CourtWatch Agent API MCP server
tech.courtwatch/agent-apicourtwatch.techstreamable-httpv1.2.0Scanned
Pickleball and padel club demand data: query venues, markets and rollups, plus public pages. No key.
4 tools: 2 change things and 2 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 1
- 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.dev only lists and labels, and these labels are the same either way.
What the CourtWatch Agent API MCP server can do
The CourtWatch Agent API MCP server is published by courtwatch.tech, a domain the MCP Registry verified. It has 4 tools. It can create or change data (2 tools: about and data), but cannot delete data. 2 tools only read.
1 tool reads private data (fetch); 1 tool can send data out of your system (data).
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.dev first saw them.
Last scanned Nov 13, 2026, version 1.2.0.
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
Changes things 2Claude Code: ask
aboutWhat CourtWatch (https://courtwatch.tech) measures at pickleball and padel clubs, its plans, free sample day and every document id, plus its sister sites.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 What CourtWatch (https://courtwatch.tech) measures at pickleball and padel clubs, its plans, free sample day and every document id, plus its sister sites.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
dataStructured rows from the Fron Research Data API (https://api.fronresearch.com/v1): markets, venues, bookable slots and rollups of sell-through and modeled revenue.Can send data outNo 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.
What it can reach
- outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Structured rows from the Fron Research Data API (https://api.fronresearch.com/v1): markets, venues, bookable slots and rollups of sell-through and modeled revenue. Without a key every query reads one free sample day for every venue, whatever dates are asked (the response's tier, free_day and range say what was read); a caller that connects to https://fronresearch.com/api/agent with "Authorization: Bearer <key>" reads the history its plan covers (a site's own /api/agent does not forward keys). Start with endpoint index (the sample day and endpoints), then markets or venues to get ids, then metrics. Fields, filters and how to get a key: https://fronresearch.com/data/history/
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
fetchRead one document by id (from search or about).Reads private dataNo findings
Why it is in this group
- The name "fetch" says "fetch": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "document": it reads documents.
Description, as the server wrote it Read one document by id (from search or about). sample/<site> returns that site's free example day as rows, CC BY 4.0.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
searchAsk a question in plain language.No findings
Why it is in this group
- The name "search" says "search": a word for reading.
Description, as the server wrote it Ask a question in plain language. Returns the most relevant passages from CourtWatch's public pages, each with its canonical URL to cite, plus its free sample day. Set site to all to search every Fron Research site.
Annotations the server declares
- readOnlyHint: 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 untrusted-input.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- 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 13, 2026, 11:20 UTC, unchanged since Nov 13, 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://courtwatch.tech/api/agent: tools/list returned 4 tools to an anonymous client, including about (write), data (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:dataChanges things
Install
Pinned to version 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-api https://courtwatch.tech/api/agentclaude mcp add --transport http agent-api https://courtwatch.tech/api/agentRun 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__agent-api__search",
"mcp__agent-api__fetch"
],
"ask": [
"mcp__agent-api__about",
"mcp__agent-api__data"
],
"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 agent-api. Review it before you use it.
Capability tags behind 2 rules
- mcp__agent-api__fetch private-data
- mcp__agent-api__data 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://anlyon.dev/api/v1/servers/tech.courtwatch/agent-api/verify?hash=90430b6a2eda612a227c03ac8d0d39d0dfdb9f6d78af00e72ffba5aa6a84c1cb" | jq -e '.changed == false'Pinned hash 90430b6a2eda, from Nov 13, 2026, 04:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://anlyon.dev/servers/tech.courtwatch/agent-api/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://anlyon.dev/servers/tech.courtwatch/agent-api)Source: MCP Registry. Synced Nov 13, 2026, 04:18 UTC.
CourtWatch Agent API MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the CourtWatch Agent API MCP server safe?
- No scan can promise that. What its definitions show: 4 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 CourtWatch Agent API MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the CourtWatch Agent API 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 CourtWatch Agent API MCP server have?
- 4 tools: 2 write, 2 read. about, data, search and fetch.
Does the CourtWatch Agent API MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the CourtWatch Agent API MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): data.
Has the CourtWatch Agent API MCP server changed its tools?
- Yes, once since anlyon.dev started tracking it, most recently on Nov 13, 2026. Every change is on this page and in its Atom feed.