.
`get_call_run`	Reads run status, activity, summary, and transcript. Read-only. After a call starts, wait ~60 seconds before the first poll, then every 5–10 seconds until terminal.

For OAuth details, tool details, and MCP setup, see the MCP guide.

SDK

CALL-E server SDKs are available for TypeScript and Python. Use them in trusted backend services, workers, and automation systems.

Install:

# TypeScript
pnpm add @call-e/calle
# Python
pip install calle-ai

Set your API key:

export CALLE_API_KEY="calle_live_key"

Get your API key from the CALL-E dashboard.

TypeScript:

import{CalleClient}from"@call-e/calle";constclient=newCalleClient({apiKey: process.env.CALLE_API_KEY!});constcall=awaitclient.calls.createAndWait({task: "Call <E164_PHONE> and confirm whether they can attend Friday lunch.",resultSchema: {type: "object",required: ["can_attend"],properties: {can_attend: {type: "string",enum: ["yes","no","unknown"]},},},});console.log(call.status);console.log(call.taskCompleted);console.log(call.completionConfidence);console.log(call.structuredResult);console.log(call.evidence);

Python:

importosfromcalleimportCalleClientclient=CalleClient(api_key=os.environ["CALLE_API_KEY"])
call=client.calls.create_and_wait(
task="Call <E164_PHONE> and confirm whether they can attend Friday lunch.",
result_schema={
"type": "object",
"required": ["can_attend"],
"properties": {
"can_attend": {"type": "string", "enum": ["yes", "no", "unknown"]},
},
},
)
print(call["status"])
print(call["task_completed"])
print(call["structured_result"])
print(call["evidence"])

API

The CALL-E Developer API provides direct HTTP access for any trusted backend, worker, or workflow system.

Set credentials:

export CALLE_API_KEY="calle_live_key"export CALLE_BASE_URL="https://api.heycall-e.com"

Endpoints:

Method	Path	Description
`POST`	`/v1/calls`	Create a one-recipient or batch call task.
`GET`	`/v1/calls/{call_id}`	Read status, summaries, structured results, and transcripts.
`GET`	`/v1/calls/{call_id}/events`	List developer-facing call events.
`POST`	`/calle/webhook`	Receive terminal call result webhooks.

Create a call:

curl "$CALLE_BASE_URL/v1/calls" \
--request POST \
--header "Authorization: Bearer $CALLE_API_KEY" \
--header "Content-Type: application/json" \
--header "Idempotency-Key: wf_123_friday_lunch" \
--data '{ "task": "Call each recipient and ask whether they can attend Friday lunch.", "recipients": [ { "phones": ["<E164_PHONE>"], "region": "US", "locale": "en-US" } ], "result_schema": { "type": "object", "required": ["completed_count"], "properties": { "completed_count": { "type": "integer" } } }, "recipient_result_schema": { "type": "object", "required": ["can_attend"], "properties": { "can_attend": { "type": "string", "enum": ["yes", "no", "unknown"] } } }, "metadata": { "workflow_run_id": "wf_123" }, "webhook_url": "https://example.com/calle/webhook" }'

Read a result:

curl "$CALLE_BASE_URL/v1/calls/call_123" \
--header "Authorization: Bearer $CALLE_API_KEY"

Terminal call result:

Example response

{
"status": "completed",
"task_completed": true,
"completion_confidence": { "score": 0.92, "label": "high" },
"evidence": ["The recipient said they can attend Friday lunch."],
"structured_result": { "completed_count": 1 },
"recipients": [
{
"structured_result": { "can_attend": "yes" },
"attempts": [
{
"transcript_turns": [
{ "offset_seconds": 0, "speaker": "bot", "text": "Hi, I am calling about Friday lunch." },
{ "offset_seconds": 4, "speaker": "user", "text": "Yes, I can attend." }
]
}
]
}
]
}

For authentication, webhooks, and the full reference, see the API docs.

Supported Regions and Languages

Use these country codes with the SDK and API recipient settings.

Country	Country Code	Calling Code	Languages	Line Region
United States of America	`US`	+1	English	Local
Singapore	`SG`	+65	English	Local
Malaysia	`MY`	+60	English, Chinese	Local
India	`IN`	+91	English, Hindi	Local
United Arab Emirates	`AE`	+971	English, Arabic	Local
Australia	`AU`	+61	English	Local
Canada	`CA`	+1	English	International
United Kingdom of Great Britain and Northern Ireland	`GB`	+44	English	International
Viet Nam	`VN`	+84	Vietnamese, English	International
Germany	`DE`	+49	English, German	International
Japan	`JP`	+81	Japanese, English	International
France	`FR`	+33	French, English	International
Mexico	`MX`	+52	Spanish, English	Local
Brazil	`BR`	+55	Portuguese, English	Local
Indonesia	`ID`	+62	English	International
Philippines	`PH`	+63	English	International
Kenya	`KE`	+254	English	International
Netherlands	`NL`	+31	English	International
Poland	`PL`	+48	Polish, English	International
Bangladesh	`BD`	+880	Bengali, English	International
Nigeria	`NG`	+234	English	International
Oman	`OM`	+968	English, Arabic	International
Thailand	`TH`	+66	English, Thai	International
Namibia	`NA`	+264	English	International
Cameroon	`CM`	+237	English, French	International
Mozambique	`MZ`	+258	English, Portuguese	International
Saudi Arabia	`SA`	+966	English, Arabic	International
Finland	`FI`	+358	English	International
Ukraine	`UA`	+380	English, Ukrainian	International
Sri Lanka	`LK`	+94	English, Tamil	International
Botswana	`BW`	+267	English	International
Pakistan	`PK`	+92	English, Urdu	International
Turkey	`TR`	+90	Turkish	International
Honduras	`HN`	+504	English, Spanish	International

Notes

Local means calls are placed using a local phone line for the destination country or region.
International means calls are currently placed using CALL-E's international phone numbers and are primarily intended for testing. For production use with a local phone number, contact the CALL-E team to enable a local line for the destination country.

Examples

Runnable demos are in examples/:

Example	What it shows
Standard MCP OAuth clients	TypeScript and Python clients connecting to CALL-E via standard MCP OAuth over Streamable HTTP. Good starting point for any new MCP client.
CALL-E broker login MCP clients	TypeScript and Python clients using CALL-E brokered login, local token caching, and MCP HTTP calls. Useful when the environment cannot complete a browser OAuth flow.
Python batch runner	Python JSONL batch runner using `calle` CLI auth state, FastMCP, Rich output, and MCP tool-call metadata. Demonstrates processing multiple call tasks from a file.

These are starting-point demos, not the canonical SDK or API contract.

Troubleshooting

If installation, authentication, or MCP tool verification fails, see the CALL-E troubleshooting guide.

Common issues covered:

Cursor sandbox network restrictions — CONNECT tunnel failed, response 403 means the Cursor agent shell is blocking outbound HTTPS. Fix: switch Cursor Auto-Run Mode to Run Everything (Unsandboxed) in Cursor Settings → Agents.
calle auth login failures — fetch failures, login errors, and token cache issues.
Missing MCP tools — how to confirm that plan_call, run_call, and get_call_run are available after install.

Repository Structure

This is a multi-ecosystem integration monorepo. Each integration has its own package and marketplace entry point.

Path	Purpose
`packages/cli`	Shared `calle` CLI. Handles authentication, token caching, MCP tool discovery, and call workflow shortcuts. Used by all agent integrations.
`packages/core`	Shared core library used across packages.
`packages/codex-plugin`	Codex plugin providing the `$calle` skill.
`packages/claude-plugin`	Claude Code plugin providing the `/calle:calle` skill.
`packages/cursor-plugin`	Cursor plugin bundling the MCP server config, `calle` skill, and real-call safety rule.
`packages/openclaw-cli-skill`	OpenClaw CALL-E skill source.
`packages/skills-sh-skill`	skills.sh compatible CALL-E skill package.
`skills/calle/`	Portable `calle` skill for public skills.sh search and install.
`examples/`	Runnable MCP client demos.
`docs/`	Integration guides, install docs, and troubleshooting.

For layout rules and marketplace naming conventions, see docs/agent-integration-layout.md.

Telemetry

The calle CLI sends best-effort usage telemetry to help diagnose installation, authentication, and tool availability issues.

What is collected: anonymous installation ID, CLI version, integration source (e.g. claude/claude_code_plugin/<version>), command stage, outcome, error type, and server host hash.

What is never collected: phone numbers, call goals, OAuth tokens, broker login URLs, transcripts, or contact data.

Opt out with any of:

DO_NOT_TRACK=1 calle auth status
CALLE_TELEMETRY=0 calle auth status
calle auth status --no-telemetry

Broker and MCP requests still create service-side security, audit, and operational logs required to run calls.

Development

Requires Node >=22 and pnpm >=10.18.3, Changesets, and GitHub Actions.

pnpm install
pnpm check
pnpm test
pnpm pack:dry-run

Package-specific checks

pnpm --filter @call-e/core check
pnpm --filter @call-e/core test
pnpm --filter @call-e/cli check
pnpm --filter @call-e/cli test
pnpm --filter @call-e/codex-plugin check
pnpm --filter @call-e/codex-plugin test
pnpm --filter @call-e/claude-plugin check
pnpm --filter @call-e/claude-plugin test
pnpm --filter @call-e/cursor-plugin check
pnpm --filter @call-e/cursor-plugin test
pnpm --filter @call-e/openclaw-cli-skill check
pnpm --filter @call-e/openclaw-cli-skill test
pnpm --filter @call-e/skills-sh-skill check
pnpm --filter @call-e/skills-sh-skill test
pnpm run check:examples

For user-visible package changes, add a changeset. The release workflow publishes changed @call-e/* packages to npm and maintains the @call-e/codex-plugin@latest and @call-e/claude-plugin@latest install aliases.

See CONTRIBUTING.md for pull request guidelines.

Name		Name	Last commit message	Last commit date
Latest commit History 140 Commits
.agents		.agents
.changeset		.changeset
.claude-plugin		.claude-plugin
.cursor-plugin		.cursor-plugin
.githooks		.githooks
.github/workflows		.github/workflows
assets		assets
docs		docs
examples		examples
packages		packages
scripts		scripts
skills/calle		skills/calle
.gitattributes		.gitattributes
.gitignore		.gitignore
.npmrc		.npmrc
AGENTS.md		AGENTS.md
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
CONTRIBUTING.md		CONTRIBUTING.md
LICENSE		LICENSE
README.md		README.md
SECURITY.md		SECURITY.md
package.json		package.json
pnpm-lock.yaml		pnpm-lock.yaml
pnpm-workspace.yaml		pnpm-workspace.yaml
skills-lock.json		skills-lock.json

Navigation Menu

Uh oh!

Repository files navigation

CALL-E Integrations

Quick Start

Contents

What is CALL-E?

Capabilities

In Development

Get Started

Agent Install

MCP

SDK

API

Supported Regions and Languages

Examples

Troubleshooting

Repository Structure

Telemetry

Development

Community

About

Releases

Packages

Contributors

Languages

Uh oh!

Folders and files

Latest commit

History

Repository files navigation

CALL-E Integrations

Quick Start

Contents

What is CALL-E?

Capabilities

In Development

Get Started

Agent Install

MCP

SDK

API

Supported Regions and Languages

Examples

Troubleshooting

Repository Structure

Telemetry

Development

Community

About

Resources

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages