// SCAN REPORT

MCPDischarge

59 tools. 15 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 3 Jul 2026

15 can modify or destroy data

44 read-only

59 tools total

Community server · catalogue entry verified 03/07/2026

How to control MCPDischarge ↓

TOOL MAP

What MCPDischarge exposes to your agents

Read (44) Write / Execute (13) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous MCPDischarge tools

Financial · High generate_payment_link Generating a payment request link initiates a financial transaction workflow by creating a binding payment demand for a patient. Financial · Critical mark_invoice_paid This tool directly commits a financial state change by marking an invoice as paid, which affects billing records and financial obligations. Execute · High escalate_to_doctor This tool executes a clinical workflow action that triggers notifications and doctor involvement in patient care decisions. Write · High create_dispense_request This tool creates new dispense requests (reversible via cancellation or correction workflows typical in pharmacy systems), affecting medication fulfillment but not immediately destroying data or executing arbitrary code.

15 of MCPDischarge's 59 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCPDischarge

PolicyLayer is an MCP gateway — it sits between your AI agents and MCPDischarge, and nothing reaches the server without passing your rules. These are the rules we recommend:

Block financial tools by default

{
  "generate_payment_link": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Rate limit write operations

{
  "confirm_dispense": {
    "limits": [
      {
        "counter": "confirm_dispense_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "audit_invoice": {
    "limits": [
      {
        "counter": "audit_invoice_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register MCPDischarge — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCPDISCHARGE →

Instant setup, no code required.

FULL CATALOGUE

All 59 MCPDischarge tools

FINANCIAL 2 tools

Financial generate_payment_link Generate a payment request link for the patient. Financial mark_invoice_paid Mark a patient's invoice as paid.

EXECUTE 1 tools

Execute escalate_to_doctor Trigger doctor review/escalation for a clinical issue.

WRITE 12 tools

Write confirm_dispense Confirm that medicines have been issued to the patient. Write create_dispense_request Submit a bulk dispense request for a patient's full medication list. Write generate_invoice Create final patient invoice using PHI-safe EHR summary and drug costs. Write log_rbac_violation Manually log an RBAC violation for auditing or testing. Write mark_patient_ready_for_discharge Mark patient discharge status as ready. Write mark_urgent_request Flag a patient request as urgent for prioritized processing. Write notify_doctor Send a notification to the attending physician via the paging system. Write notify_patient Send a notification message to the patient via the SMS portal. Write record_chat_trace Record a PHI-safe chat trace for the Logs UI (no raw user text). Write request_represcription Request doctor re-prescription when no suitable alternative exists. Write update_prescription Update discharge medications after doctor re-prescribes. Write update_stock Adjust inventory level for a drug (add or remove units).

READ 44 tools

Read audit_invoice Generate compliance audit trail for a patient invoice. Read calculate_insurance_coverage Apply insurance logic to calculate covered amount and patient liability. Read check_access Check whether a role is permitted to call a tool on a server. Read check_bulk_stock Check stock for multiple drugs in one call. Read check_dose_validity Validate prescribed dose against formulary standards. Read check_drug_interactions Detect harmful drug interactions in a medication list. Read check_nearby_pharmacy_availability Check availability at external/nearby pharmacies when local stock is out. Read check_stock Check stock availability for a single drug (generic or brand name). Read check_therapeutic_equivalence Validate whether two drugs are clinically therapeutically equivalent. Read detect_dose_conflict Flag a mismatch between prescribed dose and formulary standard dose. Read dispense_request Submit a single drug dispense request for a patient. Read flag_controlled_substance Check and flag if a drug is a controlled substance. Read get_access_logs Retrieve recent RBAC violation audit logs. Read get_admission_info Get ward, admission date, discharge date, and length-of-stay. Read get_alerts Return system alerts, optionally filtered by patient or severity level. Read get_all_alternatives Get all possible therapeutic alternatives for a drug. Read get_alternative Get the primary therapeutic alternative when a drug is unavailable. Read get_billing_safe_summary Get billing-safe patient summary (all PHI fields stripped). Read get_bulk_price Get pricing for multiple drugs in one call. Read get_charges Get ward and lab charges based on ward type and length of stay. Read get_charges_by_icd Map ICD-10 diagnosis codes to billing charges. Read get_chat_traces Return recent PHI-safe chat traces for UI display. Read get_diagnosis_codes Get ICD-10 diagnosis codes only (PHI-safe). Read get_discharge_medications Get structured discharge medication list for a patient. Read get_insurance Get insurance details and coverage information for a patient. Read get_mcp_call_count Return total MCP tool call counts, optionally filtered by patient. Read get_patient_discharge_summary Get full patient discharge summary (PHI — restricted via RBAC). Read get_patient_history Get past prescriptions and diagnosis history for a patient. Read get_price Get unit and total price for a drug and quantity. Read get_recent_calls Return recent tool calls, RBAC violations, and alerts for the UI. Read get_role_permissions Return all permissions and callable tools for a given role. Read get_summary Return raw telemetry summary (counts, rates, averages). Read get_system_health Return health status of all MCP servers and aggregate metrics. Read get_total_cost Compute complete bill breakdown for a patient. Read list_in_stock_drugs List all drugs currently in stock (no patient ID required). Read list_patients List patient IDs (PHI-safe). Read resolve_drug_name_alias Convert between brand and generic drug names. Read semantic_drug_search Fuzzy/semantic search for drugs by partial or misspelled name. Read trace_workflow Return the full ordered MCP tool call trace for a patient's workflow. Read validate_billing_data Validate billing payload to ensure no PHI leakage. Read validate_drug_name Check if a drug name exists in the pharmacy formulary. Read validate_insurance Check insurance coverage eligibility for a patient. Read validate_patient_id Check if a patient ID exists in the EHR system. Read validate_prescription Check if discharge prescriptions are complete and valid.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about MCPDischarge

Can an AI agent move money through the MCPDischarge MCP server? +

Yes. The MCPDischarge server exposes 2 financial tools including generate_payment_link, mark_invoice_paid. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

How do I prevent bulk modifications through MCPDischarge? +

The MCPDischarge server has 12 write tools including confirm_dispense, create_dispense_request, generate_invoice. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach MCPDischarge.

How many tools does the MCPDischarge MCP server expose? +

59 tools across 3 categories: Execute, Read, Write. 44 are read-only. 15 can modify, create, or delete data.

How do I enforce a policy on MCPDischarge? +

Register the MCPDischarge MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every MCPDischarge tool call.

Deterministic rules across all 59 MCPDischarge tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCPDISCHARGE →

Instant setup, no code required.

59 MCPDischarge tools catalogued and risk-classified — across an index of 43,000+ MCP servers.