storedge-mcp
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., "@storedge-mcp show me my current tenants"
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.
storedge-mcp
The first MCP server for StorEdge (Storable Edge) - the self-storage management platform that 5,000+ storage facilities rely on.
Read and write tenants, units, leads, ledgers, move-ins/outs, insurance, tasks, and surcharge calculations for a self-storage facility - straight from Claude, Cursor, or any MCP client.
Why this exists
StorEdge is the operations backbone for tens of thousands of self-storage facilities (under the Storable / Red Nova Labs umbrella). Its REST API at api.storedgefms.com powers tenant management, lead tracking, billing, insurance enrollment, task workflows, and move-in/out pipelines.
The existing integration options all require building OAuth 1.0 signing + paginated list handling + typed-error mapping from scratch every time:
Tray.ai connector - locked inside Tray's walled garden, no MCP, no local-first.
Twilio integration - single-purpose, voice-channel only.
Java/PHP/.NET sample clients (
rednovalabs/storedge-api-client-*) - boilerplate code, no Claude tool surface.No first-party MCP server - StorEdge has not shipped one.
storedge-mcp is the open MCP surface. One stdio call away, agents can answer "what 10x10 units are available right now?", "create a reservation for unit A-12", "show me who's past due this week", and "calculate the surcharge for a $125 Visa payment".
Related MCP server: ghl-mcp
Quick start
pip install -e .
export STOREDGE_CONSUMER_KEY=... # from StorEdge dashboard
export STOREDGE_CONSUMER_SECRET=... # from StorEdge dashboard
export STOREDGE_FACILITY_ID=<uuid> # optional; tools accept it as arg too
storedge-mcpIn Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"storedge": {
"command": "storedge-mcp",
"env": {
"STOREDGE_CONSUMER_KEY": "...",
"STOREDGE_CONSUMER_SECRET": "...",
"STOREDGE_FACILITY_ID": "..."
}
}
}
}Tools (26)
Diagnostic
health_check(facility_id?)- verify credentials by listing one tenant. Returns fast-fail if OAuth signing is wrong.
Tenants
list_tenants(facility_id?, per_page?, page?, created_after?, created_before?, updated_since?, only_ids?)list_current_tenants(facility_id?, per_page?, page?)- only currently-active tenantssearch_tenants(account_code?, phone_number?, facility_id?)- by account code OR phone (exactly one)get_tenant(tenant_id, facility_id?)get_tenant_ledgers(tenant_id, facility_id?)- list of a tenant's rental agreementsget_tenant_notes(tenant_id, facility_id?)- operator notes attached to a tenant
Units
list_units(facility_id?, per_page?, page?, only_ids?)- every unit (rented + vacant + offline)list_available_units(facility_id?, per_page?, page?)- only units available for move-inget_unit(unit_id, facility_id?)list_unit_groups(facility_id?, per_page?, page?)- size buckets (5x5, 10x10, etc.)list_unit_types(facility_id?, per_page?, page?)- Parking, Climate, Drive-Up, etc.
Leads
list_leads(view="current", facility_id?, per_page?, page?)- view ∈ {current, reservations, inquiries, follow_up, waitlist, missed_move_ins}get_lead_counts(facility_id?)- open lead counts by statusget_lead(lead_id, facility_id?)create_lead(lead, facility_id?)- create a reservation or inquiryupdate_lead(lead_id, lead, facility_id?)- PATCH an existing lead
Ledgers (rental agreements)
list_current_ledgers(facility_id?, per_page?, page?)get_ledger(ledger_id, facility_id?)get_ledger_delinquency(ledger_id, facility_id?)- overdue balance + days lateget_ledger_invoices(ledger_id, facility_id?)
Insurance
get_insurance_summary(facility_id?)- counts + revenue rollupget_insurance_activity(facility_id?, per_page?, page?)
Tasks
list_tasks(category_id?, facility_id?, per_page?, page?)list_task_categories(facility_id?)create_task(task, facility_id?)complete_task(task_id, facility_id?)
Move-in / move-out pipeline
list_move_ins(facility_id?, per_page?, page?)- in-progress move-inslist_move_outs(facility_id?, per_page?, page?)- scheduled move-outs
Surcharge + invoices
calculate_surcharge(amount_cents, card_type?, facility_id?)- credit-card convenience fee quotelist_invoices_and_ledgers(facility_id?, per_page?, page?)
Auth
OAuth 1.0 one-legged (RFC 5849). Get your consumer key + secret from StorEdge dashboard → Corporate → Settings → API.
storedge-mcp ships its own OAuth 1.0 signer - not authlib's - because authlib's stock OAuth1Auth strips JSON request bodies during signing (silently breaking POST/PATCH/PUT). Our signer computes oauth_body_hash for non-form bodies and includes it in the signature per RFC 5849 §3.4.1.3.
Architecture
Built on industry-leading patterns from encode/httpx, stripe-python, lepture/authlib, boto3, pytest-dev/pytest, and astral-sh/ruff:
Shared
httpx.AsyncClientwith pooling + transport-level retries.Typed exception hierarchy (
StoredgeAuthError,StoredgeNotFoundError,StoredgeRateLimitError,StoredgeAPIError,StoredgeConnectionError) carrying structurederror_code(from StorEdge'smeta.error_codeenvelope) andrequest_id.Application-level retry with exponential backoff + full jitter on 429/5xx, honoring
Retry-After.isError-compliance - every tool re-raises on failure so FastMCP sets
isError: trueon the wire (Blackwell audit / MCPTox).JSONL audit logging via
STOREDGE_AUDIT_LOGenv var (or stderr default) - every tool call emits a structured record with redaction forpassword/api_key/tokenfields.Property-based tests (Hypothesis) for JSON round-trips.
respx for httpx mocking - no live API calls in tests.
See engineering-playbook.md for the full pattern reference.
Development
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
# Lint + type check + test
ruff check src tests
mypy src tests
pytest
# Coverage
pytest --cov=storedge_mcp --cov-report=term-missingCI matrix (Python 3.10-3.13 on ubuntu/macos/windows) lives in .github/workflows/ci.yml.
Sister projects
sanjibani publishes MCP servers for one niche vertical SaaS per day. See the full list for the rest:
hawksoft-mcp- independent insurance agenciesopen-dental-mcp- dental practice mgmtezyvet-mcp- veterinaryjobber-mcp- home service / field servicepracticepanther-mcp- legal practice (solo/small)realm-mp-mcp- church / nonprofitfieldroutes-mcp- pest control / lawn carecox-automotive-mcp- auto dealershipqualia-mcp- title and escrowcampspot-mcp- outdoor hospitality (campgrounds)cleancloud-mcp- laundry / dry cleaningplaymetrics-mcp- youth sports clubsforeup-mcp- golf course management
Need a custom MCP for your vertical SaaS stack? → mcp-services.landing.
License
MIT
References
Storable Edge API docs: https://api.storedgefms.com/
Storable Edge Swagger JSON: https://api.storedgefms.com/apidoc/schema_swagger_json_v1.json
OAuth 1.0 RFC: https://datatracker.ietf.org/doc/html/rfc5849
Available Tools
31 toolscalculate_surchargeC
Calculate the surcharge (credit-card convenience fee) for a payment.
Args:
amount_cents: Payment amount in cents (e.g. 12500 = $125.00).
card_type: Optional card-type slug (e.g. "visa"). Some
facilities surcharge differently per brand.
Inputs: amount_cents (required), card_type, facility_id. Returns: result
complete_taskC
Mark a task complete.
Inputs: task_id (required), facility_id. Returns: result
create_leadA
Create a new lead (reservation or inquiry) in StorEdge.
lead is the documented payload (see
https://api.storedgefms.com/). At minimum: is_reservation (bool)
and unit_id or unit_group_id for the unit of interest, plus
tenant contact fields (first_name, last_name, email or phone).
Use when: "send me a quote for a 10x10" → confirmation creates the lead.
Inputs: lead (required), facility_id. Returns: result
create_taskA
Create a new task on the facility task list.
task follows the documented shape (see
https://api.storedgefms.com/): typically category_id, due_at,
description, optionally unit_id and assigned-to user id.
Inputs: task (required), facility_id. Returns: result
get_insurance_activityC
Detailed insurance enrollment / cancellation activity.
Inputs: page, per_page, facility_id. Returns: result
get_insurance_summaryB
Insurance coverage summary for the facility.
Returns counts (enrolled, declined, etc.) and revenue rollup. Use when: "how many tenants have insurance?", "insurance revenue MTD".
Inputs: facility_id. Returns: result
get_leadC
Fetch a single lead by id.
Inputs: lead_id (required), facility_id. Returns: result
get_lead_countsA
Open-lead counts by status (lead vs reservation).
Cheap call - perfect for "how is our funnel looking this week?" or a daily ops summary.
Inputs: facility_id. Returns: result
get_ledgerA
Fetch a single ledger by id (rent rate, balance, unit, tenant).
Inputs: ledger_id (required), facility_id. Returns: result
get_ledger_delinquencyB
Show a ledger's delinquency status (overdue balance, days late).
Use when: "who's behind on rent?", "is tenant past due?".
Inputs: ledger_id (required), facility_id. Returns: result
get_ledger_invoicesC
List invoices attached to a specific ledger.
Inputs: ledger_id (required), facility_id. Returns: result
get_tenantB
Fetch a single tenant by id.
Use when: "show me the record for tenant ".
Inputs: tenant_id (required), facility_id. Returns: result
get_tenant_ledgersB
List a tenant's current ledgers (rental agreements).
Use when: "what units is tenant renting?".
Inputs: tenant_id (required), facility_id. Returns: result
get_tenant_notesC
List notes attached to a tenant.
Use when: "what has the manager said about this tenant?".
Inputs: tenant_id (required), facility_id. Returns: result
get_unitB
Fetch a single unit (size, rate, amenities, current tenant).
Inputs: unit_id (required), facility_id. Returns: result
health_checkA
Verify credentials work by listing one tenant.
If this fails with 401, the OAuth 1.0 signature is wrong (consumer key or secret bad). If it fails with 403, the consumer is not authorized for this facility. Use this whenever other tools start returning auth errors - confirms whether the problem is creds or scoping.
Inputs: facility_id. Returns: result
list_available_unitsB
List only units available for move-in.
Use when: "what 10x10 units do I have open?", "show rentable inventory".
Inputs: page, per_page, facility_id. Returns: result
list_current_ledgersC
List current ledgers (active rental agreements) for the facility.
Inputs: page, per_page, facility_id. Returns: result
list_current_tenantsA
List only currently-active tenants (not moved-out).
Use when: "show me everyone who has a unit rented right now".
Inputs: page, per_page, facility_id. Returns: result
list_invoices_and_ledgersB
List all invoices and their associated ledgers for the facility.
Use when: "show me this month's invoices", "reconcile billed vs paid".
Inputs: page, per_page, facility_id. Returns: result
list_leadsB
List leads for a facility.
Args:
view: One of current, reservations, inquiries,
follow_up, waitlist, missed_move_ins.
current = all open leads; reservations = committed but
not yet moved in; inquiries = open questions / not yet
committed; waitlist = queued for sold-out sizes;
missed_move_ins = never showed up.
Inputs: page, view, per_page, facility_id. Returns: result
list_move_insB
List current (in-progress) move-ins for the facility.
Use when: "what move-ins are scheduled this week?".
Inputs: page, per_page, facility_id. Returns: result
list_move_outsA
List scheduled (in-progress) move-outs for the facility.
Use when: "who's moving out this month?", "any move-outs this week?".
Inputs: page, per_page, facility_id. Returns: result
list_task_categoriesA
List the facility's task categories and subcategories.
Use when: "what task types can I create?".
Inputs: facility_id. Returns: result
list_tasksC
List tasks for the facility, optionally filtered by category.
Use when: "show me the open maintenance tasks", "list overdue tasks".
Inputs: page, per_page, category_id, facility_id. Returns: result
list_tenantsA
List tenants for a facility.
Use when: "show me all tenants", "list tenants moved in this month".
Pagination: per_page up to 100, page is 1-indexed.
Time filters accept ISO 8601 timestamps (2026-07-01T00:00:00Z).
Inputs: page, only_ids, per_page, facility_id, +3 more. Returns: result
list_unit_groupsC
List unit groups (size buckets: 5x5, 10x10 climate, etc.).
Inputs: page, per_page, facility_id. Returns: result
list_unitsB
List every unit for a facility (rented + vacant + offline).
For "what's available right now" use list_available_units.
Inputs: page, only_ids, per_page, facility_id. Returns: result
list_unit_typesC
List unit types (Parking, Climate Controlled, Drive-Up, etc.).
Inputs: page, per_page, facility_id. Returns: result
search_tenantsA
Search tenants by account code or phone number.
Provide exactly ONE of account_code or phone_number. Phone
matches digits - drop any non-numeric characters first.
Use when: "find the tenant on account 12345", "who has phone 555-1212?".
Inputs: facility_id, account_code, phone_number. Returns: result
update_leadC
Update an existing lead (PATCH).
Inputs: lead (required), lead_id (required), facility_id. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 31 tools
Each tool targets a distinct entity or action: leads, tenants, units, ledgers, invoices, tasks, insurance, moves, and health. There is no ambiguity; even similar tools like list_current_tenants vs list_tenants vs search_tenants serve different scopes.
All tools follow a consistent verb_noun snake_case pattern (create_lead, get_ledger, list_units, etc.). Even health_check and calculate_surcharge fit the pattern. No mixing of conventions.
31 tools cover a broad storage facility management domain. While slightly above the typical ideal range (3-15), each tool serves a clear purpose and the count is justified by the complexity of the domain.
The set covers many read operations and a few creates/updates, but lacks update/delete for several entities (tenants, units, leads) and misses write endpoints for insurance and moves. Some obvious lifecycle gaps exist.
Maintenance
Related MCP Connectors
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
MCP Server for agents to onboard, pay, and provision services autonomously with InFlow
Official MCP server for OmniDimension. Drive voice agents, dispatch calls, and run bulk campaigns.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server for Stessa rental-property accounting platform, enabling AI agents to query properties, portfolios, banking, documents, and tenancies via natural language.MIT
- FlicenseNot gradedqualityDmaintenanceMCP server for GoHighLevel sub-accounts, enabling management of CRM contacts, pipelines, calendars, invoices, and more via natural language.-
- AlicenseAqualityDmaintenanceMCP server for Kickserv field service management that enables AI agents to read and manage customers, jobs, and invoices through natural language.7MIT
- AlicenseNot gradedqualityBmaintenanceMCP server that connects AI assistants to Five9 contact center, allowing management of campaigns, agents, lists, and statistics via natural language commands.19MIT