Typesense Cloud MCP server
org.typesense/typesense-cloudtypesense.orgstreamable-httpv1.0.1Scanned
Add fast, typo-tolerant search to your site or app, and run the Typesense clusters behind it.
2 tools: 1 can delete or cancel things and 1 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 1 finding
Sign-in required, OAuth metadata published. Remote posture
With Anlyon
1 tool here can delete or cancel 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 Typesense Cloud MCP server can do
The Typesense Cloud MCP server is published by typesense.org, a domain the MCP Registry verified. It has 2 tools. It can delete or cancel things (1 tool: create_claimable_cluster). 1 tool only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.
Its remote endpoint asks for sign-in and publishes OAuth metadata.
Last scanned Oct 21, 2026, version 1.0.1.
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.
2 tools
Deletes or cancels 1Claude Code: deny
create_claimable_clusterCreates a free-tier cluster (0.5 GB memory, 2 vCPU burst, one node) with no account and no credential, in the region nearest the caller unless one is given.1 finding
Why it is in this group
- The name "create_claimable_cluster" says "create": a word for a change.
- The server marks it destructive (destructiveHint: true).
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...burst, one node) with no account and no credential, in the region nearest the caller unles..."
Description, as the server wrote it Creates a free-tier cluster (0.5 GB memory, 2 vCPU burst, one node) with no account and no credential, in the region nearest the caller unless one is given. The answer carries a claim_url for the person you are working with and an access_token for polling; when a ready cluster is on hand it also carries the hostname and an api_key, otherwise status is provisioning and next says what to do (poll get_claimable_cluster about every 60 seconds until ready, and tell the user you are waiting). The api_key reads, writes and searches every collection but cannot delete anything or manage keys; it stays valid for 24 hours after the person claims the cluster. The cluster is deleted 72 hours after creation unless a signed-in person opens the claim_url and claims it into their Typesense Cloud account: give them the link; never open it yourself. Limits per address: 2 clusters per hour, 5 per day.
Annotations the server declares
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Create a free cluster without an account
Only reads 1Show 1 read-only tool
get_claimable_clusterPass the cluster_id from the create answer as id.No findings
Why it is in this group
- The name "get_claimable_cluster" says "get": a word for reading.
Description, as the server wrote it Pass the cluster_id from the create answer as id. Returns the cluster's status: provisioning (poll again in about 60 seconds), ready (with hostname and api_key, on every call until the person claims), claimed, or expired. Authenticate with the access_token from create_claimable_cluster as a bearer token. Limit: 120 calls per hour per cluster.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Get a claimable cluster's status
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, 19:17 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 401
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- yes
- resource_metadata in WWW-Authenticate
- https://cloud.typesense.org/.well-known/oauth-protected-resource/mcp/v1
- RFC 9728 protected resource metadata
- https://cloud.typesense.org/.well-known/oauth-protected-resource/mcp/v1
- Authorization servers
- https://cloud.typesense.org
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
Posture changes
- Oct 29, 2026
- HTTP status of an anonymous initialize: 200 to 401
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 1 to 0
- Protocol version: 2025-06-18 to none
- WWW-Authenticate on 401: not observed to yes
- resource_metadata in WWW-Authenticate: none to https://cloud.typesense.org/.well-known/oauth-protected-resource/mcp/v1
Findings
Matches of fixed checks, with the text they matched.
The description mentions "credential".
What this check looks forMatched text
description: "...burst, one node) with no account and no credential, in the region nearest the caller unles..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 401; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 1 -> 0 (and 3 more).View diff
- HTTP status of an anonymous initialize: 200 to 401
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 1 to 0
- Protocol version: 2025-06-18 to none
- WWW-Authenticate on 401: not observed to yes
- resource_metadata in WWW-Authenticate: none to https://cloud.typesense.org/.well-known/oauth-protected-resource/mcp/v1
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http typesense-cloud https://cloud.typesense.org/mcp/v1claude mcp add --transport http typesense-cloud https://cloud.typesense.org/mcp/v1Run 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__typesense-cloud__get_claimable_cluster"
],
"ask": [],
"deny": [
"mcp__typesense-cloud__create_claimable_cluster"
]
}
}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 typesense-cloud. 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/org.typesense/typesense-cloud/verify?hash=ec6cf7e08252bac8abe766da4ac530e289f737751eee38235da09df14e2bce87" | jq -e '.changed == false'Pinned hash ec6cf7e08252, from Oct 21, 2026, 19:19 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/org.typesense/typesense-cloud/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/org.typesense/typesense-cloud)Source: MCP Registry. Synced Oct 21, 2026, 18:54 UTC.
Typesense Cloud MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Typesense Cloud MCP server safe?
- No scan can promise that. What its definitions show: 2 tools, 1 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Typesense Cloud MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: create_claimable_cluster.
Can the Typesense Cloud 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 Typesense Cloud MCP server have?
- 2 tools: 1 destructive, 1 read. create_claimable_cluster and get_claimable_cluster.
Does the Typesense Cloud MCP server need sign-in or OAuth?
- Yes. Its remote endpoint answered 401 without credentials, and it publishes OAuth protected resource metadata (RFC 9728); its authorization server supports dynamic client registration.
Does the Typesense Cloud MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Typesense Cloud MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 21, 2026.