aspire-mcp
Click on "Install 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., "@aspire-mcpshow me open A/R over 60 days"
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.
Aspire read-only connector — build & deploy
A small remote MCP server that gives Claude/Cowork live, read-only access to your Aspire data, so you can hand management a Cowork space that answers questions straight from Aspire in real time.
How it fits together
Management (Cowork) ──▶ Claude ──▶ [Aspire read-only MCP server] ──▶ Aspire REST API
(custom connector, HTTPS + token) (your ClientId/Secret)Aspire ClientId/Secret live only on the server — never in Claude, never shown to viewers.
The server makes only GET requests against an allow-list of resources → read-only by construction.
Callers must send a shared bearer token (
CONNECTOR_TOKEN) to reach the server.
Related MCP server: sql-mcp
Step 1 — Create an Aspire API credential
In Aspire: System Admin → API → create a credential. Copy the ClientId and Secret.
(Reference: Aspire API guide, base URL https://cloud-api.youraspire.com, Swagger at /swagger.)
Step 2 — Configure
cp .env.example .env # then fill in ASPIRE_CLIENT_ID, ASPIRE_SECRET
# generate a long random CONNECTOR_TOKEN, e.g.:
openssl rand -hex 32Confirm ASPIRE_TOKEN_URL against your API credential page (the POST that returns a bearer token).
Step 3 — Run locally to verify
npm install
npm run dev
# in another terminal:
curl -s localhost:8080/health # -> {"ok":true}Step 4 — Host it (must be public HTTPS for a claude.ai connector)
Any of these work; pick one:
Cloudflare Workers / Render / Fly.io / Railway — deploy the repo, set the env vars as secrets.
A small VM behind HTTPS (Caddy/nginx) running
npm run build && npm start.
You need a stable URL like https://aspire-mcp.yourcompany.com/mcp.
Step 5 — Register as a custom connector in Claude
claude.ai → Settings → Connectors → Add custom connector:
URL:
https://<your-host>/mcpAuth: bearer token = your
CONNECTOR_TOKEN
Add it at the organization level so it can be shared, not just your own account.
Auth: header, not URL
The connector token is sent in the Authorization: Bearer <token> header — nothing
secret ever appears in the URL. In a Cowork plugin's .mcp.json:
{
"mcpServers": {
"Aspire_MCP": {
"type": "http",
"url": "https://<your-host>/mcp",
"headers": { "Authorization": "Bearer ${ASPIRE_CONNECTOR_TOKEN}" }
}
}
}The server still accepts the old POST /mcp/<token> path form for backward
compatibility during migration, but it is deprecated. Once every consumer sends the
token as a header, delete the legacy route in index.ts and rotate CONNECTOR_TOKEN.
Step 6 — Roll out to management (read-only)
Enable the connector for the management group/space.
They open a Cowork space and ask questions ("show me open A/R over 60 days", "billing by division this month") — Claude answers live from Aspire.
Because the server is GET-only over an allow-list, there is no way for a viewer to change Aspire data.
Tools exposed
list_aspire_resources— what can be queried.aspire_query— generic read-only OData query (resource +$filter/$select/$top/$expand…).aspire_open_ar— example curated report (open invoices by customer). Add more curated tools the same way.
Extending
Add curated, named reports (like aspire_open_ar) for the questions management asks most —
they're safer and faster than free-form queries, and read cleanly in Cowork.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Query your warehouse or a CSV with Claude/ChatGPT over MCP, governed by table-level ACL + audit.
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
- BasedashOAuthcom.basedash
Governed BI MCP. Ask questions of live company data and list workspace sources via OAuth.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables read-only access to company data across PostgreSQL, MongoDB Atlas, and flat files through MCP tools, allowing AI assistants to query and retrieve information via natural language.-
- FlicenseAqualityCmaintenanceProvides read-only SQL Server access via MCP tools and a chat interface for natural-language database queries.4-
- FlicenseNot gradedqualityBmaintenanceEnables AI assistants to query internal business data for insights into customers, revenue, subscriptions, sales, and churn through controlled, read-only MCP tools.-
- AlicenseNot gradedqualityBmaintenanceProvides read-only, guarded access to business databases via MCP. Enables natural language querying with built-in security barriers like table allowlists, PII masking, and audit logging.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tmarkstice/aspire-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server