mcp-registry/io.github.aw3-technology/cred · v1.1.0
claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server. Other clientsAs of 2026-11-22 19:00 UTC, the Cred MCP server is up with a Glimind reliability score of 94/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
Issue, deduct, refund and sell credits: checkout, subscriptions, saved cards, escrow and wallets.
Point your MCP client at this streamable-http endpoint: https://eutdgemlrpvnxfkkpvlu.supabase.co/functions/v1/cred-mcp
49 of 49 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
49 tools on one server. Tool-selection accuracy drops as the menu grows, and some clients (e.g. Cursor) cap the number of active tools.
Group tools by task into smaller servers or toolsets, and merge near-duplicates behind one tool with a mode parameter. How to fix →
20 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
15 parameter(s) across 7 tool(s) have no description.
Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call. How to fix →
Loading this server's tool list costs an agent ~18,346 tokens before any work — more than 90% of MCP servers.
Split rarely-used tools into a separate server or a toolset the client can enable, or expose one "search tools" entry point. Many agents load every connected server's tools into every request. How to fix →
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 7 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fio.github.aw3-technology%2Fcred/fixes
{
"name": "bulk_create_users",
"description": "Create or update up to 1000 users in one call (one CRD for the batch). Returns counts of created/updated and per-row errors; a bad row does not fail the batch. A row's own signup_url/signup_host overrides the request-level signup_url. Costs 1 CRD (platform credit) per call, charged even when the call is then rejected (a 429 RATE_LIMITED costs nothing). Error results include request_id; quote it to support.",
"inputSchema": {
"type": "object",
"required": [
"users"
],
"properties": {
"users": {
"type": "array",
"items": {
"type": "object",
"required": [
"external_id"
],
"properties": {
"name": {
"type": "string"
},
"email": {
"type": "string"
},
"metadata": {
"type": "object",
"description": "stripe_account_id is Cred-only: a value you send is silently dropped"
},
"signup_url": {
"type": "string"
},
"external_id": {
"type": "string"
},
"signup_host": {
"type": "string"
},
"wallet_address": {
"type": "string"
},
"signup_credit_type_id": {
"type": "string"
}
}
},
"maxItems": 1000,
"description": "User rows"
},
"api_key": {
"type": "string",
"description": "Cred API key (optional if set via the x-api-key header)"
},
"project_id": {
"type": "string",
"description": "Cred project ID (optional; the API key already identifies the project)"
},
"signup_url": {
"type": "string",
"description": "Default signup URL for rows without their own"
},
"x402_payment": {
"type": "string",
"description": "Base64 x402 PaymentPayload, only when a previous call failed with an x402 PaymentRequired because the account is out of CRD"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "buy_credits_x402",
"description": "MOVES MONEY: buy a project's credits by paying in stablecoin over x402. Call once without x402_payment to receive the payment requirements (returned as an error result containing the x402 PaymentRequired object), sign them with your wallet, then call again passing the base64 payment payload as x402_payment. Requires no API key — the payment is the credential — and costs no CRD.",
"inputSchema": {
"type": "object",
"required": [
"project_id",
"credits"
],
"properties": {
"credits": {
"type": "number",
"description": "How many credits to buy (within the project's min/max)",
"exclusiveMinimum": 0
},
"buyer_id": {
"type": "string",
"description": "Identifier to credit (defaults to your paying wallet address)"
},
"buyer_name": {
"type": "string",
"description": "Display name for the buyer record"
},
"project_id": {
"type": "string",
"description": "Project selling the credits"
},
"buyer_email": {
"type": "string",
"description": "Email to attach to the buyer record"
},
"x402_payment": {
"type": "string",
"description": "Base64-encoded x402 PaymentPayload signed by your wallet"
},
"credit_type_id": {
"type": "string",
"description": "Credit type to buy (defaults to the project's x402 credit type)"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "cancel_subscription",
"description": "Cancel a subscription. By default it cancels at period end (credits already issued stay; no further renewals). at_period_end: false cancels immediately with no refund. With user_id/email instead of subscription_id, every live subscription of that customer is canceled. Costs 1 CRD (platform credit) per call, charged even when the call is then rejected (a 429 RATE_LIMITED costs nothing). Error results include request_id; quote it to support.",
"inputSchema": {
"type": "object",
"properties": {
"email": {
"type": "string",
"description": "Customer email (alternative to subscription_id)"
},
"api_key": {
"type": "string",
"description": "Cred API key (optional if set via the x-api-key header)"
},
"user_id": {
"type": "string",
"description": "External user ID (alternative to subscription_id)"
},
"project_id": {
"type": "string",
"description": "Cred project ID (optional; the API key already identifies the project)"
},
"x402_payment": {
"type": "string",
"description": "Base64 x402 PaymentPayload, only when a previous call failed with an x402 PaymentRequired because the account is out of CRD"
},
"at_period_end": {
"type": "boolean",
"description": "Default true; false cancels now"
},
"subscription_id": {
"type": "string",
"description": "Cred subscription ID or Stripe sub_… ID"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": true,
"idempotentHint": true
}
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/io.github.aw3-technology/cred"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/io.github.aw3-technology/cred"}) over MCP.
issue_credits ~654 tokenscreate_checkout_session ~644 tokensrefund_credits ~617 tokensredeem_credits ~605 tokenscreate_escrow_hold ~555 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live.
Shows whether the server is live and its agent-readiness score; it updates within the hour.
[](https://glimind.com/server/mcp-registry%2Fio.github.aw3-technology%2Fcred?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fio.github.aw3-technology%2Fcred?ref=badge"><img src="https://glimind.com/badge/mcp-registry%2Fio.github.aw3-technology%2Fcred.svg" alt="MCP server status"></a>
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:e2328114e2bb7d87…, first seen 2026-11-16, included at leaf 302067 of 384,917. Version history · verify what your client received.
Compare: most reliable data servers · most reliable finance servers · most reliable other servers · most reliable analytics servers · most reliable blockchain servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp?ref=install-server"
}
}
}
A free Glimind key lets your agent check whether a server works right now before it calls it, and switch to a live one when it doesn't. No signup, no card.
As of 2026-11-22 19:00 UTC, the Cred MCP server is up with a Glimind reliability score of 94/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
Cred MCP server advertises 49 tools, including apply_referral, bulk_create_users, buy_credits_x402, cancel_subscription, capture_escrow_hold.
Point your MCP client at this streamable-http endpoint: https://eutdgemlrpvnxfkkpvlu.supabase.co/functions/v1/cred-mcp
Glimind scanned all 49 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.