agenttune MCP server
com.agent-tune/agenttuneagent-tune.comstreamable-httpv1.0.0Scanned
Personality tuning files for AI agents: 43 MIT-licensed tunings + 5 inline personality tests.
6 tools: 6 only read.
- Reads private data · 2
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 agenttune MCP server can do
The agenttune MCP server is published by agent-tune.com, a domain the MCP Registry verified. It has 6 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
2 tools read private data (list_tunings and get_tuning); 1 tool brings in text other people can write (get_free_tools).
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.
Last scanned Nov 10, 2026, version 1.0.0.
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.
6 tools
Only reads 6Show 6 read-only tools
get_free_toolsReturn the free browser tools catalog, destination registry, and local JavaScript API documentation.Reads text others writeNo findings
Why it is in this group
- The name "get_free_tools" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "browser": it reads web pages, which anyone can write.
Description, as the server wrote it Return the free browser tools catalog, destination registry, and local JavaScript API documentation. No personal data is accepted. Download the functions to process instructions locally; this call does not run models or install preferences.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_resourceRetrieve one page-specific Markdown resource by the exact ID from list_resources; includes provenance and evidence status.No findings
Why it is in this group
- The name "get_resource" says "get": a word for reading.
Description, as the server wrote it Retrieve one page-specific Markdown resource by the exact ID from list_resources; includes provenance and evidence status.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_test_specFetch a complete questionnaire specification for mbti (32 items), enneagram (36), disc (16), attachment (36) or big-five (50).No findings
Why it is in this group
- The name "get_test_spec" says "get": a word for reading.
Description, as the server wrote it Fetch a complete questionnaire specification for mbti (32 items), enneagram (36), disc (16), attachment (36) or big-five (50). All five are available, with exact instrument/version IDs, response anchors and strict scoring instructions. The first four preserve the legacy AgentTune adaptations; instrument-specific source terms apply. Administer only when requested, keep responses local, preserve ties, and let users review any suggested communication preferences before installation.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_tuningFetch one tuning file as Markdown with YAML front-matter.Reads private dataNo findings
Why it is in this group
- The name "get_tuning" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "fetch" and "file": it reads files.
Description, as the server wrote it Fetch one tuning file as Markdown with YAML front-matter. The front-matter links to the shared platform registry and installation protocol. structuredContent.body is the preference text; metadata stays separate. Confirmation of saved text is distinct from evaluation of behavior. MIT licensed.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_resourcesSearch the versioned catalog of setup guides, templates, protocols and research.No findings
Why it is in this group
- The name "list_resources" says "list": a word for reading.
Description, as the server wrote it Search the versioned catalog of setup guides, templates, protocols and research. Returns canonical URLs, Markdown URLs, revisions and evidence status.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_tuningsCatalog of all 43 AgentTune personality tuning files (slug, code, name, one-line blurb), optionally filtered by system.Reads private dataNo findings
Why it is in this group
- The name "list_tunings" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "file": it reads files.
Description, as the server wrote it Catalog of all 43 AgentTune personality tuning files (slug, code, name, one-line blurb), optionally filtered by system. Use it to resolve a user's personality type to the right slug before calling get_tuning.
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 outbound.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- 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, 18:33 UTC, unchanged since Oct 22, 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
- 0
- 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
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 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agenttune https://agent-tune.com/mcpclaude mcp add --transport http agenttune https://agent-tune.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": [
"mcp__agenttune__get_free_tools",
"mcp__agenttune__list_tunings",
"mcp__agenttune__get_tuning",
"mcp__agenttune__get_test_spec",
"mcp__agenttune__list_resources",
"mcp__agenttune__get_resource"
],
"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 agenttune. Review it before you use it.
Capability tags behind 3 rules
- mcp__agenttune__get_free_tools untrusted-input
- mcp__agenttune__list_tunings private-data
- mcp__agenttune__get_tuning private-data
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.agent-tune/agenttune/verify?hash=ae17ccd1bc3bd77321e7f90671975d4b1879e9fb4427eb59eb55b9135839d5f7" | jq -e '.changed == false'Pinned hash ae17ccd1bc3b, from Nov 10, 2026, 10:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.agent-tune/agenttune/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.agent-tune/agenttune)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:48 UTC.
agenttune MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the agenttune MCP server safe?
- No scan can promise that. What its definitions show: 6 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 agenttune MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the agenttune 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 agenttune MCP server have?
- 6 tools: 6 read. get_free_tools, list_tunings, get_tuning, get_test_spec, list_resources and get_resource.
Does the agenttune MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the agenttune MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the agenttune MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.