MCP Server for insurance carrier accounting — ingest carrier PDFs/Excel, reconcile against Applied Epic, post entries. Built for US insurance agencies.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"carrier-accounting-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Carrier Accounting MCP Server <!-- mcp-name: io.github.pramodmisra/carrier-accounting-mcp --> AI-powered carrier statement processing for US insurance agencies using Applied Epic. ## What It Does Automates the full carrier accounting lifecycle: 1. **Ingest** carrier PDFs, Excel, and CSV statements (48+ carriers supported) 2. **Normalize** via Claude LLM — maps any carrier format to a canonical schema 3. **Reconcile** with 5-layer matching engine (99.5% accuracy) 4. **Score** confidence per transaction (policy match, name, amount, date, duplicates) 5. **Post** to Applied Epic via SDK, UI automation, or CSV batch import 6. **Monitor** with daily accuracy dashboards and exception queues ## MCP Tools (21 tools) ### Ingestion - `ingest_carrier_statement` — Full pipeline: parse → normalize → validate → stage - `ingest_pdf` — Ingest a PDF carrier statement - `ingest_excel` — Ingest an Excel/CSV bordereaux ### Standalone Pipeline - `normalize_transactions` — Parse + normalize without validation - `validate_against_datalake` — Parse + normalize + validate (no staging) - `score_confidence` — Score a single transaction's match confidence - `browse_carrier_portal` — Download statements from carrier portals via Playwright ### Review Queue - `get_exception_queue_today` — Transactions needing human review - `approve` — Approve a transaction - `reject` — Reject a transaction with reason - `approve_run` — Bulk approve all review items from a run ### Epic Posting - `post_to_epic` — Post via REST API - `post_to_epic_via_browser` — Post via Playwright UI automation - `generate_epic_import` — Generate Epic-compatible CSV - `rollback` — Rollback posted entries ### Monitoring & Reports - `daily_metrics` — Daily accuracy scorecard - `carrier_accuracy` — Per-carrier accuracy over N days - `run_history` — Recent ingestion runs - `list_supported_carriers` — All 48+ configured carriers - `reconciliation_report` — Posted vs Epic compa…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.