Svix MCP by usefulapi
io.usefulapi/svixusefulapi.iostreamable-httpv1.40.4Scanned
Send and debug webhooks — applications, endpoints, messages, delivery attempts and replays.
19 tools: 5 can delete or cancel things, 1 change things and 13 only read.
- Reads private data · 4
- Reads text others write · 5
- Can send data out · 2
- No findings
The remote endpoint did not answer the last look. Remote posture
Anlyon alternative
6 of these tools change something. Run those 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 Svix MCP by usefulapi can do
The Svix MCP by usefulapi is published by usefulapi.io, a domain the MCP Registry verified. It has 19 tools. It can delete or cancel things (5 tools: svix_create_application, svix_create_endpoint, svix_send_message, svix_resend_message and 1 more) and create or change data (1 tool: svix_health). 13 tools only read.
4 tools read private data (svix_list_messages, svix_get_message, svix_list_attempts_by_message and 1 more); 5 tools bring in text other people can write (svix_get_endpoint, svix_list_messages, svix_get_message and 2 more); 2 tools can send data out of your system (svix_send_message and svix_resend_message). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Oct 25, 2026, version 1.40.4.
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.
19 tools
Deletes or cancels 5Claude Code: deny
svix_create_applicationCreate a new application (one tenant/customer of yours) in the Svix environment.No findings
Why it is in this group
- The name "svix_create_application" says "create": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Create a new application (one tenant/customer of yours) in the Svix environment. Svix REST: POST /api/v1/app.
Annotations the server declares
- title: Create an application
- destructiveHint: true
svix_create_endpointRegister a webhook endpoint URL for one application, optionally scoped to specific event types and channels.No findings
Why it is in this group
- The name "svix_create_endpoint" says "create": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Register a webhook endpoint URL for one application, optionally scoped to specific event types and channels. Svix REST: POST /api/v1/app/{app_id}/endpoint.
Annotations the server declares
- title: Create an endpoint
- destructiveHint: true
svix_recover_endpointReplay every failed message for one endpoint since a timestamp.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 destructive (destructiveHint: true).
Description, as the server wrote it Replay every failed message for one endpoint since a timestamp. Runs as a background task — follow it with svix_list_background_tasks. Svix REST: POST /api/v1/app/{app_id}/endpoint/{endpoint_id}/recover.
Annotations the server declares
- title: Recover an endpoint's failed messages
- destructiveHint: true
svix_resend_messageQueue one message for redelivery to one endpoint.Can send data outNo findings
Why it is in this group
- The name "svix_resend_message" says "resend": a word for sending, and what is sent cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- outboundThe name "svix_resend_message" says "resend": it sends or publishes something to other people.
Description, as the server wrote it Queue one message for redelivery to one endpoint. The usual fix after a customer's endpoint was down. Svix REST: POST /api/v1/app/{app_id}/msg/{msg_id}/endpoint/{endpoint_id}/resend.
Annotations the server declares
- title: Resend a message to one endpoint
- destructiveHint: true
svix_send_messageSend a webhook message to every endpoint of an application subscribed to the event type.Can send data outNo findings
Why it is in this group
- The name "svix_send_message" says "send": a word for sending, and what is sent cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- outboundThe name "svix_send_message" says "send": it sends or publishes something to other people.
Description, as the server wrote it Send a webhook message to every endpoint of an application subscribed to the event type. This delivers real traffic to your customers' URLs. Svix REST: POST /api/v1/app/{app_id}/msg.
Annotations the server declares
- title: Send a message
- destructiveHint: true
Changes things 1Claude Code: ask
svix_healthCheck that the Svix API is reachable and the API key works.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 Check that the Svix API is reachable and the API key works. Returns 200 with an empty body when healthy. Svix REST: GET /api/v1/health.
Annotations the server declares
- title: Check API health
- readOnlyHint: true
Only reads 13Show 13 read-only tools
svix_get_applicationFetch a single application by its Svix id or your own uid.No findings
Why it is in this group
- The name "svix_get_application" says "get": a word for reading.
Description, as the server wrote it Fetch a single application by its Svix id or your own uid. Svix REST: GET /api/v1/app/{app_id}.
Annotations the server declares
- title: Get one application
- readOnlyHint: true
svix_get_endpointFetch a single webhook endpoint, including its URL, subscribed event types and channels.Reads text others writeNo findings
Why it is in this group
- The name "svix_get_endpoint" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Fetch a single webhook endpoint, including its URL, subscribed event types and channels. Svix REST: GET /api/v1/app/{app_id}/endpoint/{endpoint_id}.
Annotations the server declares
- title: Get one endpoint
- readOnlyHint: true
svix_get_endpoint_statsRead delivery statistics for one endpoint — counts of success, pending, sending and fail.No findings
Why it is in this group
- The name "svix_get_endpoint_stats" says "get": a word for reading.
Description, as the server wrote it Read delivery statistics for one endpoint — counts of success, pending, sending and fail. The fastest way to see whether an endpoint is healthy. Svix REST: GET /api/v1/app/{app_id}/endpoint/{endpoint_id}/stats.
Annotations the server declares
- title: Get endpoint delivery stats
- readOnlyHint: true
svix_get_event_typeFetch a single event type by name, including its description and JSON schema.No findings
Why it is in this group
- The name "svix_get_event_type" says "get": a word for reading.
Description, as the server wrote it Fetch a single event type by name, including its description and JSON schema. Svix REST: GET /api/v1/event-type/{event_type_name}.
Annotations the server declares
- title: Get one event type
- readOnlyHint: true
svix_get_messageFetch a single message, including its event type and payload.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "svix_get_message" says "get": a word for reading.
What it can reach
- private-dataThe name "svix_get_message" says "get" and "message": it reads messages.
- private-dataThe description's first sentence says "fetch" and "message": it reads messages.
- untrusted-inputThe name "svix_get_message" says "get" and "message": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "fetch" and "message": it reads messages, which other people can write.
Description, as the server wrote it Fetch a single message, including its event type and payload. Svix REST: GET /api/v1/app/{app_id}/msg/{msg_id}.
Annotations the server declares
- title: Get one message
- readOnlyHint: true
svix_list_applicationsList the applications (your tenants/customers) in the Svix environment.No findings
Why it is in this group
- The name "svix_list_applications" says "list": a word for reading.
Description, as the server wrote it List the applications (your tenants/customers) in the Svix environment. Svix REST: GET /api/v1/app.
Annotations the server declares
- title: List applications
- readOnlyHint: true
svix_list_attempts_by_endpointList delivery attempts against one endpoint, newest first.No findings
Why it is in this group
- The name "svix_list_attempts_by_endpoint" says "list": a word for reading.
Description, as the server wrote it List delivery attempts against one endpoint, newest first. Filter by status to find the failures. Svix REST: GET /api/v1/app/{app_id}/attempt/endpoint/{endpoint_id}.
Annotations the server declares
- title: List delivery attempts for an endpoint
- readOnlyHint: true
svix_list_attempts_by_messageList every delivery attempt Svix made for one message, across endpoints — status, response code and body.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "svix_list_attempts_by_message" says "list": a word for reading.
What it can reach
- private-dataThe name "svix_list_attempts_by_message" says "list" and "message": it reads messages.
- private-dataThe description's first sentence says "list" and "message": it reads messages.
- untrusted-inputThe name "svix_list_attempts_by_message" says "list" and "message": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "message": it reads messages, which other people can write.
Description, as the server wrote it List every delivery attempt Svix made for one message, across endpoints — status, response code and body. This is the tool for answering 'why did this webhook not arrive?'. Svix REST: GET /api/v1/app/{app_id}/attempt/msg/{msg_id}.
Annotations the server declares
- title: List delivery attempts for a message
- readOnlyHint: true
svix_list_background_tasksList Svix background tasks (bulk replays, expunges, imports) with their status.No findings
Why it is in this group
- The name "svix_list_background_tasks" says "list": a word for reading.
Description, as the server wrote it List Svix background tasks (bulk replays, expunges, imports) with their status. Use it to follow up a recover or replay. Svix REST: GET /api/v1/background-task.
Annotations the server declares
- title: List background tasks
- readOnlyHint: true
svix_list_endpoint_messagesList the messages destined for one endpoint, with each message's delivery status.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "svix_list_endpoint_messages" says "list": a word for reading.
What it can reach
- private-dataThe name "svix_list_endpoint_messages" says "list" and "message": it reads messages.
- private-dataThe description's first sentence says "list" and "message": it reads messages.
- untrusted-inputThe name "svix_list_endpoint_messages" says "list" and "message": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "message": it reads messages, which other people can write.
Description, as the server wrote it List the messages destined for one endpoint, with each message's delivery status. Svix REST: GET /api/v1/app/{app_id}/endpoint/{endpoint_id}/msg.
Annotations the server declares
- title: List messages for an endpoint
- readOnlyHint: true
svix_list_endpointsList the webhook endpoints registered for one application.No findings
Why it is in this group
- The name "svix_list_endpoints" says "list": a word for reading.
Description, as the server wrote it List the webhook endpoints registered for one application. Svix REST: GET /api/v1/app/{app_id}/endpoint.
Annotations the server declares
- title: List endpoints
- readOnlyHint: true
svix_list_event_typesList the event types defined in the environment — the catalogue endpoints can subscribe to.No findings
Why it is in this group
- The name "svix_list_event_types" says "list": a word for reading.
Description, as the server wrote it List the event types defined in the environment — the catalogue endpoints can subscribe to. Svix REST: GET /api/v1/event-type.
Annotations the server declares
- title: List event types
- readOnlyHint: true
svix_list_messagesList the webhook messages sent for one application, newest first.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "svix_list_messages" says "list": a word for reading.
What it can reach
- private-dataThe name "svix_list_messages" says "list" and "message": it reads messages.
- private-dataThe description's first sentence says "list" and "message": it reads messages.
- untrusted-inputThe name "svix_list_messages" says "list" and "message": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "message": it reads messages, which other people can write.
Description, as the server wrote it List the webhook messages sent for one application, newest first. Filter by event type, channel, tag or time window. Svix REST: GET /api/v1/app/{app_id}/msg.
Annotations the server declares
- title: List messages
- 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.
40 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.
- Reads private data4
- 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 out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__svix__svix_resend_message",
"mcp__svix__svix_send_message"
]
}
}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, 19:37 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
- Tools that change things, listed without credentials: 6 to 0
- Protocol version: 2025-06-18 to none
- RFC 9728 protected resource metadata: https://svix.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
- Authorization servers: https://svix.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 6 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 6 to 0
- Protocol version: 2025-06-18 to none
- RFC 9728 protected resource metadata: https://svix.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
- Authorization servers: https://svix.usefulapi.io to none
- Dynamic client registration: yes to not observed
- Client ID metadata documents: no to not observed
Install
Pinned to version 1.40.4. Values in angle brackets are yours to fill in.
claude mcp add --transport http svix https://svix.usefulapi.io/mcpclaude mcp add --transport http svix https://svix.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__svix__svix_list_applications",
"mcp__svix__svix_get_application",
"mcp__svix__svix_list_endpoints",
"mcp__svix__svix_get_endpoint",
"mcp__svix__svix_get_endpoint_stats",
"mcp__svix__svix_list_messages",
"mcp__svix__svix_get_message",
"mcp__svix__svix_list_attempts_by_message",
"mcp__svix__svix_list_attempts_by_endpoint",
"mcp__svix__svix_list_endpoint_messages",
"mcp__svix__svix_list_event_types",
"mcp__svix__svix_get_event_type",
"mcp__svix__svix_list_background_tasks"
],
"ask": [
"mcp__svix__svix_health"
],
"deny": [
"mcp__svix__svix_create_application",
"mcp__svix__svix_create_endpoint",
"mcp__svix__svix_send_message",
"mcp__svix__svix_resend_message",
"mcp__svix__svix_recover_endpoint"
]
}
}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 svix. Review it before you use it.
Capability tags behind 7 rules
- mcp__svix__svix_get_endpoint untrusted-input
- mcp__svix__svix_list_messages private-data, untrusted-input
- mcp__svix__svix_get_message private-data, untrusted-input
- mcp__svix__svix_list_attempts_by_message private-data, untrusted-input
- mcp__svix__svix_list_endpoint_messages private-data, untrusted-input
- mcp__svix__svix_send_message outbound
- mcp__svix__svix_resend_message outbound
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/svix/verify?hash=431f4733c8ab81e21a77ef74e0a47f2a58789a89234bf876e3166c22eaaf1a41" | jq -e '.changed == false'Pinned hash 431f4733c8ab, from Oct 25, 2026, 23:19 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.usefulapi/svix/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.usefulapi/svix)Source: MCP Registry · repository. Synced Nov 18, 2026, 11:19 UTC.
Svix MCP by usefulapi: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Svix MCP by usefulapi safe?
- No scan can promise that. What its definitions show: 19 tools, 6 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 Svix MCP by usefulapi delete data?
- Yes. 5 tools can delete, cancel or revoke something: svix_create_application, svix_create_endpoint, svix_send_message, svix_resend_message and svix_recover_endpoint.
Can the Svix 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 Svix MCP by usefulapi have?
- 19 tools: 5 destructive, 1 write, 13 read. svix_create_application, svix_create_endpoint, svix_send_message, svix_resend_message, svix_recover_endpoint, svix_health, svix_list_applications, svix_get_application and 11 more.
Does the Svix MCP by usefulapi need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Svix MCP by usefulapi send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): svix_send_message and svix_resend_message.
Has the Svix MCP by usefulapi changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 25, 2026.