hub-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
hub-mcp: the Hub Culture connector for Claude
A remote MCP server that lets Claude act on the Hub Culture network through HubID. It acts either as a signed-in member or as an agent persona (such as Vela Lumen) under its owner's HubID. It covers profiles, friends, hubs, discussions, events, pavilions and messages; Ven prices, the wallet and purchases; and Zeke.
It implements phase 1 of the PRD, Hub Culture Connector for Claude. Its Implementation status section tracks what is built, what changed, and what still waits on other teams.
Add it in Claude under Settings → Connectors → Add custom connector with https://<your host>/mcp. In Claude Code, run claude mcp add --transport http hub-culture https://<your host>/mcp.
How sign-in works
Claude ──/authorize (PKCE)──▶ hub-mcp consent page
member: ──▶ HubID /oauth/authorization ──▶ /hubid/callback?access_token=<HubID JWT>
agent: owner pastes the agent's Mandala agent key ──▶ HubID /mandala/key/token
Claude ◀──code── hub-mcp Claude ──/token──▶ opaque access + refresh tokens
Claude ──/mcp + Bearer──▶ hub-mcp ──Private-Key + the principal's JWT──▶ HubID / paymentshub-mcp is its own OAuth 2.1 server. It provides metadata discovery, dynamic client registration, PKCE (S256), refresh-token rotation and revocation. HubID's own sign-in is implicit-style and returns a JWT, so hub-mcp wraps it until HubID offers OAuth 2.1 itself.
Two kinds of principal, as in the PRD.
Members sign in with HubID. Their JWT refreshes for 14 days after a login, so they reconnect every 14 days.
Agents connect with a Mandala agent key, which the owner issues and can revoke in HubID; no password is involved. hub-mcp re-exchanges the key for a fresh JWT every 50 minutes, the most
/mandala/v1allows. A sign-in lastsAGENT_GRANT_DAYS.
Clients never see a HubID JWT or an agent key. Both are stored encrypted (AES-256-GCM), and tokens are stored only as hashes.
Only allow-listed redirect URIs can register. By default those are Claude's callbacks and loopback addresses (
ALLOWED_REDIRECT_URIS).
Related MCP server: Basecamp MCP Server
Scopes and tools
A token only lists the tools its scopes allow, minus any in DISABLED_TOOLS. claude.ai asks for no specific scopes, so it gets DEFAULT_SCOPES.
Scope | Tools |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
* Only when PAYMENTS_URL is set. ** Only when ZEKE_URL is set.
Safety
Ven mandate.
ven_sendrequires apurposeand anidempotency_key. A retry with the same key returns the first result instead of sending twice.Agents send through HubID's
/mandala/send. There the owner's custodian policy applies: per-send cap, rolling-window cap, recipient allowlist and approval threshold. A large send comes back aspending_approvalfor the owner to confirm. HubID only enforces this withMANDALA_ENFORCE_VEN_SEND=true.Members send through
/transactions, which has no mandate, so hub-mcp enforcesVEN_SEND_PER_TXandVEN_SEND_PER_DAYover a rolling 24 hours.Both stay under the connector caps, which act as a ceiling.
Idempotency elsewhere.
ven_requestalso requires anidempotency_key. Posting and messaging tools accept an optional one.Audit. Every write logs one JSON
auditline: SHA-256 hashes of the principal, tool, arguments and result, plus a timestamp. Forwarding these to OAI.io waits on OAI.io's write API.Rate limits apply per sign-in:
RATE_LIMIT_READ_PER_MINUTEandRATE_LIMIT_WRITE_PER_MINUTE.Kill switches.
DISABLED_TOOLSturns off a tool for everyone. Revoking an agent key cuts off that agent within the hour, the next time hub-mcp renews its token; revoking the connector's HubID app keys cuts off every call at once.Data minimisation. Other members come back with public basics only; emails, banking and profile fields are dropped. Private fields go only to their owner.
Zeke answers with the caller's context but stays read-only.
ask_zekeforwards the caller's token so Zeke knows who is asking, their friends and its memory of them. It also sendsread_only, which switches off Zeke's own send-Ven tool, so Ven moves only through the connector's mandate.The token goes only to a Zeke whose
/healthadvertisesread_only(zeke-ai-server branchclaude/connector-read-only). An older Zeke gets no token and answers from public knowledge; the result'scaller_contextsays which happened.thread_idmust be one the connector issued to the same HubID, so nobody can resume another member's conversation.
No admin access. The payments interchange is always called as role
buyer.
Services it calls
Service | Repo | Auth |
HubID API ( | hub/HubID | Connector app's |
Ven rates ( | hub/Ven.vc-Core-Laravel | Public |
Payments interchange | hub-culture/payments-interchange | HMAC-signed as Hub does ( |
Zeke ( | hub-culture/zeke-ai-server | System bearer token, plus the caller's JWT and |
Setup
The go-live checklist, with owners and checks, is in DEPLOY.md.
Development
npm install
npm test # end-to-end: both sign-in paths, the mandate and tool calls against fake HubID, payments and Zeke
npm run dev # needs a .env (or exported variables)
npx @modelcontextprotocol/inspector # point it at http://localhost:8080/mcpTool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
OAuth 2.1 short-link tools for AI agents with scoped tokens, approvals, audit logs, and revocation.
Generate images and video, run Spaces and build canvases from your agent. OAuth sign-in.
Connect AI agents to 1000+ apps with managed authentication and tool-calling.
Persistent identity, email, saved accounts and scoped credentials for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables Claude to authenticate with GitHub OAuth and access tools for user information, calculations, and GitHub repositories.5MIT
- FlicenseNot gradedqualityDmaintenanceEnables Claude to interact with Basecamp API for project and to-do management via OAuth authentication.-
- AlicenseAqualityBmaintenanceEnables Claude, Cursor, or any MCP client to query your own recovery scores, sleep, strain cycles, workouts, profile, and body measurements through every WHOOP API v2 read endpoint. Tools return records exactly as WHOOP sends them, with paging and date-range filtering, and refresh tokens automatically after a one-time login.113 npm1MIT
- AlicenseBqualityCmaintenanceEnables MCP clients such as Claude Desktop and Claude Code to give an agent its own verifiable identity, then ask and answer questions, publish and discuss library content, follow threads, exchange messages, and manage a public profile on a network reserved for AI agents. Exposes these capabilities as stdio tools, with content from other agents marked as data rather than instructions.4149 PyPIMIT