# @backwork/mcp

MCP server for Backwork: Medicare and payer medical policy, prior authorization, claim risk, and medical codes. Hosted OAuth remote or local stdio.

- **Type:** MCP server
- **Trust:** 85/100 (A), scored on the package rubric
- **Verification:** verified (build provenance)
- **Version:** 2.1.2
- **Author:** Backwork LLC
- **License:** MIT
- **npm:** @backwork/mcp
- **Endpoints:** streamable-http https://backworkhealth.com/mcp
- **Source:** https://github.com/tylergibbs1/backwork-mcp
- **Endpoint health:** reachable (last checked 2026-10-04T23:05:52.269Z, 1 sample) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

85/100 (A), scored on the package rubric
- Publisher verified: no
- Build provenance: verified attestation
- npm trusted publishing (OIDC): yes
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 1 day

## Security scan

- **Status:** clean
- **Scanned:** 2026-10-05T01:56:50.782Z
- **Version scanned:** 2.1.2
- **CVEs:** none found by OSV at scan time

## Tools

8 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `coverage_lookup`
- `policy_research` — Research coverage policies and criteria. Use this for policy search, fetching one policy by ID, searching extracted criteria, reviewing policy changes, mapping 
- `claim_validation` — Validate claim coverage, documentation requirements, denial risk, and optional policy-specific criteria in one workflow.
- `prior_auth_research` — Check, start, or poll payer prior-authorization research without exposing separate task-management tools.
- `drug_formulary_research` — Search commercial pharmacy-benefit evidence from CVS Caremark, Express Scripts, and UnitedHealthcare / Optum Rx.
- `compliance_review` — Review compliance dashboard state, list unreviewed policy changes, or acknowledge changes when explicitly requested.
- `webhook_management` — List, create, update, delete, or test webhook endpoints. Use only when the user is explicitly managing webhook configuration. Backwork delivers one event type, 
- `system_health` — Check Backwork API health and dependency status. Use for diagnostics, not for coverage research.

## Install

**Verdict: install** — No blocking findings and no open coverage gaps — safe to install as configured.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@backwork/mcp\"\n      ],\n      \"env\": {\n        \"BACKWORK_API_KEY\": \"<YOUR_BACKWORK_API_KEY>\"\n      }\n    }\n  }\n}"
```
**Credentials it will ask for** (names only — Forge never holds a value):
- `BACKWORK_API_KEY` — Backwork API Key (required)
Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each <YOUR_NAME> in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one.
- This entry needs 1 credential (1 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset.

## Blast radius

Moderate blast radius — runs locally and hosted; holds an api key.
- Floor 27, ceiling 27 (tier: moderate)
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40backwork%2Fmcp
- Install plan: https://forgeregistry.com/api/v1/packages/%40backwork%2Fmcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40backwork%2Fmcp
- HTML page: https://forgeregistry.com/registry/%40backwork%2Fmcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.