GPH Intelligence - Healthcare Vendor Finder MCP server
io.github.Crindo2/gph-mcp-serverCrindo2streamable-httpv1.1.1Scanned
Find 76,000+ curated healthcare service vendors across 25 categories and all 50 US states.
6 tools: 1 change things and 5 only read.
- Reads private data · 2
- Reads text others write · 3
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- 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 GPH Intelligence - Healthcare Vendor Finder MCP server can do
The GPH Intelligence - Healthcare Vendor Finder MCP server is published by the GitHub account Crindo2. It has 6 tools. It can create or change data (1 tool: match_practice), but cannot delete data. 5 tools only read.
2 tools read private data (search_providers and list_categories); 3 tools bring in text other people can write (search_providers, get_ehr_product_detail and practice_data_counts).
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 2 times since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 1.1.1.
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.
6 tools
Changes things 1Claude Code: ask
match_practiceRecommend and rank the best healthcare vendors for a specific medical practice.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 Recommend and rank the best healthcare vendors for a specific medical practice. Use this when a practice manager, physician, or administrator asks for a recommendation, e.g. "recommend a medical billing / RCM company for my practice", "who should I use for credentialing / payer enrollment", "find an EHR for my small [specialty] practice", or "which practice-management software fits a [size] practice in [city, state]". Scores and ranks providers against the practice profile (specialty, size, location, EHR system, budget) and returns up to 5 merit-ranked matches (completeness-scored, no paid placement) with {company_name, category, city, state_abbr, quality_score (0-100; profile completeness -- how many listing fields are filled in -- not a quality or reputation rating; 0 means never scored), final_score (0-100), description, website, profile_url, slug}. Use service_needs to specify up to six controlled service codes for staffing, billing or credentialing; codes must belong to the requested category. Use vendor_geo_preference to prefer local or state vendors, allow national vendors, or request only national or explicitly serves-your-state vendors. State is the practice location and may be omitted only with NATIONAL_OK or NATIONAL_ONLY; category remains required. Capability evidence, geography basis, profile extraction date and service-need coverage are returned where available; missing evidence is unknown, never a verified or paid badge. For open-ended browsing without a practice profile, use search_providers. Pass a match's slug to get_provider_detail for the full profile.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
Only reads 5Show 5 read-only tools
get_ehr_product_detailRead the free versioned EHR product JSON projection by exact product key.Reads text others writeNo findings
Why it is in this group
- The name "get_ehr_product_detail" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read the free versioned EHR product JSON projection by exact product key. Returns the complete HTTP JSON body, including explicit edition records, facts, plans, conditions, sources and publication metadata. Optional edition_key validates an explicit identity under this product; the full product response is returned unchanged. No alias resolution, edition inheritance, calculation or ranking. Unknown values and open bounds remain unchanged. Company profiles use get_provider_detail.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
- destructiveHint: false
get_provider_detailGet the full profile of one healthcare vendor by slug.No findings
Why it is in this group
- The name "get_provider_detail" says "get": a word for reading.
Description, as the server wrote it Get the full profile of one healthcare vendor by slug. Use this after match_practice or search_providers when the user asks to "tell me more about [vendor]", "what services does [vendor] offer", "where did GPH get this information", or wants contact info or services for a specific provider. Returns company_name, category, city/state, quality_score (0-100; profile completeness, not a quality rating; 0 means never scored), description, services offered, practice_size_fit, phone and website where listed, Google rating and Google review count where present, a Provenance section that labels each fact GPH-researched, Vendor-supplied, GPH-verified or GPH conclusion with its last-checked date where one exists, and the profile URL. No listing carries a verified badge: the legacy verified flag is not a recorded check and is not shown. Where a vendor has been enrichment-extracted, the description, services and practice-size fit come from that extraction, the profile adds certifications and compliance attestations, locations served and founding year where extracted, and the response states the extraction confidence and what it was grounded in (where the extraction abstained on practice-size fit, the legacy listing value is returned and labelled as not extracted); otherwise the legacy listing fields are returned. Slug comes from match_practice or search_providers results; returns an error if the slug is unknown.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
list_categoriesList every service category in the GPH vendor directory with its live provider count.Reads private dataNo findings
Why it is in this group
- The name "list_categories" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "directory": it reads files.
Description, as the server wrote it List every service category in the GPH vendor directory with its live provider count. Call this FIRST when you do not already know which category fits the user's need, when a category search returned nothing, or when the user asks what kinds of vendors are available. Returns all 25 categories with {category, slug, providers}. The category names returned here are the exact values match_practice and search_providers expect (common aliases also resolve). Takes no arguments.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
practice_data_countsCounts practices with headline (strongest-tier) evidence only, by US state and practice segment, from the public Practice Data aggregate endpoint (unit: practices (headline evidenc…Reads text others writeNo findings
Why it is in this group
- The name "practice_data_counts" says "count": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Counts practices with headline (strongest-tier) evidence only, by US state and practice segment, from the public Practice Data aggregate endpoint (unit: practices (headline evidence)). It excludes lower-evidence records, so these numbers are lower than the all-record totals on the Practice Data product pages (507,423 nationally as published there). Cells with fewer than 25 practices are not published (returned with count null and suppressed true). Aggregate counts only: no records or names are returned. Optional state and segment filters narrow the result; the JSON body is returned unchanged.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
- destructiveHint: false
search_providersBrowse and filter the healthcare vendor directory.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "search_providers" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "browse" and "directory": it reads files.
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it Browse and filter the healthcare vendor directory. Use this for open-ended exploration, e.g. "show me medical billing companies in Texas", "list credentialing services", "what EHR vendors are there for cardiology", or when the user wants to page through options rather than get a scored shortlist. Paginated results filtered by category, location, minimum profile-completeness score, curated Tier-1 grade, and practice-size fit; returns a page of providers with {company_name, category, city, state_abbr, quality_score (0-100; profile completeness, not a quality rating; 0 means never scored), contact info, slug}. For a scored recommendation to a specific practice profile, use match_practice instead. Pass a returned slug to get_provider_detail for the full profile.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: 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 data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- 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, 18:57 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
- 1
- Protocol version
- 2024-11-05
- 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 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://gph-mcp-server.pages.dev/mcp: tools/list returned 6 tools to an anonymous client, including match_practice (write)
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.+1 addedView diff
- Added:practice_data_countsOnly reads
Tools1 added.+1 addedView diff
- Added:get_ehr_product_detailOnly reads
Install
Pinned to version 1.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http gph https://gph-mcp-server.pages.dev/mcpclaude mcp add --transport http gph https://gph-mcp-server.pages.dev/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__gph__search_providers",
"mcp__gph__get_provider_detail",
"mcp__gph__list_categories",
"mcp__gph__get_ehr_product_detail",
"mcp__gph__practice_data_counts"
],
"ask": [
"mcp__gph__match_practice"
],
"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 gph. Review it before you use it.
Capability tags behind 4 rules
- mcp__gph__search_providers private-data, untrusted-input
- mcp__gph__list_categories private-data
- mcp__gph__get_ehr_product_detail untrusted-input
- mcp__gph__practice_data_counts 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/io.github.Crindo2/gph-mcp-server/verify?hash=08c2c3e58f0d920312e7f609601b3e9a6b1b9652c564f741806faf4454c28950" | jq -e '.changed == false'Pinned hash 08c2c3e58f0d, from Nov 15, 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/io.github.Crindo2/gph-mcp-server/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Crindo2/gph-mcp-server)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:15 UTC.
GPH Intelligence - Healthcare Vendor Finder MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the GPH Intelligence - Healthcare Vendor Finder MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 1 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 GPH Intelligence - Healthcare Vendor Finder MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the GPH Intelligence - Healthcare Vendor Finder 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 GPH Intelligence - Healthcare Vendor Finder MCP server have?
- 6 tools: 1 write, 5 read. match_practice, search_providers, get_provider_detail, list_categories, get_ehr_product_detail and practice_data_counts.
Does the GPH Intelligence - Healthcare Vendor Finder MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the GPH Intelligence - Healthcare Vendor Finder MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the GPH Intelligence - Healthcare Vendor Finder MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.