Canvas Medical MCP by usefulapi
io.usefulapi/canvas-medicalusefulapi.iostreamable-httpv1.41.0Scanned
Search and read a patient chart over the Canvas FHIR R4 API. Read-only.
4 tools: 4 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
The remote endpoint did not answer the last look. Remote posture
Anlyon alternative
Run the operations that matter as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Canvas Medical MCP by usefulapi can do
The Canvas Medical MCP by usefulapi is published by usefulapi.io, a domain the MCP Registry verified. It has 4 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Oct 25, 2026, version 1.41.0.
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
Only reads 4Show 4 read-only tools
canvas_get_capability_statementFetch the server's FHIR CapabilityStatement — exactly which resources, interactions and search parameters this Canvas instance supports.No findings
Why it is in this group
- The name "canvas_get_capability_statement" says "get": a word for reading.
Description, as the server wrote it Fetch the server's FHIR CapabilityStatement — exactly which resources, interactions and search parameters this Canvas instance supports. Read it when a search is rejected and you want to know what the instance actually accepts. Canvas: GET /metadata.
Annotations the server declares
- title: Get the FHIR capability statement
- readOnlyHint: true
canvas_get_patient_everythingFetch a patient's full record in one FHIR bundle — conditions, medications, observations, encounters and more.No findings
Why it is in this group
- The name "canvas_get_patient_everything" says "get": a word for reading.
Description, as the server wrote it Fetch a patient's full record in one FHIR bundle — conditions, medications, observations, encounters and more. The fastest way to answer a broad question about one person, but it can return a large document, so prefer canvas_search when you know which resource you need. Canvas: GET /Patient/{id}/$everything.
Annotations the server declares
- title: Get everything for one patient
- readOnlyHint: true
canvas_readFetch a single FHIR resource by type and id.No findings
Why it is in this group
- The name "canvas_read" says "read": a word for reading.
Description, as the server wrote it Fetch a single FHIR resource by type and id. Canvas: GET /{resource}/{id}.
Annotations the server declares
- title: Read one FHIR resource
- readOnlyHint: true
canvas_searchSearch any supported FHIR R4 resource in the chart.No findings
Why it is in this group
- The name "canvas_search" says "search": a word for reading.
Description, as the server wrote it Search any supported FHIR R4 resource in the chart. Pick `resource`, then narrow with the standard FHIR search parameters. Nearly every clinical question starts here: Condition or Observation for a problem list and results, MedicationRequest for prescriptions, Appointment or Encounter for visits, DocumentReference for notes. Canvas: GET /{resource}.
Annotations the server declares
- title: Search a FHIR resource
- readOnlyHint: true
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 20, 2026, 19:33 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- no
- HTTP status of an anonymous initialize
- not observed
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- 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
The probe stopped: The server redirected a POST to a different request.
Posture changes
- Oct 29, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Protocol version: 2025-06-18 to none
- RFC 9728 protected resource metadata: https://canvas-medical.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
- Authorization servers: https://canvas-medical.usefulapi.io to none
- Dynamic client registration: yes to not observed
- Client ID metadata documents: no to 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.
PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 5 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Protocol version: 2025-06-18 to none
- RFC 9728 protected resource metadata: https://canvas-medical.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
- Authorization servers: https://canvas-medical.usefulapi.io to none
- Dynamic client registration: yes to not observed
- Client ID metadata documents: no to not observed
Install
Pinned to version 1.41.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http canvas-medical https://canvas-medical.usefulapi.io/mcpclaude mcp add --transport http canvas-medical https://canvas-medical.usefulapi.io/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__canvas-medical__canvas_search",
"mcp__canvas-medical__canvas_read",
"mcp__canvas-medical__canvas_get_patient_everything",
"mcp__canvas-medical__canvas_get_capability_statement"
],
"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 canvas-medical. 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/io.usefulapi/canvas-medical/verify?hash=1572b2a289ff1ed8acd2ad5e83c0d09f4b65b434bb846b6c02312f993953efc1" | jq -e '.changed == false'Pinned hash 1572b2a289ff, from Oct 25, 2026, 23:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.usefulapi/canvas-medical/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.usefulapi/canvas-medical)Source: MCP Registry · repository. Synced Nov 21, 2026, 08:17 UTC.
Canvas Medical MCP by usefulapi: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Canvas Medical MCP by usefulapi safe?
- No scan can promise that. What its definitions show: 4 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 Canvas Medical MCP by usefulapi delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Canvas Medical MCP by usefulapi 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 Canvas Medical MCP by usefulapi have?
- 4 tools: 4 read. canvas_search, canvas_read, canvas_get_patient_everything and canvas_get_capability_statement.
Does the Canvas Medical MCP by usefulapi need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Canvas Medical MCP by usefulapi send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Canvas Medical MCP by usefulapi changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 25, 2026.