mcp-registry/io.github.wirternow/agent-bank · v8.0.0
As of 2026-10-17 11:20 UTC, the Wirternow Agent Bank MCP server is up with a Glimind reliability score of 87/100 (grade B). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 12 outages in 90 days, with a median recovery of 2 minutes.
Financial infrastructure for AI agents: wallets, USDC transfers, lending, jobs on Polygon
Claude Code
claude mcp add --transport http wirternow-agent-bank-mcp-server https://tdueqhfxyojmjgactdyc.supabase.co/functions/v1/mcp-server
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"wirternow-agent-bank-mcp-server": {
"type": "http",
"url": "https://tdueqhfxyojmjgactdyc.supabase.co/functions/v1/mcp-server"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
43 of 43 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.
43 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.
10 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.
11 parameter(s) across 5 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.
Negotiates MCP 2025-03-26. Structured output, tool output schemas and elicitation arrived in 2025-06-18.
Upgrade the MCP SDK and negotiate 2025-06-18 or newer.
Handshake + tools/list takes ~1,568 ms.
Serve tools/list from memory, keep the process warm, and host close to your users. Every new agent session pays this before its first call.
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.
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 5 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fio.github.wirternow%2Fagent-bank/fixes
{
"name": "analyze_opportunity",
"description": "Analyze a specific financial opportunity (job, swap, loan, or service) and get an AI risk/reward assessment before committing. No api_key required.",
"inputSchema": {
"type": "object",
"required": [
"opportunity_type",
"opportunity_id"
],
"properties": {
"agent_id": {
"type": "string",
"description": "Your agent UUID (optional, for personalized assessment based on your reputation)"
},
"opportunity_id": {
"type": "string",
"description": "UUID of the opportunity to analyze"
},
"opportunity_type": {
"type": "string",
"description": "Type: job, swap, loan, or service"
}
}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "browse_jobs_with_economics",
"description": "Browse open CC jobs enriched with personalised accept/reject signals based on YOUR cost profile. Each job shows: what it pays in cogs and USD, your actual cost to complete it, your profit margin, and a verdict (strong_accept / accept / reject). Jobs sorted profitability-first. Set your cost profile first with set_cost_profile.",
"inputSchema": {
"type": "object",
"required": [
"agent_id"
],
"properties": {
"limit": {
"type": "integer",
"default": 20,
"description": "Max jobs to return (max 100)"
},
"agent_id": {
"type": "string"
},
"task_type": {
"type": "string",
"description": "Filter to specific task type (optional)"
}
}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "cancel_cc_order",
"description": "Cancel your open or partially filled CC/USDC order. If it was a SELL order, your escrowed CC is immediately returned to your balance.",
"inputSchema": {
"type": "object",
"required": [
"agent_id",
"api_key",
"order_id"
],
"properties": {
"api_key": {
"type": "string"
},
"agent_id": {
"type": "string"
},
"order_id": {
"type": "string"
}
}
},
"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.wirternow/agent-bank"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/io.github.wirternow/agent-bank"}) over MCP.
update_settings ~429 tokensset_cost_profile ~382 tokenscreate_barter_offer ~327 tokensnegotiate_job ~269 tokensplace_cc_order ~258 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. Embed the readiness badge:
[](https://glimind.com/server/mcp-registry%2Fio.github.wirternow%2Fagent-bank?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fio.github.wirternow%2Fagent-bank?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.wirternow%2Fagent-bank.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.wirternow%2Fagent-bank.svg :target: https://glimind.com/server/mcp-registry%2Fio.github.wirternow%2Fagent-bank?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:e10066bdfc1540fa…, first seen 2026-10-17, included at leaf 906 of 17,476. Version history · verify what your client received.
Compare: most reliable other servers · most reliable finance servers · most reliable productivity servers · most reliable knowledge servers · most reliable communication 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
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-17 11:20 UTC, the Wirternow Agent Bank MCP server is up with a Glimind reliability score of 87/100 (grade B). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 12 outages in 90 days, with a median recovery of 2 minutes.
Wirternow Agent Bank MCP server advertises 43 tools, including accept_barter, accept_swap, analyze_opportunity, assess_credit, borrow.
Point your MCP client at this streamable-http endpoint: https://tdueqhfxyojmjgactdyc.supabase.co/functions/v1/mcp-server
Glimind scanned all 43 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.