Slide MCP Server
This is a read-only MCP server for Slide backup/BDR visibility, exposing non-mutating GET endpoints with live secrets stripped from responses.
List/get accounts, clients, users, and user avatars.
Inspect agents, agent file paths/versions, backed-up services, and passphrase metadata without passphrase values.
List and retrieve alerts, audit logs, audit actions, and audit resource types.
View backup attempts and snapshots, including snapshot service-verification results.
Browse billing credit memos, invoices, and subscriptions/licenses.
Inspect devices, device network configs, and VLANs.
View disaster-recovery networks, port forwards, IPsec connections, and WireGuard peers without PSKs/private keys.
Inspect file restores, file restore pushes, image exports, and virtual machines without Samba/VNC passwords.
No create/update/delete, backup-starting, restore-push, reboot, or other mutating operations are available.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Slide MCP Server Show me the latest backup status for all agents"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Slide MCP Server
MCP server for Slide's backup/BDR (business continuity/disaster recovery) API - account, agent, device, network, backup, snapshot, and restore visibility, for AI assistants and the WYRE Conduit gateway.
Authentication
Slide authenticates with a static bearer API token, issued per-account in the Slide Console (Settings > API Keys) - not OAuth. This connector never mints or refreshes anything: it only ever holds a live token, sent as Authorization: Bearer <token> to api.slide.tech. In gateway mode the token arrives per-request via the X-Slide-Api-Token header and a request missing that header is rejected. In local/stdio mode, and in HTTP AUTH_MODE=env, it's read from SLIDE_API_TOKEN.
Related MCP server: CyberQP MCP Server
Configuration
Copy .env.example and set the variables below. Leave CONDUIT_S2S_SECRET empty in that file.
Env var | Description |
| Static bearer API token, issued in the Slide Console. Required for stdio and for HTTP |
|
|
|
|
| Required for HTTP. HMAC key for |
| Set to exactly |
| Bind address when |
| HTTP port. Defaults to |
|
|
/health and /healthz stay unauthenticated and do not read credentials. The stdio transport does not use CONDUIT_S2S_SECRET.
HTTP authentication
With MCP_TRANSPORT=http and CONDUIT_S2S_SECRET set, every /mcp request must include X-Gateway-S2S. The check is verifyS2sHeader in src/s2s-verify.ts: the header value is t=<unix seconds>,v1=<hex>, where the hex is HMAC-SHA256 of the literal string t=<unix seconds> keyed with CONDUIT_S2S_SECRET (64 lowercase hex characters). The timestamp must be within 300 seconds of the server clock. A missing or invalid header is HTTP 401, before the Slide token is read.
TS=$(date +%s)
SIG=$(printf 't=%s' "$TS" | openssl dgst -sha256 -hmac "$CONDUIT_S2S_SECRET" -hex | awk '{print $NF}')
curl -sS http://127.0.0.1:8080/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-H "X-Gateway-S2S: t=${TS},v1=${SIG}" \
-H "X-Slide-Api-Token: $SLIDE_API_TOKEN" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'In AUTH_MODE=gateway, /mcp also requires X-Slide-Api-Token. That header is the only credential source for the request. A missing header is HTTP 401 and does not fall back to SLIDE_API_TOKEN.
AUTH_MODE=env still requires a valid X-Gateway-S2S header, then uses SLIDE_API_TOKEN when the request does not carry X-Slide-Api-Token.
Request limits
HTTP request bodies are capped at 256 KiB (262144 bytes). After the
X-Gateway-S2Scheck and (inAUTH_MODE=gateway) theX-Slide-Api-Tokenpresence check pass, aContent-Lengthabove the cap returns 413 with a JSON-RPC error; bodies withoutContent-Lengthare capped by the MCP SDK transport. Unauthenticated requests still get 401 first.tools/callarguments are capped at 10,000 elements (every array item and object key at any depth). Larger inputs return anisErrortool result and are never dispatched.
These limits address CVE-2026-111768 / GHSA-46jr-4wx8-v453 (memory exhaustion during validation) and GHSA-f897-62hf-6gxq (no request body / batch cap).
Tools
Accounts
slide_list_accounts- list accounts, filterable by creation date.slide_get_account- get a single account by ID.
Agents
slide_list_agents- list agents (protected systems), filterable by device, client, type, and pairing date.slide_get_agent- get a single agent by ID (backup schedule, retention, volumes, alert configs).slide_search_agent_files- search the indexed file paths on an agent's protected system.slide_get_agent_file_versions- get the snapshot versions available for a file path on an agent.slide_get_agent_services- get the backed-up services detected on an agent.
Alerts
slide_list_alerts- list alerts, filterable by device, agent, resolved status, and creation date.slide_get_alert- get a single alert by ID.
Audits
slide_list_audit_logs- list audit log entries, filterable by action, resource type, client, and time range.slide_list_audit_actions- list the full set of audit action names.slide_list_audit_resource_types- list the full set of audit resource type names.slide_get_audit_log- get a single audit log entry by ID.
Backups
slide_list_backups- list backup attempts, filterable by agent, snapshot, device, and time range.slide_get_backup- get a single backup attempt by ID.
Billing
slide_list_billing_credit_memos- list billing credit memos.slide_list_billing_invoices- list billing invoices.slide_list_billing_subscriptions- list subscriptions and device licenses.
Clients
slide_list_clients- list clients (the MSP's end customers), filterable by creation date.slide_get_client- get a single client by ID.
Devices
slide_list_devices- list devices (physical/virtual Slide Boxes), filterable by client and creation date.slide_get_device- get a single device by ID.slide_get_device_network- get a device's network configuration.slide_list_device_vlans- list a device's configured VLANs.slide_get_device_vlan- get a single VLAN on a device by ID.
Networks
slide_list_networks- list disaster-recovery networks, filterable by client and creation date.slide_get_network- get a single network by ID (port forwards, IPsec connections, WireGuard peers).
Restores (File)
slide_list_file_restores- list file restores, filterable by creation date.slide_get_file_restore- get a single file restore by ID.slide_browse_file_restore- browse the files/folders exposed by a file restore.slide_list_file_restore_pushes- list push operations for a file restore, filterable by time range.slide_get_file_restore_push- get the status of a single file restore push.
Restores (Image)
slide_list_image_exports- list image exports, filterable by creation date.slide_get_image_export- get a single image export by ID.slide_browse_image_export- browse the files/folders exposed by an image export.
Restores (Virtual Machine)
slide_list_virtual_machines- list virtual machines created from a snapshot, filterable by creation date.slide_get_virtual_machine- get a single virtual machine by ID.
Snapshots
slide_list_snapshots- list snapshots, filterable by agent, location/deletion state, and time range.slide_get_snapshot- get a single snapshot by ID.slide_get_snapshot_service_verification- get service-verification results for a snapshot.
Users
slide_list_users- list users, filterable by creation date.slide_get_user- get a single user by ID.slide_get_user_avatar- get a user's avatar image (base64 data URL).
Scope
This is a deliberately read-only, non-credential-exposing v1 surface, covering all 43 of Slide's non-secret-exposing GET endpoints. Slide is backup/DR infrastructure - several of its real endpoints return live secrets, and every mutating endpoint is out of scope for v1. None of the excluded material is implemented here, by design, not by oversight. Every tool is classified isAdmin: true in the Conduit wiring, given the sensitivity of backup/DR infrastructure data (client environments, device inventories, network topology).
Secret-bearing fields - stripped from an otherwise-useful response, never implemented as a pass-through:
Agent.passphrases[].passphrase(the live agent-encryption passphrase) - stripped fromslide_list_agents/slide_get_agent. The passphrase'snameandagent_passphrase_idare kept.Network.ipsec_conns[].psk(the live IPsec pre-shared key) - stripped fromslide_list_networks/slide_get_network.Network.wg_peers[].wg_private_key(the live WireGuard private key) - stripped from the same two tools.wg_public_keyis not secret and is kept.VirtualMachine.vnc_password(the live VNC password) - stripped fromslide_list_virtual_machines/slide_get_virtual_machine. Thevncconnection-info array (host/port/websocket URI) andvnc_enabledare not secret and are kept.ImageExport.password(the live Samba password for the exported share) - stripped fromslide_list_image_exports/slide_get_image_export. This field isn't one of Slide's headline "secret" endpoints, but it's the same class of live credential material as the four above, so it's held to the same bar.
Hard-excluded (mutating) - every POST/PATCH/PUT/DELETE endpoint, never implemented: creating/updating clients, networks, devices, agents, VLANs; starting backups; creating file/image/VM restores and push operations; managing IPsec connections, port forwards, and WireGuard peers; agent passphrase add/delete; device reboot/poweroff; and all other writes across every tag. This is real destructive/mutating infrastructure (delete client, delete network, delete restore, reboot device) - out of scope for v1 by design.
Out of v1 scope (not credential/provisioning, just not part of this connector's structured-data surface):
GET /v1/billing/credit-memo/{id}/pdf(BillingCreditMemoPDF) - returns rawapplication/pdfbinary, not structured data.GET /v1/billing/invoice/{id}/pdf(BillingInvoicePDF) - same.
They can be added as a follow-up if there's demand, after a deliberate scope decision - not by default.
Credential scope
This connector's own code is read-only by construction — but Slide also offers a real way to make the underlying credential read-only too, and we recommend using it.
Slide documents six account roles: Account Owner, Account Admin, Business Continuity Technician, Billing, and Read Only (read-only access to all resources). An API token inherits the role of whoever generates it in the Slide Console (Settings → API Keys).
Recommended: generate this connector's API token from a dedicated user with the Read Only role, not from an Account Owner/Admin user. This means that even if the token is ever exposed outside Conduit's control (a credential-store compromise, a misconfigured log, etc.), it cannot be used to delete backups, restores, networks, or devices — matching this connector's own read-only code with a read-only credential, rather than relying on the connector's code as the only safeguard.
Two separate claims, kept at different confidence levels:
Structurally verified (checked directly, stated with full confidence): this connector's own code makes zero mutating calls (
client.tshas exactly one HTTP verb function,doGet), and strips five live secret fields (agent passphrase, IPsec PSK, WireGuard private key, VM VNC password, image-export Samba password) from every response before it reaches a tool result — seesecret-redaction.test.ts.Vendor-documented, not independently verified (hedged deliberately): whether the Read Only role's restriction is enforced server-side against every mutating endpoint (vs. merely hidden in the console UI) has not been tested against a live Read Only account. This role is also opt-in, not default — a token from an Account Owner/Admin user (the common case for a fresh account) has no such restriction.
Do not read this connector, or this README, as having established that every Slide token is read-only — only that this connector's own code never attempts a mutation, and that Slide offers (but does not default to) a way to make the credential itself read-only as well.
Development
npm install
npm run build
npm test
npm run lint # tsc --noEmitDocker
The image listens on 0.0.0.0 inside the container (MCP_HTTP_HOST) and defaults to AUTH_MODE=gateway. Publish the port on loopback and pass the S2S secret. In gateway mode the Slide token arrives on each request as X-Slide-Api-Token. It is not read from the environment.
docker build -t slide-mcp .
docker run \
-e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
-p 127.0.0.1:8080:8080 \
slide-mcpCompose refuses to start when CONDUIT_S2S_SECRET is unset or empty. The gateway service does not set SLIDE_API_TOKEN and does not use env_file, so a project .env cannot inject a static vendor credential. Compose still interpolates CONDUIT_S2S_SECRET from that file. The published port is 127.0.0.1:8080:8080:
CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" docker compose upSingle-tenant HTTP (AUTH_MODE=env) still requires the S2S secret, then uses SLIDE_API_TOKEN:
docker run \
-e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
-e AUTH_MODE=env \
-e SLIDE_API_TOKEN="$SLIDE_API_TOKEN" \
-p 127.0.0.1:8080:8080 \
slide-mcpLocal HTTP without a secret is development-only. It binds 127.0.0.1 only (a non-loopback MCP_HTTP_HOST, including 0.0.0.0, is ignored and the override is logged) and logs a warning:
MCP_TRANSPORT=http MCP_ALLOW_INSECURE_DEV=1 npm run start:httpAvailable Tools
43 toolsslide_browse_file_restoreB
Browse the files and folders exposed by a file restore, optionally at a specific path.
Inputs: file_restore_id (required), path, limit, offset.
slide_browse_image_exportB
Browse the files and folders exposed by an image export.
Inputs: image_export_id (required), limit, offset.
slide_get_accountB
Get a single Slide account by ID.
Inputs: account_id (required).
slide_get_agentA
Get a single agent by ID - backup schedule, retention policy, volumes, alert configs, and connection info. If the agent has user-managed passphrases, only their names/IDs are returned, never the passphrase value itself.
Inputs: agent_id (required).
slide_get_agent_file_versionsA
Get the snapshot versions available for a specific file path on an agent.
Inputs: path (required), agent_id (required), limit, offset, +2 more.
slide_get_agent_servicesA
Get the list of backed-up services (e.g. installed applications, database engines) detected on an agent.
Inputs: agent_id (required).
slide_get_alertB
Get a single alert by ID.
Inputs: alert_id (required).
slide_get_audit_logB
Get a single audit log entry by ID.
Inputs: audit_id (required).
slide_get_backupA
Get a single backup attempt by ID, including its result and error details if it failed.
Inputs: backup_id (required).
slide_get_clientA
Get a single client by ID.
Inputs: client_id (required).
slide_get_deviceA
Get a single device by ID - hardware/service model, storage usage, warranty, and service status.
Inputs: device_id (required).
slide_get_device_networkB
Get a device's network configuration (DNS servers, network mode, gateway/address).
Inputs: device_id (required).
slide_get_device_vlanA
Get a single VLAN interface on a device by ID.
Inputs: vlan_id (required), device_id (required).
slide_get_file_restoreA
Get a single file restore by ID.
Inputs: file_restore_id (required).
slide_get_file_restore_pushA
Get the status of a single file restore push operation.
Inputs: file_restore_id (required), file_restore_push_id (required).
slide_get_image_exportA
Get a single image export by ID - image type, ISCSI/NFS connection info. Same secret redaction as slide_list_image_exports: no Samba password.
Inputs: image_export_id (required).
slide_get_networkA
Get a single disaster-recovery network by ID - port forwards, IPsec connections, and WireGuard peers. Same secret redaction as slide_list_networks: no IPsec PSK, no WireGuard private key.
Inputs: network_id (required).
slide_get_snapshotA
Get a single snapshot by ID - its storage locations and any deletions.
Inputs: snapshot_id (required).
slide_get_snapshot_service_verificationA
Get service-verification results for a snapshot (confirms which detected services would boot/mount successfully from it).
Inputs: snapshot_id (required).
slide_get_userA
Get a single user by ID.
Inputs: user_id (required).
slide_get_user_avatarA
Get a user's avatar image, returned as a base64 data URL.
Inputs: user_id (required).
slide_get_virtual_machineA
Get a single virtual machine by ID - state, CPU/memory, network config, RDP endpoint. Same secret redaction as slide_list_virtual_machines: no VNC password.
Inputs: virt_id (required).
slide_list_accountsB
List Slide accounts (the top-level MSP/reseller billing entities), filterable by creation date.
Inputs: limit, offset, sort_by, sort_asc, +2 more.
slide_list_agentsA
List agents (protected systems - servers, workstations, NAS shares - each paired to a Slide device), filterable by device, client, type, and pairing date. Never returns the agent-encryption passphrase, even if one is set - see slide_get_agent.
Inputs: limit, offset, sort_by, sort_asc, +5 more.
slide_list_alertsA
List alerts (e.g. device offline, agent backup failed, storage low), filterable by device, agent, resolved status, and creation date.
Inputs: limit, offset, sort_by, agent_id, +5 more.
slide_list_audit_actionsA
List the full set of audit action names usable in slide_list_audit_logs' audit_action_name filter.
Inputs: limit, offset, sort_by, sort_asc.
slide_list_audit_logsA
List audit log entries, filterable by action name, resource type, client, and audit-time range.
Inputs: limit, offset, sort_by, sort_asc, +5 more.
slide_list_audit_resource_typesA
List the full set of audit resource type names usable in slide_list_audit_logs' audit_resource_type_name filter.
Inputs: limit, offset, sort_by, sort_asc.
slide_list_backupsA
List backup attempts (each may have succeeded or failed), filterable by agent, snapshot, device, and start/end time range.
Inputs: limit, offset, sort_by, agent_id, +7 more.
slide_list_billing_credit_memosC
List billing credit memos.
Inputs: limit, offset.
slide_list_billing_invoicesC
List billing invoices.
Inputs: limit, offset.
slide_list_billing_subscriptionsB
List subscriptions and device licenses.
Inputs: limit, offset.
slide_list_clientsA
List clients (the MSP's end customers), filterable by creation date.
Inputs: limit, offset, sort_by, sort_asc, +2 more.
slide_list_devicesA
List devices (physical or virtual Slide Boxes), filterable by client and creation date.
Inputs: limit, offset, sort_by, sort_asc, +3 more.
slide_list_device_vlansA
List a device's configured VLAN interfaces.
Inputs: device_id (required).
slide_list_file_restore_pushesA
List push operations (copying a restored file back to a protected system) for a file restore, filterable by start/end time range.
Inputs: file_restore_id (required), limit, offset, sort_by, +5 more.
slide_list_file_restoresB
List file restores (a snapshot exposed for browsing/downloading individual files), filterable by creation date.
Inputs: limit, offset, sort_by, sort_asc, +2 more.
slide_list_image_exportsA
List image exports (a snapshot exported as an ISCSI/NFS/Samba-mountable disk image), filterable by creation date. The live Samba password is never returned, even though the underlying Slide API includes it.
Inputs: limit, offset, sort_by, sort_asc, +2 more.
slide_list_networksA
List disaster-recovery networks, filterable by client and creation date. IPsec connections and WireGuard peers are included with their non-secret fields only - the live IPsec pre-shared key and WireGuard private key are never returned, even though the underlying Slide API includes them.
Inputs: limit, offset, sort_by, sort_asc, +3 more.
slide_list_snapshotsA
List snapshots (taken as part of a successful backup), filterable by agent, location/deletion state, and backup start/end time range.
Inputs: limit, offset, sort_by, agent_id, +6 more.
slide_list_usersB
List users (technicians with console access), filterable by creation date.
Inputs: limit, offset, sort_by, sort_asc, +2 more.
slide_list_virtual_machinesA
List virtual machines created from a snapshot, filterable by creation date. VNC connection info (host/port/websocket URI) is included, but the live VNC password is never returned even though the underlying Slide API includes it.
Inputs: limit, offset, sort_by, sort_asc, +2 more.
slide_search_agent_filesA
Search the file paths indexed on an agent's protected system (requires file indexing to be enabled on the agent).
Inputs: agent_id (required), search_term (required), limit, offset, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 43 tools
Each tool maps to a distinct entity or sub-resource—accounts, agents, backups, snapshots, restores, exports, networks, VLANs, billing, audit, users—so the boundaries are mostly clear. A few list/get pairs, especially around file restores, restores pushes, and image exports, could be confused at a glance, but the descriptions resolve the differences.
All tools follow a consistent slide_<verb>_<noun> pattern, with get_ for single resources and list_ for collections. The one semantic outlier, slide_search_agent_files, still uses a clear verb-first convention and fits the overall style.
43 tools is well above the 3-15 well-scoped range and even past the 16-25 heavy range. The count is inflated by exhaustive read-only views of many sub-resources, which feels bloated even if each individual tool is narrowly defined.
The read-side surface is broad, covering list/get/browse for nearly every entity, but there are zero create, update, delete, or action tools for backups, snapshots, restores, alerts, devices, billing, users, or networks. Any workflow requiring lifecycle management or triggering operations will dead-end.
Maintenance
Related MCP Connectors
Read-only AI access to HAVN properties, leads, tasks, files, media, and analytics.
Securely review your Neuron business profile, services, calls, leads, bookings, and CRM data after account owner authorization. Read-only: the assistant can view only the Neuron account and permissions the owner approves.
Read-only by architecture: ask AI about QuickBooks, Xero and NetSuite, across every entity.
Ask your AI assistant about your logs, traces, security events, robot runs and video. Read-only.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables read-only file-management operations from AI assistants, including health checks, connection and folder listings, search, share-link resolution, metadata retrieval, and on-demand document reading.MIT
- AlicenseAqualityBmaintenanceProvides read-only visibility into CyberQP privileged access management data, including customer and account metadata, tenant event logs, and Just-In-Time account status and policies, for AI assistants.10Apache 2.0
- AlicenseNot gradedqualityCmaintenanceProvides safe, read-only CRM access for AI assistants with per-key scopes, field masking, rate limits, and a full audit log of allowed and blocked actions.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to read Datto SIRIS and ALTO backup appliance data, including protected machines and shares, snapshot history with local and screenshot verification, offsite replication status, fleet alerts, and partner portal activity logs. Provides read-only access to the Datto partner REST API with stateless, per-request authentication.Apache 2.0