chatgpt MCP server
com.medigami/chatgptmedigami.comstreamable-httpv1.0.0Scanned
Medigami patient tools: rates, markups, denial codes, deadlines, overturn rates, procedure codes
6 tools: 6 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 chatgpt MCP server can do
The chatgpt MCP server is published by medigami.com, a domain the MCP Registry verified. It has 6 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool reads private data (get_hospital_rate); 1 tool brings in text other people can write (get_insurer_overturn_rate).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 13, 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.
6 tools
Only reads 6Show 6 read-only tools
check_bill_markupCompares one billed line to the hospital's own published negotiated rate for that code and returns the multiple.No findings
Why it is in this group
- The description's first verb is "compare": a word for reading.
Description, as the server wrote it Compares one billed line to the hospital's own published negotiated rate for that code and returns the multiple. You type the code and amount; no bill upload. Educational, not billing advice.
Annotations the server declares
- title: Bill markup check
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
explain_denial_codeExplains a CARC claim-adjustment reason code from the public X12 code list: what it means, whether it is typically appealable, and the general appeal path.No findings
Why it is in this group
- The name "explain_denial_code" says "explain": a word for reading.
Description, as the server wrote it Explains a CARC claim-adjustment reason code from the public X12 code list: what it means, whether it is typically appealable, and the general appeal path. Not legal advice.
Annotations the server declares
- title: Denial code explainer
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_appeal_deadlineReturns the appeal window that applies to a plan type (employer ERISA plan, marketplace/individual, Medicare Advantage, Medicaid) with the federal citation and how the clock is cou…No findings
Why it is in this group
- The name "get_appeal_deadline" says "get": a word for reading.
Description, as the server wrote it Returns the appeal window that applies to a plan type (employer ERISA plan, marketplace/individual, Medicare Advantage, Medicaid) with the federal citation and how the clock is counted. Cites the rule; does not tell you whether to file.
Annotations the server declares
- title: Appeal deadline rule
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_hospital_rateReturns the negotiated rate a named hospital publishes in its federally required machine-readable file for a CPT/HCPCS code, with the file's as-of date.Reads private dataNo findings
Why it is in this group
- The name "get_hospital_rate" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "file": it reads files.
Description, as the server wrote it Returns the negotiated rate a named hospital publishes in its federally required machine-readable file for a CPT/HCPCS code, with the file's as-of date. Public hospital-transparency data; educational, not billing advice.
Annotations the server declares
- title: Hospital published rate
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_insurer_overturn_rateReturns, for one insurer in one state, the share of external-review appeals the state regulator reports as overturned, with the sample size, the regulator's report as the source, a…Reads text others writeNo findings
Why it is in this group
- The name "get_insurer_overturn_rate" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "review": it reads comments, which other people can write.
Description, as the server wrote it Returns, for one insurer in one state, the share of external-review appeals the state regulator reports as overturned, with the sample size, the regulator's report as the source, and the as-of date. Available for CA, NY, MD, NJ, MI, OH, NC. This is one insurer's own historical rate — not a ranking or comparison against other insurers, and not a prediction for your case.
Annotations the server declares
- title: Insurer overturn rate
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
lookup_procedure_codePlain-English description of a CPT/HCPCS procedure code and its category, from public code references.No findings
Why it is in this group
- The name "lookup_procedure_code" says "lookup": a word for reading.
Description, as the server wrote it Plain-English description of a CPT/HCPCS procedure code and its category, from public code references.
Annotations the server declares
- title: Procedure code lookup
- readOnlyHint: true
- destructiveHint: false
- 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 outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- 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 20, 2026, 18:42 UTC, unchanged since Oct 22, 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
- 0
- 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
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
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 chatgpt https://mcp.medigami.com/chatgpt/mcpclaude mcp add --transport http chatgpt https://mcp.medigami.com/chatgpt/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": [
"mcp__chatgpt__get_hospital_rate",
"mcp__chatgpt__check_bill_markup",
"mcp__chatgpt__explain_denial_code",
"mcp__chatgpt__get_appeal_deadline",
"mcp__chatgpt__get_insurer_overturn_rate",
"mcp__chatgpt__lookup_procedure_code"
],
"ask": [],
"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 chatgpt. Review it before you use it.
Capability tags behind 2 rules
- mcp__chatgpt__get_hospital_rate private-data
- mcp__chatgpt__get_insurer_overturn_rate untrusted-input
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.medigami/chatgpt/verify?hash=317494f87925e5e708e3bf3e63a176b0e7280def682815fc2a8ec5486b0d74fb" | jq -e '.changed == false'Pinned hash 317494f87925, from Nov 13, 2026, 18:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.medigami/chatgpt/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.medigami/chatgpt)Source: MCP Registry. Synced Oct 21, 2026, 17:59 UTC.
chatgpt MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the chatgpt MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the chatgpt MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the chatgpt 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 chatgpt MCP server have?
- 6 tools: 6 read. get_hospital_rate, check_bill_markup, explain_denial_code, get_appeal_deadline, get_insurer_overturn_rate and lookup_procedure_code.
Does the chatgpt MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the chatgpt MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the chatgpt MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.