Health Agent MCP server
com.bonissystems/health-agentbonissystems.comstreamable-httpv1.0.0Scanned
Look up a denial code, your appeal deadline, a billing code or 2027 Medicare drug plans.
4 tools: 4 change things.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Health Agent MCP server can do
The Health Agent MCP server is published by bonissystems.com, a domain the MCP Registry verified. It has 4 tools. It can create or change data (4 tools: medicare_drug_plans_2027, denial_code_lookup, appeal_deadline and hcpcs_lookup), but cannot delete data. None of its tools only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 14, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
4 tools
Changes things 4Claude Code: ask
appeal_deadlineThe last day to file an appeal of a Medicare, Medicare Advantage, Part D or commercial/ACA/employer plan denial, counted the way the rules count it (Medicare presumes receipt 5 day…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it The last day to file an appeal of a Medicare, Medicare Advantage, Part D or commercial/ACA/employer plan denial, counted the way the rules count it (Medicare presumes receipt 5 days after the notice date), with days remaining, who decides, and the next level. Not legal advice; confirm the exact date with the official source it names.
Annotations the server declares
- title: Last day to appeal a denial
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
denial_code_lookupWhat an insurance or Medicare denial code on an explanation of benefits means: a Claim Adjustment Reason Code (e.g.1 finding
Why it is in this group
- The name "denial_code_lookup" says "lookup": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "denial_code_lookup" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "denial_code_lookup" says "lookup": a word for reading.
Description, as the server wrote it What an insurance or Medicare denial code on an explanation of benefits means: a Claim Adjustment Reason Code (e.g. CO-97, PR-1, 197) or a Remark Code (e.g. M15, N432), from the X12 code lists. With a prefix it says whether the person may owe the amount (CO is the provider's write-off, PR is patient responsibility); for common codes it gives the typical fix and who acts. Not legal or billing advice.
Annotations the server declares
- title: What a claim denial code means
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
hcpcs_lookupWhat a HCPCS Level II code on a bill, supplier invoice or explanation of benefits describes (a letter and four digits, e.g.1 finding
Why it is in this group
- The name "hcpcs_lookup" says "lookup": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "hcpcs_lookup" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "hcpcs_lookup" says "lookup": a word for reading.
Description, as the server wrote it What a HCPCS Level II code on a bill, supplier invoice or explanation of benefits describes (a letter and four digits, e.g. E0601, J9271, A4253), with its Medicare coverage status, from CMS's quarterly HCPCS file. CPT codes (five digits) are not covered: their descriptions are copyrighted.
Annotations the server declares
- title: What a HCPCS billing code is
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
medicare_drug_plans_2027Every 2027 Medicare plan with drug coverage CMS lists for a county: stand-alone drug plans (with Original Medicare) and Medicare Advantage plans, each with company, monthly premium…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Every 2027 Medicare plan with drug coverage CMS lists for a county: stand-alone drug plans (with Original Medicare) and Medicare Advantage plans, each with company, monthly premium, change from 2026, drug deductible and, for stand-alone plans, the premium with Extra Help. Give a ZIP code, or a state and county. From CMS's 2027 plan file. It does not say which plan covers which drug (the county page it links checks that against CMS's 2027 drug lists) and it is not a recommendation.
Annotations the server declares
- title: 2027 Medicare drug plans for a county
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 15, 2026, 13:18 UTC, unchanged since Nov 15, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://healthagentcare.com/api/mcp: tools/list returned 4 tools to an anonymous client, including medicare_drug_plans_2027 (write), denial_code_lookup (write), appeal_deadline (write), hcpcs_lookup (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "denial_code_lookup" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "denial_code_lookup" says "lookup": a word for reading.
- Warnhcpcs_lookup
The server marks "hcpcs_lookup" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "hcpcs_lookup" says "lookup": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http health-agent https://healthagentcare.com/api/mcpclaude mcp add --transport http health-agent https://healthagentcare.com/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__health-agent__medicare_drug_plans_2027",
"mcp__health-agent__denial_code_lookup",
"mcp__health-agent__appeal_deadline",
"mcp__health-agent__hcpcs_lookup"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as health-agent. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.bonissystems/health-agent/verify?hash=2d368680597c4760bd3958bded6607bd6a167e41a3431acd5a29a24a20bde1cd" | jq -e '.changed == false'Pinned hash 2d368680597c, from Nov 14, 2026, 18:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.bonissystems/health-agent/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.bonissystems/health-agent)Source: MCP Registry. Synced Nov 14, 2026, 18:17 UTC.
Health Agent MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Health Agent MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 4 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Health Agent MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Health Agent MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Health Agent MCP server have?
- 4 tools: 4 write. medicare_drug_plans_2027, denial_code_lookup, appeal_deadline and hcpcs_lookup.
Does the Health Agent MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Health Agent MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Health Agent MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.