Cisco Meraki Agent
Cisco Meraki in Switchboard. Review AI skills, playbooks, access limits and setup requirements before connecting your MSP systems.
How the Cisco Meraki integration works
Meraki is the layer everything else at a client sits on, and it is where an outage gets diagnosed or misdiagnosed. Connect it for read-only visibility and a session reads the whole picture — networks, devices and their live status, wireless health, switch ports, appliance uplinks and VPN, licensing and firmware — read-only today. Any change the integration could make in Meraki is held back — refused by our server before anything reaches Meraki — until a person switches it on, and nothing is switched on today. Beyond that, the client refuses any request outside five device-action paths (ping from a device, cable test, port cycle, LED blink, reboot), so no setting can change from here. Switchboard connects through an MSPStuff-hosted MCP server, so there's nothing to install and no API keys to hand your techs.
Hosted and external AI connections provide read-only access. Guidance, shared playbooks and automations we release for everyone are included with Dedicated. Bespoke automation builds are scoped separately. Any change a platform could make is held back — refused by our server before anything reaches the platform — until a person switches it on, and nothing is switched on today. Vendor consent does not switch any change on.
| Device / site | Status |
|---|---|
| MX-01 · Acme | Offline |
| MS-02 · Harbor | Alerting |
| MR-03 · Northstar | Alerting |
Read-only today. Any change the integration could make in Meraki is held back — refused by our server before anything reaches Meraki — until a person switches it on, and nothing is switched on today. Held back that way are five device actions — ping from a device, cable test, switch-port cycle, LED blink, and reboot. Nothing else could be written even then, because the client rejects any request to a path outside that allowlist before it leaves the building: no SSID, VLAN, firewall rule, port setting, license, or firmware schedule is changeable from here, and there is no create or delete anywhere in the surface. Even diagnostics should target the intended device and run at an appropriate time. Cycling a port drops whatever hangs off it for the moment it takes, and a reboot puts the device off the network for 30–60 seconds. The underlying tool does not ask for a typed confirmation. Hosted and external AI connections remain read-only. The API key carries whatever dashboard rights the admin who generated it holds, and every org-scoped call is fenced to the Meraki organizations bound at connect time.
What it can do
- Organization & inventoryThe org-wide view: what every device is doing right now, how uplinks are performing, what licensing and firmware look like, and what Meraki itself has flagged.8skills
Read-only. It cannot schedule or cancel a firmware upgrade, claim, move, or renew a license, or acknowledge and close an alert. On a long list the read stops at our page cap, and the reply says so rather than coming back quietly short. Everything here runs inside one bound Meraki organization at a time — where a connection binds several, the ask has to name which.
- The bound organization's own record — its name, the licensing model it runs under, and how it's managed.
- Where every piece of hardware stands at this moment — online, alerting, offline or dormant — each row carrying its network and serial.
- The same fleet seen as uptime instead of a status colour: availability state, device by device.
- Packet loss and latency on every MX and Z uplink in the org, sampled over the last five minutes only — a live reading, not a trend line.
- Licensing in summary — status, expiry, counts — and the one that answers for co-termination and per-device orgs alike.
- Licensing broken out device by device; a co-termination org has no such list and returns a 404 instead, so the summary is the answer for those.
- The firmware record for the org: what's scheduled, what's running, and what already landed.
- What Meraki is raising on its own — devices down, uplinks struggling, config-drift signals — narrowable by severity and by category.
- Networks & clientsThe day-to-day layer: which networks exist, what hardware sits in each, and what has been connected to them lately.6skills
Reading only — no network is created, renamed, tagged, or deleted, and no client is blocked, unblocked, or given a group policy. Client history reaches back 31 days at the outside; that ceiling is Meraki's, not a setting here.
- Every network under the bound org, with its product types, tags, and timezone — and filterable by tag when a client uses them.
- A single network's record, pulled straight by its N_ identifier.
- The hardware inventory — model, serial, home network, firmware, and site address — narrowable to one model family such as MR, MS, or MX.
- One device on its own, looked up by the serial on its label.
- What has actually been on a network in a given window — usage, IP, VLAN, and how each one connected. A day unless you widen it, and 31 days is as far back as it goes.
- A single connected device on a network, found either by its client id or by its MAC.
- WirelessSSID configuration and the health of what's associating to it — the aggregate number, and the individual failures underneath it.3skills
SSIDs are readable and never writable: none is created, renamed, enabled, disabled, or re-keyed from here. Radio settings, RF profiles, and per-client wireless history aren't part of this surface. SSID responses can include pre-shared keys, so what comes back is treated as sensitive rather than something to paste into a summary.
- The SSIDs configured on a wireless network — read-only, and worth handling carefully, because the response can carry admin pre-shared keys.
- Association success against failure for a whole network over the window you choose — the health number you check before going hunting.
- The failures behind that number, one event at a time, each pinned to the stage it broke at: association, authentication, DHCP, or DNS.
- SwitchingA switch's ports both ways round: how they're configured, and what they're doing right now.2skills
Port configuration is read-only — no VLAN, PoE setting, or port name is written from here. The one thing a session can do to a port is cut its power and restore it, and that lives with the NOC actions.
- How a switch's ports are set up — name, VLAN, enabled state, PoE — as configuration to read, never to rewrite.
- The live half of the same switch: link and negotiated speed, error and warning counts, traffic, and the CDP/LLDP neighbour on the far end.
- Security applianceThe MX and Z side: WAN uplinks across the org, site-to-site VPN reachability, and how hard a single appliance is working.7skills
Status and load only. Firewall rules, VPN configuration, traffic shaping, and content filtering are neither read nor changed here — if the answer is 'a rule is wrong', fixing it is still a dashboard job.
- Every appliance's WAN interfaces across the org — IP, gateway, and whether the connection is genuinely up.
- Site-to-site VPN seen org-wide, appliance by appliance, with each peer and whether it can currently be reached.
- One MX's load score — the number that decides whether the box itself is the bottleneck.
- Per-port configuration for an MX appliance network (enabled, VLAN, access policy) — read-only.
- Static routes configured on an MX network.
- DHCP subnet + lease-utilization info for an MX appliance.
- RF profiles configured for MX-integrated wireless on a network.
- NOC actionsThe five device actions — each held back and refused by our server until a person switches it on, and none is switched on today — and the fetcher for a job that outran the call that started it.1skills
None of it writes configuration: no setting, policy, or schedule changes. Ping, cable test, and port cycle run as Meraki jobs — the call waits around thirty seconds and, if the job is still going, hands back a job id to collect later instead of blocking. The tool itself does not request typed confirmation; review the targets in the separate Switchboard approval flow: a port cycle drops what's plugged into it, and a reboot takes the device off the network for 30–60 seconds.
Writes: Five device operations, and nothing beyond them: send a ping from a Meraki device, cable-test named switch ports, power those ports off and back on, blink a chassis light, and reboot the device. That list is the complete write surface — the client refuses any other action path outright.
- Collect a ping, cable test, or port cycle by its job id when the original call stopped waiting — a read, not a second run of the action.
- Agent & sessionWhat this connection is: the Meraki organizations it's bound to, and whether the key behind it still works.1skills
Read-only, and it reports the binding rather than altering it — it cannot add an organization to the roster, swap the API key, or repair a connection Meraki has stopped accepting. When a key is revoked in the dashboard the next call fails and the connection is marked invalid; this is where that shows up.
- Which Meraki organizations this connection binds, what the session is allowed to do, and whether the stored key is still valid and when it was last checked.
- Audit9skills
- The org's configuration change log (who changed what, old/new value, when) — the primary audit trail.
- Dashboard admins on the org and their access privileges. Contains admin email addresses — treat as sensitive, do not echo into shared summaries.
- The org's login security policy (password requirements, 2FA enforcement, idle timeout, IP allowlisting).
- Whether SAML SSO is enabled for the org dashboard.
- The org's configured SAML identity providers. May include IdP metadata — treat as sensitive.
- The org's SAML role mappings (which IdP role maps to which dashboard access level).
- Recent Dashboard API request log for the org (path, method, admin/PAT, status, response time).
- Aggregate API request volume/response-code breakdown for the org over a timespan.
- The org's white-label / branding policies (custom logos, support contact overrides per admin group).
- Camera14skills
- Video settings for an MV camera (external RTSP enabled, RTSP URL).
- Video quality and retention settings for an MV camera (resolution, quality, motion-based retention).
- MV Sense (computer vision) settings for a camera: enabled, sense API, audio detection.
- Wireless uplink profiles configured on an MV camera.
- A viewing link (video wall URL) for an MV camera, optionally at a given timestamp. The returned URL grants video access to whoever holds it — treat as sensitive, do not echo into shared summaries.
- MV Sense analytics zones configured on a camera.
- Person/vehicle entrance counts and time-in-zone history for one analytics zone.
- Live MV Sense analytics state for a camera (current object counts).
- Recent MV Sense analytics detections for a camera.
- Summary MV Sense analytics (object counts over time) for a camera.
- Custom analytics (customer-provided vision model) config for a camera, if configured.
- Camera recording schedules configured on a network.
- Camera-role permission sets defined for the org (who can view which cameras).
- Onboarding/setup status for MV cameras across the org (video settings applied, wireless profile pushed).
- Security19skills
- L3 outbound firewall rules for an MX network (protocol/src/dst/policy).
- L7 application-layer firewall rules for an MX network.
- Application categories/known apps available for L7 firewall rules on a network.
- Outbound firewall rules applied when an MX is on its cellular (failover) uplink.
- Inbound firewall rules for an MX network (WAN -> LAN).
- Inbound firewall rules applied on the cellular uplink.
- 1:1 NAT mappings configured on an MX network.
- 1:many NAT mappings configured on an MX network.
- Port-forwarding rules configured on an MX network.
- Network-wide firewall settings (spoofed-IP protection mode, allowed IPs).
- Firewall rules for Meraki-hosted services (web UI, SNMP, ICMP ping) on an MX network.
- Content filtering config for an MX network (allowed/blocked URL patterns, blocked categories).
- Content filtering categories available to block on a network.
- Global traffic-shaping settings for an MX network (default rules, per-client bandwidth limits).
- Custom traffic-shaping performance classes defined on a network.
- Intrusion detection/prevention (IDS/IPS) settings for an MX network (mode, ruleset).
- Advanced Malware Protection (AMP) settings for an MX network (mode, allowed-file-hash list).
- IDS/IPS and AMP security events detected on an MX network over a timespan.
- Air-Marshal rogue AP / rogue SSID / spoofed-network detections for a wireless network.
- Sensor8skills
- Most recent reading of every metric for every MT sensor in the org.
- Historical MT sensor readings over a timespan (org-wide, filterable).
- MT sensor alert profiles configured on a network (thresholds, recipients).
- One MT sensor alert profile by id.
- MT sensor-to-device pairings (which sensor monitors which door/camera/switch) for a network.
- The paired-device relationship for one MT sensor.
- Past commands issued to an MT sensor (e.g. button-press-simulated actions) — history only, does not issue new ones.
- One past MT sensor command by id, with its result status.
- Systems Manager12skills
- Enrolled Systems Manager (MDM) devices on a network (owner, OS, tags, enrollment status).
- CPU/memory/network performance history for one SM-managed device.
- Cellular data usage history for one SM-managed device.
- A device's installed certificates. Includes cert subjects/issuers — treat as sensitive, do not echo into shared summaries.
- A device's network adapters (interface, MAC, IP).
- A device's applied MDM restriction policies.
- A device's OS-reported security center status (AV, firewall, disk encryption).
- A desktop device's SM agent event log.
- A device's installed applications (name, version, publisher) as reported to SM.
- Configuration profiles (payloads) defined for Systems Manager on a network.
- Systems Manager end users on a network (BYOD identities tied to devices).
- Profiles assigned to one Systems Manager user, across their devices.
How it has been taught to work it
Playbooks are the vetted techniques a session loads for this platform — what to check, in what order, and what a number means before it is reported.
- Cisco Meraki domain model (per-client orgs, and why every call names one)Always when Meraki is attached. Its entity model, the multi-org binding that gates every call, the device families, and the read/device-ops/DARK-write boundary.Vetted Sep 2, 2026Always on
- Meraki appliance config & security reads — firewall, content filtering, traffic shaping, IDS/IPS, rogue APAuditing or reviewing an MX network's firewall rules (L3/L7/cellular/inbound/NAT/port forwarding), content filtering, traffic shaping, intrusion/malware protection, security events, rogue-AP (Air Marshal) detections, or basic appliance config (ports, static routes, DHCP, RF profiles).Vetted Sep 2, 2026
- Meraki camera (MV) reads — video/quality settings, MV Sense analytics, schedules, permissionsMV camera config (video settings, quality/retention, sense settings, wireless uplink profile), MV Sense analytics (zones, live/recent/overview counts, custom analytics), getting a video link, or org-level camera admin (recording schedules, view permissions, onboarding status).Vetted Sep 2, 2026
- Meraki device-ops — the safe diagnostics and the outage rulesRun a diagnostic on a Meraki device, ping from a device, cable test, blink/locate a device, reboot or power-cycle a port — and when NOT to.Vetted Sep 2, 2026
- Meraki network health — is a client's network up, and what's wrongIs client X's network healthy, what's down, device/uplink/wireless problems, alerts firing, network status check for one client or across clients.Vetted Aug 31, 2026
- Meraki org audit trail reads — config changes, admins, login security, SSO, API log, brandingWho changed what and when in a client's org, the dashboard admin roster and their access, the org's login/2FA/SSO posture, or recent Dashboard API request activity.Vetted Sep 2, 2026
- Meraki sensor (MT) reads — environmental readings, alert profiles, device pairings, command historyTemperature/humidity/water/door/CO2 (or other MT metric) readings, sensor alert thresholds, which device an MT sensor is paired to/monitors, or MT sensor command history.Vetted Sep 2, 2026
- Meraki Systems Manager (MDM) reads — enrolled devices, posture, profiles, usersMDM/endpoint posture questions answered via Meraki Systems Manager — enrolled device inventory, installed certs/apps, security-center (AV/firewall/disk encryption) status, network adapters, restriction policies, desktop logs, configuration profiles, or SM end users.Vetted Sep 2, 2026
- Querying Meraki — the merakiOrg rule, paging, and the live trapsAlways when Meraki is attached. The read + device-ops + DARK-write surface, resolving client→org→network→device, paging, scopes, and the co-term/PSK/VPN gotchas.Vetted Sep 2, 2026Always on