Fixpayment

Created By
FixPayment3 months ago
FixPayment MCP for Creditors is a production-ready integration layer that connects AI assistants directly to the FixPayment creditor portal, enabling real-time interaction with live recovery and payment data. Built on a FastMCP-powered backend, this server allows AI tools to securely perform core creditor operations—such as creating and managing accounts, updating recovery statuses, and generating detailed financial reports—using simple natural language commands.Designed for automation and scale, the MCP server supports everything from basic account summaries to advanced performance analytics, mirroring the same insights available in the FixPayment dashboard. With strict API key-based authentication and per-creditor data isolation, it ensures that all operations remain secure and scoped. Whether you're building internal dashboards, automating collections workflows, or integrating AI into your finance stack, FixPayment MCP provides a seamless, reliable bridge between your assistant and your debt recovery operations.
Overview

FixPayment MCP for Creditors enables AI assistants to directly interact with live debt recovery and payment resolution workflows through a secure, API-key-based MCP server. By connecting your AI tools to the FixPayment creditor portal, you can automate account creation, track payment statuses, and generate real-time financial reports, all using natural language.

Built on a production-grade system already used by creditors, this MCP server transforms manual collection processes into intelligent, AI-driven operations. It allows teams to move faster, reduce operational overhead, and gain instant insights without switching between dashboards or writing complex queries.

Use Cases

  1. Automated Account Creation Quickly create recovery or reminder accounts directly from your AI assistant. Example: Create accounts for unpaid invoices in bulk Reduces manual data entry and onboarding time

  2. Real-Time Status Management Update account statuses like active, paid, settled, or closed instantly. Example: Automatically mark accounts as “paid” after confirmation Keeps your system always up-to-date

  3. AI-Powered Financial Reporting Generate detailed reports without logging into the portal. Accounts, payments, settlements, and performance insights Example: “Show me total collections this month”

  4. Bulk Account Monitoring List and analyze multiple accounts without exposing sensitive debtor data. Ideal for dashboards and internal tracking tools Maintains privacy while enabling insights

  5. Workflow Automation for Collections Teams Integrate with internal tools to automate repetitive recovery tasks. Example: Auto-create accounts from CRM or ERP systems Trigger actions based on account events

  6. Performance Tracking & Analytics Track collection rates, payment trends, and recovery performance over time. Example: Identify underperforming segments or months Helps optimize recovery strategies

  7. AI Assistant Integration (Claude & Others) Use natural language to control your entire creditor workflow. Example prompts: “Create a recovery account for invoice INV-1023” “Give me a summary of all unpaid accounts” No need for manual API handling

  8. Secure Multi-Tenant Operations Each API key is scoped to a single creditor. Ensures strict data isolation and security Plan-based access control (Basic, Reports, Full)

Server Config

{
  "mcpServers": {
    "fixpayment-cred-portal": {
      "transport": "http",
      "url": "http://fixpayment.org:8000",
      "headers": {
        "Content-Type": "application/json"
      }
    }
  }
}
Project Info
Created At
3 months ago
Updated At
3 months ago
Author Name
FixPayment
Star
-
Language
-
License
-
Category

Recommend Servers

View All
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

7 hours ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago