wyre-ai/msp-claude-plugins/clients
Claude Code and agent skill by wyre-ai/msp-claude-plugins
- community
Checking that the SKILL.md file is still in the repository.
Axcient x360Recover clients: the health_status model, client_code, the three-way protected-system counter breakdown (appliance_based, d2c, cloud_archive), and minting direct-to-cloud agent enrollment tokens.
Install
npx vskill@latest install wyre-ai/msp-claude-plugins/clientsSKILL.md
Axcient Clients
Overview
A "client" in x360Recover is the tenant/customer boundary — roughly equivalent to a PSA company. Every device, job, vault, and appliance belongs to exactly one client. Client health is a rollup Axcient computes from the devices underneath it, not a value you set.
Tools
| Tool | Description | Arguments | |
|---|---|---|---|
axcient_list_clients | Every client visible to this credential | include_appliances? | |
axcient_get_client | One client's detail | client_id, include_appliances? | |
axcient_get_d2c_agent_token | Mint a D2C agent enrollment token | client_id, vault_id |
List Clients
Example response (one client):
Protected-System Counters
devices_counters breaks the client's protected systems into three independent buckets, each split by SERVER/WORKSTATION:
| Bucket | Meaning | |
|---|---|---|
appliance_based | Backed up to a local Axcient appliance | |
d2c | Direct-to-cloud — no local appliance, agent replicates straight to Axcient's cloud | |
cloud_archive | Long-term cloud archive copies |
A device can appear in more than one bucket (e.g. appliance-based and cloud-archived via vault replication). Sum the buckets to get a client's total protected-system count; do not assume they're mutually exclusive.
Client Health Status
health_status is a client-level rollup (values observed: NORMAL, and presumably WARNED/CRITICAL mirroring the device-level status model — see the devices skill). It reflects the worst device under that client, not an independently-computed value. To find which device is dragging a client's health down, call axcient_list_devices_by_client and inspect each device's own current_health_status.
Minting a D2C Agent Token
Parameters:
client_id-- The client to enroll the new agent under (required)vault_id-- The vault the agent will replicate to (required)
Returns short-lived credential material for installing a new direct-to-cloud backup agent. This is a provisioning action, not a read — every call issues fresh token material. It does not affect any agent already enrolled, and it cannot be used to recover or inspect an existing agent's credentials.
Common Workflows
Client Health Triage
axcient_list_clients— scanhealth_statusacross all clients- For any client not
NORMAL,axcient_list_devices_by_clienton that
client_id to find the specific device(s) failing
axcient_get_deviceon the failing device(s) for
current_health_status.reason and timestamps
- Cross-reference with
axcient_list_jobs_by_device/
axcient_get_job_history — a device can be "healthy" by its own status while its most recent job run failed
Enrolling a New D2C Agent
- Confirm the target client with
axcient_get_client - Confirm the target vault exists and is reachable with
axcient_get_vault
(see the vaults skill — private vaults may have connectivity constraints a cloud vault doesn't)
axcient_get_d2c_agent_tokenwith thatclient_id/vault_id- Hand the returned token to whoever is installing the agent — it is not
something this tool surface can retrieve again after the fact
Error Handling
Client Not Found
Cause: Invalid client_id, or the client belongs to a different organization than the API key's Solution: Verify against axcient_list_clients. A non-numeric client_id surfaces as a 401, not a 400 — see the api-patterns skill.
D2C Token Request Fails with 403
Cause: The API key's account lacks permission to provision new agents Solution: This is an admin-gated operation on Axcient's side; the key needs elevated permissions, not a retry.
Best Practices
- Treat
health_statusas a starting point for triage, not the final
answer — it tells you which client needs attention, not why.
client_codeis the short human identifier used elsewhere in Axcient's
UI and reports; surface it alongside name when presenting client lists to a technician who already knows the codes.
- Don't call
axcient_get_d2c_agent_tokenspeculatively — each
call provisions real enrollment material. Confirm the client and vault first.
Related Skills
- api-patterns - Authentication, tool catalog, error codes
- devices - Device-level health and protection detail
- vaults - Vault selection for D2C enrollment
- appliances - Appliance inventory per client
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingmsp-claude-plugins/axcient/axcient/skills/clients/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/wyre-ai/msp-claude-plugins/clients)