coverage-rights MCP server
com.coverage-rights/coverage-rightscoverage-rights.comstreamable-httpv1.4.1Scanned
Insurer denial rates, appeal outcomes, appeal rights, and drug denial playbooks.
10 tools: 2 change things and 8 only read.
- Reads private data · 1
- Reads text others write · 5
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 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 coverage-rights MCP server can do
The coverage-rights MCP server is published by coverage-rights.com, a domain the MCP Registry verified. It has 10 tools. It can create or change data (2 tools: rank_denial_rates and prepare_knee_injection_evidence), but cannot delete data. 8 tools only read.
1 tool reads private data (get_state_external_review); 5 tools bring in text other people can write (get_treatment_outcomes, get_condition_outcomes, get_appeal_rights and 2 more).
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, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 10, 2026, version 1.4.1.
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.
10 tools
Changes things 2Claude Code: ask
prepare_knee_injection_evidencePrepare a free, category-level evidence checklist for a knee osteoarthritis hyaluronic-acid injection denial using routing facts, injection-series status, and record availability c…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 Prepare a free, category-level evidence checklist for a knee osteoarthritis hyaluronic-acid injection denial using routing facts, injection-series status, and record availability categories. Reuses the existing knee denial preparation kit. Does not inspect records or verify an insurer's specific criteria, provide clinical recommendations, draft an appeal, calculate deadlines, or estimate success. Send only the schema's bounded categories; never send names, identifiers, record text, or uploaded documents. Missing routing facts and unsupported routes remain explicit holds.
Annotations the server declares
- title: Prepare knee injection evidence
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
rank_denial_ratesInsurer prior-authorization denial rates (CY2025), ranked only within compatible reporting cohorts.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 Insurer prior-authorization denial rates (CY2025), ranked only within compatible reporting cohorts. Each row includes its cohort, rank within that cohort, exact source scope, calculation method, and source link. Never compare ranks across cohorts.
Annotations the server declares
- title: Denial rates ranked
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 8Show 8 read-only tools
get_appeal_rightsDeterministically resolve the governing appeal route, missing facts, filing recipient, deadlines, current external-review status, and verified grounds.Reads text others writeNo findings
Why it is in this group
- The name "get_appeal_rights" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it Deterministically resolve the governing appeal route, missing facts, filing recipient, deadlines, current external-review status, and verified grounds. Distinguishes Original Medicare, Medicare Advantage medical benefits, Part D pharmacy benefits, employer funding/governance, ACA, Medicaid, FEHB, TRICARE, and unknown coverage; unsupported or ambiguous routes fail closed.
Annotations the server declares
- title: Appeal rights lookup
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_condition_outcomesExternal-review outcomes for a medical condition: how often insurance denials involving this condition were overturned, plus the most-fought treatments for it.Reads text others writeNo findings
Why it is in this group
- The name "get_condition_outcomes" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it External-review outcomes for a medical condition: how often insurance denials involving this condition were overturned, plus the most-fought treatments for it.
Annotations the server declares
- title: Condition denial outcomes
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_drug_playbookCurated medication background, common denial patterns, preparation considerations, and available historical California review outcomes for covered GLP-1 and IBD drugs.Reads text others writeNo findings
Why it is in this group
- The name "get_drug_playbook" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it Curated medication background, common denial patterns, preparation considerations, and available historical California review outcomes for covered GLP-1 and IBD drugs. Accepts a brand or generic name. Confirm current labeling, the actual benefit channel and plan criteria; the guide does not establish current coverage, an exception entitlement, an individual outcome, or an applicable deadline.
Annotations the server declares
- title: Drug denial playbook
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_insurer_metricsGet an insurer's verified CY2025 prior-authorization metrics (denial rate, appeal overturn rate, decision times) from its own CMS-0057-F disclosure, plus contract/plan-level rows w…No findings
Why it is in this group
- The name "get_insurer_metrics" says "get": a word for reading.
Description, as the server wrote it Get an insurer's verified CY2025 prior-authorization metrics (denial rate, appeal overturn rate, decision times) from its own CMS-0057-F disclosure, plus contract/plan-level rows where collected. Includes source URLs and scope notes.
Annotations the server declares
- title: Insurer denial metrics
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_state_external_reviewHow a state's external review process works: filing deadline, regulator contact, and key facts.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_state_external_review" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "contact": it reads contacts.
- untrusted-inputThe name "get_state_external_review" says "get" and "review": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it How a state's external review process works: filing deadline, regulator contact, and key facts. Verified detail currently covers 10 states (CA, TX, FL, NY, PA, IL, OH, GA, NC, MI); other states return the covered list.
Annotations the server declares
- title: State external review
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_treatment_outcomesExternal-review outcomes for a treatment: how often insurer denials of this treatment/drug/procedure were overturned by independent reviewers (42,749 published CA IMR decisions, 20…Reads text others writeNo findings
Why it is in this group
- The name "get_treatment_outcomes" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it External-review outcomes for a treatment: how often insurer denials of this treatment/drug/procedure were overturned by independent reviewers (42,749 published CA IMR decisions, 2001–2026). Accepts a category slug (e.g. 'pharmacy') or specific treatment slug (e.g. 'zepbound', 'speech-therapy').
Annotations the server declares
- title: Treatment denial outcomes
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_insurersList tracked U.S.No findings
Why it is in this group
- The name "list_insurers" says "list": a word for reading.
Description, as the server wrote it List tracked U.S. health insurers with whether verified CMS-0057-F prior-authorization metrics are available for each.
Annotations the server declares
- title: List insurers
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_outcomesSearch treatments (categories + specific drugs/procedures) and conditions by the names used in the published data.No findings
Why it is in this group
- The name "search_outcomes" says "search": a word for reading.
Description, as the server wrote it Search treatments (categories + specific drugs/procedures) and conditions by the names used in the published data. The query must appear in a name as a whole word or phrase (e.g. 'wegovy', 'back pain', 'ct scan'); generic names, abbreviations and drug classes are not translated, so search the brand or the specific treatment. Returns slugs for get_treatment_outcomes / get_condition_outcomes plus headline overturn rates.
Annotations the server declares
- title: Search outcomes
- 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 outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write5
- 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, 18:36 UTC, unchanged since Nov 6, 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
- 2
- 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.coverage-rights.com/api/mcp: tools/list returned 10 tools to an anonymous client, including rank_denial_rates (write), prepare_knee_injection_evidence (write)
Posture changes
- Nov 6, 2026
- Tools that change things, listed without credentials: 1 to 2
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.
Tools1 added, 9 changed.+1 added~9 changedView diff
- Added:prepare_knee_injection_evidenceChanges things
- Changed:get_appeal_rightsOnly readsinputSchema
- Changed:get_condition_outcomesOnly readsinputSchema
- Changed:get_drug_playbookOnly readsdescriptioninputSchema
- Changed:get_insurer_metricsOnly readsinputSchema
- Changed:get_state_external_reviewOnly readsinputSchema
- Changed:get_treatment_outcomesOnly readsinputSchema
- Changed:list_insurersOnly readsinputSchema
- Changed:rank_denial_ratesChanges thingsinputSchema
- Changed:search_outcomesOnly readsdescriptioninputSchema
PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 2.View diff
- Tools that change things, listed without credentials: 1 to 2
Install
Pinned to version 1.4.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http coverage-rights https://www.coverage-rights.com/api/mcpclaude mcp add --transport http coverage-rights https://www.coverage-rights.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": [
"mcp__coverage-rights__list_insurers",
"mcp__coverage-rights__get_insurer_metrics",
"mcp__coverage-rights__get_treatment_outcomes",
"mcp__coverage-rights__get_condition_outcomes",
"mcp__coverage-rights__search_outcomes",
"mcp__coverage-rights__get_appeal_rights",
"mcp__coverage-rights__get_drug_playbook",
"mcp__coverage-rights__get_state_external_review"
],
"ask": [
"mcp__coverage-rights__rank_denial_rates",
"mcp__coverage-rights__prepare_knee_injection_evidence"
],
"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 coverage-rights. Review it before you use it.
Capability tags behind 5 rules
- mcp__coverage-rights__get_treatment_outcomes untrusted-input
- mcp__coverage-rights__get_condition_outcomes untrusted-input
- mcp__coverage-rights__get_appeal_rights untrusted-input
- mcp__coverage-rights__get_drug_playbook untrusted-input
- mcp__coverage-rights__get_state_external_review private-data, 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.coverage-rights/coverage-rights/verify?hash=656a474f836c2e366b4b02b7b3eca6eb93ebd63c8e7cf9c9004be5b2d5755d29" | jq -e '.changed == false'Pinned hash 656a474f836c, from Nov 10, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.coverage-rights/coverage-rights/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.coverage-rights/coverage-rights)Source: MCP Registry. Synced Nov 10, 2026, 21:17 UTC.
coverage-rights MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the coverage-rights MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 2 of which can change, send or delete something, and 0 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 coverage-rights MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the coverage-rights 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 coverage-rights MCP server have?
- 10 tools: 2 write, 8 read. rank_denial_rates, prepare_knee_injection_evidence, list_insurers, get_insurer_metrics, get_treatment_outcomes, get_condition_outcomes, search_outcomes, get_appeal_rights and 2 more.
Does the coverage-rights MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the coverage-rights MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the coverage-rights MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.