AgentCache MCP server
com.myuiaf/agentcachemyuiaf.comstreamable-httpv1.0.1Scanned
Semantic answer cache for agents: reuse answers to repeated or reworded questions, $0.002 per hit.
4 tools: 2 can delete or cancel things and 2 change things.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Sign-in required, OAuth metadata published. Remote posture
With Anlyon
2 tools here can delete or cancel 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 Radar only lists and labels, and these labels are the same either way.
What the AgentCache MCP server can do
The AgentCache MCP server is published by myuiaf.com, a domain the MCP Registry verified. It has 4 tools. It can delete or cancel things (2 tools: delete_entry and purge_namespace) and create or change data (2 tools: lookup and store). None of its tools only reads.
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.
Its remote endpoint asks for sign-in and publishes OAuth metadata.
Last scanned Nov 8, 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.
4 tools
Deletes or cancels 2Claude Code: deny
delete_entryPermanently delete one saved answer by its entry_id (returned by lookup and store).No findings
Why it is in this group
- The name "delete_entry" says "delete": a word for removing or ending something.
- The description says "Permanently delete".
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Permanently delete one saved answer by its entry_id (returned by lookup and store). Free.
Annotations the server declares
- title: Delete a saved answer
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
purge_namespacePermanently delete every saved answer in a namespace (and context), up to 500 per call; call again while "more" is true.No findings
Why it is in this group
- The name "purge_namespace" says "purge": a word for removing or ending something.
- The description says "Permanently delete".
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Permanently delete every saved answer in a namespace (and context), up to 500 per call; call again while "more" is true. Use it when the information behind those answers has changed. Free.
Annotations the server declares
- title: Clear a namespace
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
Changes things 2Claude Code: ask
lookupCall this BEFORE calling a model or paid API.No findings
Why it is in this group
- The name "lookup" says "lookup": a word for reading.
- The description's first verb is "call": a word for a change.
Description, as the server wrote it Call this BEFORE calling a model or paid API. Returns a saved answer if this agent already answered the same question, or a reworded one (similarity >= 0.95 and identical numbers). A hit costs $0.002 from the prepaid wallet; a miss is free. On a miss, answer normally and then call store.
Annotations the server declares
- title: Look up a saved answer
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
storeSave a question and its answer so the next identical or reworded question is a hit.No findings
Why it is in this group
- The name "store" says "store": a word for a change.
Description, as the server wrote it Save a question and its answer so the next identical or reworded question is a hit. Free. Saving the same question again replaces its answer. Do not save personal data or answers that depend on who is asking.
Annotations the server declares
- title: Save an answer
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: 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 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 16, 2026, 14:20 UTC, unchanged since Nov 9, 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://cache.myuiaf.com/.well-known/oauth-protected-resource/mcp
- RFC 9728 protected resource metadata
- https://cache.myuiaf.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://api.myuiaf.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http agentcache https://cache.myuiaf.com/mcpclaude mcp add --transport http agentcache https://cache.myuiaf.com/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": [],
"ask": [
"mcp__agentcache__lookup",
"mcp__agentcache__store"
],
"deny": [
"mcp__agentcache__delete_entry",
"mcp__agentcache__purge_namespace"
]
}
}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 agentcache. 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/com.myuiaf/agentcache/verify?hash=ef8a0c96874e729b94bbd5b784c8067e69c5e5b7436e761c6da3b4fd29276603" | jq -e '.changed == false'Pinned hash ef8a0c96874e, from Nov 8, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.myuiaf/agentcache/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.myuiaf/agentcache)Source: MCP Registry. Synced Nov 13, 2026, 01:17 UTC.
AgentCache MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AgentCache MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 4 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 AgentCache MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: delete_entry and purge_namespace.
Can the AgentCache 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 AgentCache MCP server have?
- 4 tools: 2 destructive, 2 write. delete_entry, purge_namespace, lookup and store.
Does the AgentCache 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 AgentCache MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the AgentCache MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 8, 2026.