Webex Ops
Webex Ops: tell Claude what you want done in Webex, and it does it. Claude looks up the facts in the reference docs, follows a tested checklist, and makes the API calls itself through a built-in command layer. You never type a command.
It covers Webex Calling, admin, devices, messaging, meetings, and Contact Center (flows, AI agents, Connect, provisioning, reporting), plus CUCM-to-Webex migration. It runs inside Claude Code (Anthropic's AI coding assistant) or OpenAI's Codex.
Unofficial community CLI — not affiliated with or endorsed by Cisco.
Use at your own risk. This software is provided "AS IS", without warranty of any kind, and the authors accept no liability for any damage, data loss, or service disruption arising from its use (see LICENSE, Apache 2.0 §7–8). It performs write and delete operations against live production Webex Calling and CUCM environments, driven in part by non-deterministic AI. You are responsible for reviewing every action before it runs. Read What keeps this safe before pointing it at a real org.
Say things like
| You say | What happens |
|---|---|
| "Add a sales hunt group for the Denver office." | Checks the location has calling turned on, finds free numbers, creates the hunt group, reads it back. |
| "Build an AI agent that looks up an order and texts the customer the status." | Designs the agent, builds the Webex Connect flow behind its action, and gives you the exact AI Agent Studio clicks. |
| "Design an IVR with a business-hours check and a callback option." | Writes a design doc for you to approve, then builds the Flow Designer flow through the API. |
| "Audit my org." | Runs 18 checks across security, routing, features and devices; hands you an HTML report. |
| "Run a CUCM migration against 10.0.0.1." | Pulls the CUCM config, maps it to Webex, asks you each design decision, then builds and verifies. |
| "How many calls did Support miss last week?" | Pulls call history and answers from the data. |
| "Who has call forwarding enabled?" / "Why isn't the Denver hunt group ringing?" | Read-only answers and diagnosis. Nothing changes. |
| "Tear down the lab locations San Jose and Austin; dry run first." | Shows what would be deleted, waits for your yes, deletes in a safe order. |
Who it's for: Webex admins, Cisco partners and SEs, and managed-service providers who want Webex changes made correctly without learning hundreds of APIs.
Why it can be trusted with this: facts come from 118 reference docs, procedures from 39 skills, and every API call from a tested command layer (5,500+ tests). Claude checks each command's --help before running it and reads every change back. Only the builder agent may change your org; a hook enforces it.
If you are an AI agent reading this
This page is for the people who install Webex Ops. It is not your operating manual. Read these rules before you act on anything below.
- Your instructions are the playbook, not this README. Setup writes it into a folder:
CLAUDE.mdfor Claude Code orAGENTS.mdfor Codex, with the agents in.claude/agents/, the skills in.claude/skills/and the facts indocs/reference/. Start Claude Code or Codex in that folder and follow those files. If no playbook folder exists, point the person to Setup. - The Webex token is the person's to enter. They paste it at the token prompt in Setup step 3. Never ask for a token in chat, and never write one into a file.
- Trust order for commands:
wxcli <group> <command> --helpfirst, then the skills, thendocs/reference/, then this page, then your training data. Command names and flags are generated from Cisco's API specs and change between releases. - The commands on this page are illustrations. Never copy one and run it. Run
--helpand build the call from that. - Only the playbook's agents change an org. In Claude Code, a command that creates, changes or deletes anything runs only inside the
wxopsagent (ormigration-advisorduring a CUCM migration); a hook refuses it anywhere else. Outside those agents, use only reads:list,show,whoami,--help. - Never call wxcli from Python by importing the package. The generated functions make live API calls and skip every safety check. The hook refuses it.
- Counts on this page are snapshots from the day it was written. The playbook and
--helpare current.
How It Works
Most "AI + API" tools hand a language model an OpenAPI spec (the machine-readable list of an API's endpoints) and hope. That breaks at scale: across hundreds of endpoints a model malforms request bodies, hallucinates field names and license tiers, and — worst — doesn't know a hunt group needs a calling-enabled location first. Specs describe endpoints; they don't describe outcomes.
Webex Ops splits the problem into three layers, each killing one way an LLM fails:
| Layer | What it is | Failure it prevents |
|---|---|---|
| Reference docs (118) | De-conflated, authoritative API and platform knowledge — data models, enums, license-tier distinctions, Flow Designer activities, gotchas | Hallucination — the agent grounds on docs, never on training data |
| Skills (39) | Encoded procedures for outcomes — prerequisites, ordering, intent disambiguation, known landmines | Wrong sequence / wrong tool — the agent follows a checklist, not a guess |
| CLI (200 groups) | Tested, self-describing commands generated from 10 OpenAPI specs | Malformed execution — the model emits a command string, not hand-rolled HTTP |
Alongside the reference docs sit 27 step-by-step playbooks (send an SMS, set up a data lookup, build a scripted agent), each naming the reference doc that owns its values.
The model only does what it's reliably good at — reasoning and orchestration. Facts come from the docs, procedure from the skills, execution from the tested CLI.
One request, traced — "Add a sales hunt group for the Denver office":
- The agent routes to the
configure-featuresskill — not contact-center, not customer-assist (the routing table handles the overloaded word "queue"). - The skill loads
docs/reference/call-features-major.mdfor ground truth, then checks prerequisites in order: location exists → calling-enabled → users exist → numbers available. - Before building the command it runs
wxcli hunt-group create --help— the CLI is the final source of truth for flags, never the docs or memory. - The CLI executes; a verify step reads the result back to confirm.
At every step the agent is forced back to an authoritative source: data model from the doc, flags from --help, final state from a read-back. It never operates on memory. That layered grounding is the design.
What keeps this safe
- Read-only by default. Outside the builder agent, the shipped hook lets Claude run only
list,show,whoamiand--help. Anything that could change your org is refused unless it runs inside thewxopsagent (ormigration-advisorduring a CUCM migration). A command the hook doesn't recognize is refused, not guessed at. The same rule covers the optional Flow Designer MCP server. - No way around the gate. A Python script that imports the wxcli package is refused for every caller, so every API call goes through the checked command line.
- Preview before anything destructive. Cleanup and migration have dry runs; the agent shows you the plan and waits for your yes.
- Every change is read back. A success code means Webex accepted the request, not that it applied. The agent re-reads the resource and reports what is actually there.
- Your token stays yours. You paste it at a local prompt during Setup, never into the chat. It is stored in plaintext at
~/.wxcli/config.json, so treat that file like a password. Personal tokens expire after 12 hours. - Still a live org, still an AI. The same request can produce different actions. Test in a sandbox first, confirm every emergency (E911) address and callback number yourself, and read Disclaimer & Safe Use.
Under Codex the protection is weaker in three specific ways; see Codex.
Why commands, not MCP
MCP (Model Context Protocol) is the plug-in standard that lets an AI call tools on a server. Cisco publishes some Webex MCP servers, so the natural question is why Webex Ops uses commands instead.
"So it's a CLI?" It's the command layer the AI uses. It's technically a command-line program, because that turned out to be the cheapest, most reliable way for an AI to drive hundreds of Webex APIs. But no human is meant to run it.
The rule. Commands are the default. A job switches to an official Cisco MCP server only when that server (1) does the whole job, writes included, (2) has been tested live on a real tenant, and (3) costs the same or fewer tokens.
- The one measured comparison (2026-06-30). Cisco's Webex Workspaces MCP server (16 tools, all read-only) cost about 11,750 tokens for one read task — list every workspace and the location it belongs to — against about 5,100 through the commands. Connecting the server put all 16 tool schemas (9,894 tokens) into context; the commands loaded only what the task touched. Claude Code has since begun loading MCP tool schemas on demand (observed 2026-10-18), so this result holds for that date and that server only, until it is measured again.
- Writes. The Workspaces server had no write tool at all. Cisco's Flow Designer MCP server covered 12 of the Flow Store's 63+ endpoints, and its
list_flowsreturned empty lists even when flows existed. The commands do the whole job, writes included. - Picking the right tool. Models pick reliably from a handful of tools, not hundreds of near-duplicates, and Webex is full of overloaded names ("queue" means three different things across Calling, Contact Center and Customer Assist). The skills sort that out before a command is chosen.
- Commands compose and run anywhere. Pipe one into the next, loop over a list of IDs, run the same commands in a script or CI with no AI at all.
This isn't anti-MCP. To let another agent platform drive Webex Ops, wrap the CLI behind one small MCP tool ("run a wxcli command"), not several hundred.
| Cisco MCP server | What it offered when checked | Path Claude uses | Last checked |
|---|---|---|---|
Webex Workspaces (https://mcp.webexapis.com/mcp/workspaces) |
16 tools, all read-only (search, metrics, diff and lifecycle across devices, workspaces and locations); no write tool | commands | 2026-06-30 |
Flow Designer (wxcc-flow-builder, the Flow Store's /flow-store/mcp) |
12 tools over 12 of 63+ Flow Store endpoints; list_flows returned empty lists; tokens rotated |
commands (cc-flow and the Flow Store groups) |
July 2026 (the day was not recorded) |
Optional MCP servers in the playbook
The playbook's .mcp.json lists two optional servers, with placeholders: Cisco's Flow Designer MCP server (YOUR_FLOW_STORE_TOKEN) and Supabase (YOUR_SUPABASE_PROJECT_REF, YOUR_SUPABASE_ACCESS_TOKEN), for a Supabase database behind an AI agent. Neither is needed: Claude does Flow Designer work through the commands. To use one, paste your own values over its placeholders (they are secrets, so this is yours to do), and delete an entry you don't use. The bundled Flow Store URL is the US-1 production address; an org homed in another region uses its region's production Flow Store host. In Claude Code, the Flow Designer server's read tools run anywhere, and its other tools run only inside the wxops agent. Under Codex the server reads its token from the WEBEX_ACCESS_TOKEN environment variable (.codex/config.toml), so no token is written into a project file. The table above is re-checked with the weekly Flow Store drift runbook (tools/CLAUDE.md).
Setup — the only commands you type
You need Claude Code or Codex. Then you type three things: an install, a folder, and your Webex token (again whenever it expires). After that you talk to Claude.
1. Install.
pipx install wxcli # isolated, always on PATH
Works on macOS, Linux, and Windows, with Python 3.11 or newer. pipx pulls every dependency automatically.
Don't have pipx (command not found: pipx)?
Install it first, then open a new terminal and run pipx install wxcli:
- macOS (with Homebrew):
brew install pipx && pipx ensurepath - Linux (Debian/Ubuntu):
sudo apt install pipx && pipx ensurepath - Windows: install Python 3.11+ (tick "Add python.exe to PATH" during setup), then
python -m pip install --user pipx && python -m pipx ensurepath
Plain pip install wxcli usually fails on macOS and recent Linux: there may be no pip command at all, pip3 with Homebrew's Python refuses with externally-managed-environment, and the Python built into macOS is 3.9, too old for wxcli. Use pipx.
2. Put the playbook in a folder, and start Claude Code or Codex there.
wxcli init # writes the Claude Code + Codex playbook into ./wxcli-playbook
cd wxcli-playbook && claude # start Claude Code…
cd wxcli-playbook && codex # …or start Codex — reads AGENTS.md + .codex/
The playbook ships inside the installed package, so there is nothing to clone. It holds:
- 2 agents:
wxops, which does every job that changes or audits your org, andmigration-advisorfor CUCM migrations. - 39 skills and the reference docs.
- A
.claude/settings.jsonthat pre-approves the skills and installs the safety hook (What keeps this safe).
wxcli init --claude-only or wxcli init --codex-only writes one of the two; wxcli init --uninstall removes the files init wrote. Personal overrides go in .claude/settings.local.json.
3. Give it your Webex token. Get a personal access token (a 12-hour admin key) from developer.webex.com. Run wxcli configure and paste the token at the prompt. Identical in macOS/Linux Terminal, Windows PowerShell, and cmd:
wxcli configure
# prompts: "Webex API token:" → paste token, press Enter
The token is your secret, so this step stays yours. When it expires, or Claude reports a 401 or 403, paste a new one: in Claude Code type ! wxcli configure in the prompt (the ! runs it in the session); in a terminal run wxcli configure. A partner token that reaches several customer orgs: wxcli configure asks which org to target.
Prefer a per-session environment variable to a saved token? Set WEBEX_ACCESS_TOKEN instead — export WEBEX_ACCESS_TOKEN="YOUR_TOKEN" (macOS / Linux), $env:WEBEX_ACCESS_TOKEN="YOUR_TOKEN" (PowerShell), set WEBEX_ACCESS_TOKEN=YOUR_TOKEN (cmd). Claude checks the token with wxcli whoami before it starts.
What it can do
Each area below is a set of skills Claude picks from by itself. The commands shown are what Claude runs, printed so you can follow along; you don't type them.
Webex Calling
Locations, users, numbers and licenses; auto attendants, call queues, hunt groups, paging, call park and pickup, voicemail groups, schedules; trunks, route groups, dial plans and translation patterns; per-person settings such as forwarding, do-not-disturb, executive-assistant and recording; phones, DECT, line keys and 9800-series PhoneOS settings; emergency addresses and callback numbers; live call control.
"Create a San Jose location and turn on calling." "Set up call forwarding for the front desk." "Give the 9861 in reception ringtone 4 on line 2."
Contact Center and AI agents
The deepest part of the playbook. Claude designs first, gets your approval, then builds.
- Voice flows (IVRs) in Flow Designer: business hours, menus, callbacks, skill-based routing, data lookups. Claude writes a design doc, then either builds the flow through the API or gives you a step-by-step build. The reference covers 48 Flow Designer activities, and 4 working example flows ship with the playbook.
- AI agents in AI Agent Studio, both kinds: autonomous agents, where an AI decides when to call each action, and scripted agents, built from intents and entities.
- Webex Connect flows behind those agents: the API call for an agent action, inbound conversations on SMS, WhatsApp, Apple Messages, RCS, email and live chat with hand-off to a person, outbound notifications with a voice fallback, and chat-to-voice escalation that carries the transcript.
- Data lookups from a flow or agent: the Business Rules Engine (Cisco's built-in lookup tables) or a database such as Supabase.
- Contact Center setup: agents, queues, entry points, teams, skills, dial numbers, business hours and campaigns, plus queue and agent statistics.
- Diagrams and solution decks from the design doc, for showing a customer.
Webex Connect and AI Agent Studio have no API for these steps, so for those parts Claude gives you the exact click path in each screen instead of doing it for you.
"Build an AI agent action that looks up an order." "Send an SMS when a ticket closes." "Design an IVR with a business-hours check."
CUCM-to-Webex migration
Ask "Run a CUCM migration" and give Claude the CUCM host and credentials. Claude pulls the configuration from CUCM through its admin API (AXL), maps every object to its Webex Calling equivalent, and stops at each design decision for you to answer, with a recommendation and its reasons. Then it builds, checks and reports.
Along the way you get a customer-ready assessment report (complexity score, environment inventory, analog gateway review, effort estimates), a per-user before/after comparison, and an email-ready notice for your users.
wxcli cucm init myproject # Create project
wxcli cucm discover --host 10.0.0.1 \ # Extract from CUCM via AXL
--username admin --password secret -p myproject
wxcli cucm normalize -p myproject # Normalize to canonical models
wxcli cucm map -p myproject # Map CUCM objects to Webex operations
wxcli cucm analyze -p myproject # Run 15 analyzers, generate decisions
wxcli cucm report --brand "Acme Corp" \ # Generate HTML assessment report
--prepared-by "Jane Admin" -p myproject
wxcli cucm user-diff -p myproject # Per-user before/after comparison
wxcli cucm user-notice --brand "Acme" \ # Email-ready migration notice
--migration-date "2026-06-01" \
--helpdesk "help@acme.com" -p myproject
wxcli cucm plan -p myproject # Build dependency-ordered execution plan
wxcli cucm preflight -p myproject # Run 10 preflight checks
wxcli cucm export -p myproject # Export deployment plan
wxcli cucm execute -p myproject \ # Execute all operations concurrently
--concurrency 15
The build creates things in dependency order, adopts a resource that already exists instead of failing, and skips anything whose prerequisite failed.
How the migration engine is built
- SQLite-backed store with objects, cross-references, decisions, and journal
- 42 normalizers + a cross-reference builder that links related CUCM objects
- 26 mappers that convert CUCM objects to Webex Calling operations
- 15 analyzers that surface decisions requiring human review
- Advisory system with 25 per-decision rules + 30 cross-cutting patterns
- Dependency graph (NetworkX) for ordering and batch planning
- Async execution engine with configurable concurrency
- 3133 migration tests
Org health assessment
Ask "audit my org". The wxops agent collects your org's configuration, runs 18 deterministic checks across 4 categories, and produces a self-contained HTML report.
| Category | Checks |
|---|---|
| Security Posture | Unrestricted international dialing, no outgoing call restrictions, auto attendant external transfer enabled, call queues without recording |
| Routing Hygiene | Empty dial plans, orphan route components (route groups/lists without trunks), trunk errors |
| Feature Utilization | Disabled auto attendants, understaffed call queues, single-member hunt groups, empty voicemail groups, empty paging groups, empty call parks |
| Device Health | Offline devices, users at device limit, unassigned devices, workspaces without devices, stale activation codes |
Reporting and questions about your org
Plain-English questions answered from live data, without changing anything: call history (more than 70 ready-made call-history queries plus a guide for composing new ones), call queue and auto attendant statistics, call quality, Contact Center queue and agent statistics, meeting quality and usage.
"How many calls did Support miss last week?" "Which locations have no users?" "Which queues had the longest waits yesterday?"
Admin, identity, messaging and meetings
License audits and reclaiming licenses from inactive users; directory sync (SCIM), groups and domain verification; admin audit logs and security events; Webex spaces, bots and adaptive cards; scheduling and managing meetings; Video Mesh.
"Reclaim licenses from users inactive for 90 days." "Post this incident card to the NOC space."
Partner / multi-org
For partners, resellers and managed-service providers managing several customer organizations with one token. Ask Claude to switch the target org ("switch to the Acme org", "which org am I in?"); it runs these. Pasting the partner token stays your step (Setup, step 3), and that step asks which org to target first.
wxcli switch-org # Change the active target org
wxcli clear-org # Revert to single-org behavior
wxcli whoami # Shows "Target:" line when an org is set
The commands add the selected organization ID to every endpoint that accepts it — no extra flag required.
Cleanup
Ask Claude to tear down what you name ("delete the lab locations San Jose and Austin; dry run first"). It batch-deletes Webex Calling resources in dependency-safe order (13 layers, reverse of creation order):
wxcli cleanup run --scope "San Jose,Austin" # Specific locations only
wxcli cleanup run --all # Entire org
wxcli cleanup run --all --dry-run # Preview without deleting
Flags:
--include-users— also delete users (off by default)--include-locations— also delete locations (off by default)--exclude-user-domains "wbx.ai,corp.com"— protect users matching these email domains--max-concurrent N— parallel deletions per layer (default 5)--force— skip confirmation prompt
Deletion order: dial plans → route lists → route groups → translation patterns → trunks → call features → schedules/operating modes → virtual lines → devices → workspaces → users → numbers → locations.
Codex
wxcli init writes the Codex files too (AGENTS.md, .codex/). Start Codex in the folder and trust the folder when Codex asks: the shipped .codex/config.toml (approval policy, sandbox mode, MCP servers) takes effect only in a folder Codex trusts. Codex has no per-command allowlist, so expect an approval prompt when a command needs to run outside the workspace sandbox.
Three limits apply under Codex that Claude Code does not have:
- Flow Designer MCP writes are not checked. The Codex safety hook watches shell commands only, so a write through the Flow Designer MCP server is not held to the
wxopsagent the way it is in Claude Code.wxclicommands are checked. - Several unattended runs started at once may run without the safety lock. In a 2026-10-20 test on Codex 0.163.0, 4 of 7
codex execruns started together loaded none of the folder's hooks, and two of them ran a write the lock should have stopped. Runs started one at a time all loaded the hooks. Interactive Codex was not measured. Start runs one at a time. - The larger
AGENTS.mdlimit needs a trusted folder. The playbook setsproject_doc_max_bytes = 65536so Codex reads all ofAGENTS.md. Codex ignores that setting in a folder it does not trust, and by default cuts the file at 32,768 bytes.
Updating
Claude can run this for you. At the start of each Claude Code session the playbook checks PyPI (cached for a day) and tells Claude when a newer wxcli exists, so Claude can offer the upgrade:
wxcli update # check PyPI and upgrade in place
wxcli update --check # report the latest version without upgrading
wxcli update detects how it was installed and upgrades accordingly — pipx upgrade wxcli for pipx installs, pip install --upgrade wxcli for pip installs — then deep-links the release notes for the new version. Then run wxcli init in the playbook folder again: it refreshes only the files it wrote, for the assistants already installed there, and never touches files you added.
Behind a firewall that blocks PyPI? Point WXCLI_UPDATE_INDEX_URL at an internal mirror, or install fresh with pipx install wxcli.
For developers: the command layer on its own
Claude reads --help, not this section. It is here so you can follow what Claude does, or use the CLI in your own scripts and CI without any AI. Outside Claude, the reference docs in docs/reference/ are a Webex API knowledge base any developer can read, and the 10 OpenAPI specs (specs/webex-*.json) import into Postman or any API client.
wxcli --help # all 200 command groups
wxcli locations list # location IDs
wxcli users list --location-id LOC_ID # person IDs
wxcli numbers list --location-id LOC_ID # number inventory
wxcli hunt-group create --help # every flag a command takes
More example commands, flags, and the common command groups
# List calling-enabled locations
wxcli location-settings list-1
# Create a location (address requires --json-body)
wxcli locations create --name "San Jose Office" \
--time-zone "America/Los_Angeles" \
--preferred-language en_us \
--announcement-language en_us \
--json-body '{"address": {"address1": "123 Main St", "city": "San Jose", "state": "CA", "postalCode": "95113", "country": "US"}}'
# Enable Webex Calling on a location (fetch details first with wxcli locations show LOCATION_ID)
wxcli location-settings create --id LOCATION_ID --name "..." --time-zone "..." --preferred-language en_US --announcement-language en_us
# Create an auto attendant (LOCATION_ID is positional)
wxcli auto-attendant create LOCATION_ID \
--name "Main Menu" --extension 1000 --business-schedule "Business Hours"
# Create a call queue
wxcli call-queue create LOCATION_ID \
--name "Support Queue" --extension 2000
# Create a hunt group
wxcli hunt-group create LOCATION_ID \
--name "Sales Team" --extension 3000 --enabled
# View user call settings
wxcli user-settings show-call-forwarding PERSON_ID --output json
Flags
--json-body— For complex nested settings (call forwarding rules, voicemail config, agent lists), pass the full JSON body:wxcli call-queue update LOC_ID QUEUE_ID --json-body '{"agents": [...]}'--all— On everylistcommand: fetch every page instead of just the first. The default is a single fetch, so a count drawn from it on a large org is wrong. When pages are left behind the CLI says so on stderr (Note: N records returned and the server has more pages...). Walking is capped at 1000 pages (WXCLI_MAX_PAGES); hitting the cap prints an error containing INCOMPLETE, which means records are missing.--fields— A JMESPath expression (a JSON query language) applied to the response before rendering, on every command:wxcli people list --fields '[].{name:displayName,id:id}' -o json--debug— Add to any command for verbose HTTP request/response output
The full behavior reference, including the eleven known issues, is docs/reference/wxcli-behavior.md.
Common command groups (run wxcli --help to see all 200 groups, which also cover admin, device, messaging, meetings, and contact center APIs)
| Group | Description |
|---|---|
whoami |
Show current authenticated user and org |
locations |
Create, list, enable calling on locations |
users |
Create, list, manage users |
licenses |
List and inspect licenses |
numbers |
Manage phone numbers |
location-schedules |
Business hours and holiday schedules |
auto-attendant |
IVR menus with key-press routing |
call-queue |
Hold callers until an agent is free |
hunt-group |
Ring a group of agents directly |
call-park |
Park calls on extensions |
call-pickup |
Answer each other's ringing phones |
paging-group |
One-way broadcast announcements |
location-voicemail |
Shared voicemail boxes |
operating-modes |
Business hours operating modes |
call-routing |
Dial plans, trunks, route groups |
call-controls |
Real-time call control (dial, hold, transfer) |
user-settings |
Person-level call settings (forwarding, DND, voicemail, etc.) |
location-settings |
Location-level call settings |
dect-devices |
DECT networks, base stations, handsets |
device-settings |
Device configurations |
workspaces |
Workspace management |
emergency-services |
E911 and emergency services |
announcements |
Announcement repository |
announcement-playlists |
Playlist management |
virtual-extensions |
Virtual extension management |
single-number-reach |
Single number reach settings |
call-recording |
Call recording settings |
pstn |
PSTN connection management |
cx-essentials |
Customer Assist (screen pop, wrap-up, supervisors) |
cleanup |
Batch-delete resources in dependency-safe order |
Known limitations
- Call control commands require a user-level OAuth token. Admin and service app tokens return
400 "Target user not authorized". Use a personal access token from the user who will control calls. - Complex nested settings need
--json-body. Call forwarding rules, agent lists, voicemail config, and similar deeply nested structures can't be expressed as CLI flags — pass the full JSON body instead. - Some person call settings have no admin path and need a user-level token. The list is in
docs/reference/wxcli-behavior.md§ 3. Known Issues, item 4. - CDR/analytics endpoints require the
analytics:read_allscope, which standard admin tokens may not include.
Requirements
- Python 3.11+
- A Webex admin account. A personal access token is enough to start; for long-running work use a service app. Token types and OAuth flows:
docs/reference/authentication.md.
OAuth scopes, by API domain
Not all scopes are needed — request only those for the API domains you use.
Minimum scopes for Webex Calling admin operations:
| Scope | Purpose |
|---|---|
spark-admin:telephony_config_read |
Read telephony config (locations, numbers, call routing, features) |
spark-admin:telephony_config_write |
Create/edit/delete telephony config |
spark-admin:people_read |
Read people across the organization |
spark-admin:people_write |
Create/update/delete people |
spark-admin:locations_read |
List and view locations |
spark-admin:locations_write |
Create/update/delete locations |
spark-admin:licenses_read |
List and inspect licenses |
spark-admin:devices_read |
View devices |
spark-admin:devices_write |
Add/update/delete devices |
spark-admin:workspaces_read |
View workspaces and workspace settings |
spark-admin:workspaces_write |
Create/update/delete workspaces |
Additional scopes by API domain:
| Domain | Scopes |
|---|---|
| PSTN / routing | spark-admin:telephony_pstn_read, spark-admin:telephony_pstn_write |
| Workspace locations | spark-admin:workspace_locations_read, spark-admin:workspace_locations_write |
| Org-wide call control | spark-admin:calls_read, spark-admin:calls_write |
| CDR / call history | spark-admin:calling_cdr_read (+ admin role "Webex Calling Detailed Call History API access") |
| Reports / analytics | analytics:read_all (requires Pro Pack) |
| Org & roles | spark-admin:organizations_read |
| Audit events | spark-admin:audit_events_read |
| SCIM identity sync | identity:people_rw, identity:people_read |
| Hybrid services | spark-admin:hybrid_clusters_read, spark-admin:hybrid_connectors_read |
| Recordings | spark-admin:recordings_read, spark-admin:recordings_write |
| Data sources | spark-admin:datasource_read, spark-admin:datasource_write |
| Resource groups | spark-admin:resource_groups_read, spark-admin:resource_group_memberships_write |
| Partner reports | spark-admin:reports_read, spark-admin:reports_write |
| Messaging (rooms) | spark:rooms_read, spark:rooms_write |
| Messaging (memberships) | spark:memberships_read, spark:memberships_write |
| RoomOS xAPI | spark:xapi_commands, spark:xapi_statuses |
| Device activation | identity:placeonetimepassword_create or Identity:one_time_password |
| Contact center | cjp:config_read, cjp:config_write (also requires wxcli set-cc-region) |
User-level scopes (for call control and self-service settings — requires a user token, not admin):
| Scope | Purpose |
|---|---|
spark:calls_read |
List active calls and call history |
spark:calls_write |
Call control (answer, hold, transfer, park) |
spark:people_read |
Read own user info |
spark:people_write |
Modify own call settings |
spark:xsi |
XSI scope for Webex Calling resources |
For maintainers
This section is for people changing this repository. In the repo, too, Claude runs the commands; the rules it follows are in .claude/rules/repo-development.md and tools/CLAUDE.md.
Project layout, design decisions, building and checking
wxops/
├── src/wxcli/ # CLI source (Typer + httpx REST client)
│ ├── main.py # Entry point — registers 200 command groups
│ ├── auth.py # Token storage and API client init
│ ├── output.py # Table/JSON output formatting
│ ├── commands/ # generated command modules (one per API tag) + _registry.py manifest
│ ├── org_health/ # Org health assessment engine (18 checks → HTML report)
│ ├── _playbook/ # GENERATED playbook bundle that `wxcli init` writes (Claude Code + Codex)
│ └── migration/ # CUCM-to-Webex migration engine
│ ├── cucm/ # AXL extractors and discovery
│ ├── transform/ # Normalizers, mappers, analyzers
│ ├── execute/ # Async execution engine + handlers
│ ├── advisory/ # Decision recommendations
│ ├── report/ # HTML/PDF assessment report generator
│ └── models.py # 38 canonical data models
├── tools/ # Code generator pipeline and the drift gate
│ ├── generate_commands.py # Orchestrator: OpenAPI → Click commands
│ ├── openapi_parser.py # Parses OpenAPI 3.0 specs into Endpoint objects
│ ├── command_renderer.py # Renders Endpoints into Python command files
│ ├── drift_check.py # The drift gate (docs, skills and CLI agree)
│ └── field_overrides.yaml # Table columns, display config, bug fixes
├── wxcli-dist/ # assemble.py + the curated settings, MCP and hook files it ships
├── tests/ # 5,500+ tests (pytest)
├── specs/ # 10 OpenAPI 3.0 specs (calling, admin, device, messaging, meetings, CC, CC Flow Store, UCM, BroadWorks, wholesale)
├── docs/reference/ # 118 reference docs (API + platform knowledge + gotchas)
├── docs/playbooks/ # 27 step-by-step platform guides
├── .claude/agents/ # wxops (the builder) + migration-advisor
└── .claude/skills/ # 39 skills
Key design decisions:
- Commands are generated, never hand-edited. Fix bugs in
field_overrides.yamland regenerate withtools/generate_commands.py. - The CLI uses raw HTTP via its own
WebexSessionclient (src/wxcli/auth.py) built onhttpx, not any third-party SDK. Every operation in the 10 bundled specs has a command, except 194 deliberately skipped; the drift gate enforces it. - Reference docs serve both humans and AI. Developers can read them directly; the playbook loads them as context for guided configuration.
Building and checking:
- Drift gate.
venv/bin/python -m tools.drift_check --enforcemust endresult: PASS: every command a doc cites exists, every published count matches, every group is routed. Run it in the venv; on a Python withoutpyyamlit crashes. - Tests. Run the files a change touches,
venv/bin/python -m pytest <files> -q. Theliveandmutationtiers call a real org and are opt-in; CI runs everything else on Python 3.11 and 3.12. - The playbook bundle.
src/wxcli/_playbook/is generated: never hand-edit it. After changing a shipped source (CLAUDE.md,.claude/agents|skills|rules,docs/reference|playbooks|templates|examples), runpython wxcli-dist/assemble.pyand commit the bundle with the change. It reads tracked files only (git ls-files), substitutes the curatedwxcli-dist/settings.bundled.jsonand the sanitizedwxcli-dist/mcp.bundled.json, generates the Codex profile, and fails on a repo-only path left in a shipped file. - Releases. A
v*tag runs.github/workflows/release.yml, which re-runs the assembler, refuses to publish a stale bundle, and publishes to PyPI.
Disclaimer & Safe Use
wxcli is an unofficial, community-maintained tool. It is not affiliated with, endorsed by, or supported by Cisco. "Webex", "Webex Calling", and "CUCM" are Cisco trademarks, used here only to describe interoperability.
This tool changes and deletes real telephony configuration. The AI playbook reasons and orchestrates using a large language model, which is non-deterministic: the same prompt can produce different actions, and the agent can select the wrong resource. The layered design (docs → skills → tested CLI, with read-back verification) is built to reduce this, but cannot eliminate it.
Before running anything against a production org:
- Preview first. Use
--dry-run(cleanup, migration) and review the plan. - Verify emergency services. E911 / emergency-callback misconfiguration is a life-safety risk. Independently confirm every emergency address and emergency callback number (ECBN) after any change — do not rely on the tool's read-back alone.
cleanup run --allis irreversible and deletes an entire org's calling config. There is no undo.- Test in a lab or sandbox org first, especially for CUCM migrations.
- You are the operator of record. You are responsible for reviewing and authorizing every action, and for compliance with your own change-control, regulatory (e.g. the US emergency-calling laws Kari's Law and RAY BAUM's Act), and data-handling obligations.
By using this tool you accept these risks and the terms of the Apache 2.0 License.
Credentials, secrets, and API usage
- Tokens are stored locally in plaintext in your wxcli config file. Treat that file like a password — it grants full admin access to your Webex org. Personal access tokens expire after 12 hours; OAuth/service-app tokens live longer, so guard them accordingly.
- CUCM AXL credentials passed inline to
wxcli cucm discover --username/--passwordland in your shell history. Prefer a prompt-based flow or a throwaway shell, and clear the history afterward. - The AI playbook can generate many API calls in a loop. Long agent runs and large migrations may hit Webex API rate limits; the tool retries, but you own the API-usage footprint against your org.
License
Apache 2.0 — see LICENSE.
Metadata
Release files for wxcli 1.11.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| wxcli-1.11.2.tar.gz | 8.0 MB | With provenance | Details for wxcli-1.11.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| wxcli-1.11.2-py3-none-any.whl | Python 3 | none | any | Details for wxcli-1.11.2-py3-none-any.whl |
Total release size: 11.8 MB
Release files / wxcli-1.11.2.tar.gz
| Download URL | wxcli-1.11.2.tar.gz |
|---|---|
| Size | 8.0 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ed913dd6f1d0c3af22844440f045109c2d34c1383c53ecf77d534e2e78e8c9e1
|
|
BLAKE2b-256 checksum How to use checksums |
af42fd94872ab3362ff9d17d0d6590f08fb00d5e2aa5c36506f4731b30a87378
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 2, 2026.
Transparency logRelease files / wxcli-1.11.2-py3-none-any.whl
| Download URL | wxcli-1.11.2-py3-none-any.whl |
|---|---|
| Size | 3.8 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
408a9bc4bb1e3871ec77b7007f58dbf2e005e615d982ad4e60ce21fe59175e37
|
|
BLAKE2b-256 checksum How to use checksums |
ec099ff5333319ecd95fd4c03fc2a8fa10a1c7b1d80b106de5a2baa97f30bdef
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 2, 2026.
Transparency logSecurity for wxcli 1.11.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for wxcli-1.11.2.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 2, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.