Search / com.agent-tune/agenttune
agenttune
R0· no sign-inPersonality tuning files for AI agents: 43 MIT-licensed tunings + 5 inline personality tests.
v1.0.0 · active · repository · website · descriptor JSON · versions
Search / com.agent-tune/agenttune
R0· no sign-inPersonality tuning files for AI agents: 43 MIT-licensed tunings + 5 inline personality tests.
v1.0.0 · active · repository · website · descriptor JSON · versions
{
"mcpServers": {
"agenttune": {
"type": "http",
"url": "https://agent-tune.com/mcp"
}
}
}claude mcp add --transport http agenttune https://agent-tune.com/mcp[mcp_servers.agenttune]
url = "https://agent-tune.com/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"agenttune": {
"type": "remote",
"url": "https://agent-tune.com/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"agenttune": {
"type": "http",
"url": "https://agent-tune.com/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=agenttune&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYWdlbnQtdHVuZS5jb20vbWNwIn0%3D"
}{
"servers": {
"agenttune": {
"type": "http",
"url": "https://agent-tune.com/mcp"
}
}
}{
"mcpServers": {
"agenttune": {
"httpUrl": "https://agent-tune.com/mcp"
}
}
}extensions:
"agenttune":
enabled: true
name: "agenttune"
type: streamable_http
uri: "https://agent-tune.com/mcp"
timeout: 300
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28protocol.statelessonly applies to 2026-07-28 serversprotocol.transportstreamable HTTPprotocol.list_ttlonly applies to 2026-07-28 serversauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_lengthdescriptions are concisetools.schemasevery tool has an object input schematools.annotations6 of 6 tools declare readOnlyHint or destructiveHinttools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_tuning (destructiveHint, idempotentHint); get_test_spec (destructiveHint, idempotentHint); list_resources (destructiveHint, idempotentHint); …tools.token_costabout 754 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changes7 tool changes in 30 daysstability.rug_pull2 tools kept their name but changed most of their description in 30 days; review before trusting themdeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packageget_test_specchangedtitle, description, output schemameaning changedFetch a complete, self-contained test specification as Markdown: full item list, response scale, scoring algorithm, and the mapping from result to tuning slug. Administer the items to the user inline (bulk-paste is fine), score per the algorithm, then call get_tuning. Tests: mbti (OEJTS, 32 items, ~5 min), enneagram (OEPS, 36, ~5 min), disc (ODAT, 16, ~3 min), attachment (ECR-R, 36, ~5 min), big-five (IPIP-50, 50, ~7 min → maps to ocean files).
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.
get_resourceaddedRetrieve one page-specific Markdown resource by the exact ID from list_resources; includes provenance and evidence status.
list_resourcesaddedSearch the versioned catalog of setup guides, templates, protocols and research. Returns canonical URLs, Markdown URLs, revisions and evidence status.
get_test_specchangedoutput schemaget_tuningchangeddescription, output schemameaning changedFetch one tuning file as Markdown with YAML front-matter. The front-matter is machine-readable install metadata (install.surfaces = where to write it per agent surface, verify.probe = how to confirm it took effect); the body is the behavioral tuning to load as system-prompt content. MIT licensed.
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.
list_tuningschangedoutput schemaget_free_toolsaddedReturn 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.
Full history: list_changes · trend: quality JSON.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +dns-namespace +website +reachable +uptime-97% ~updated-132d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://agent-tune.com/mcp streamable-http | none | yes | 97% | 210 ms | 2025-06-18 | 2026-10-20 |
get_free_toolsread-only | 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. |
get_resourceread-only | Retrieve one page-specific Markdown resource by the exact ID from list_resources; includes provenance and evidence status. |
get_test_specread-only | 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. |
get_tuningread-only | 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. |
list_resourcesread-only | Search the versioned catalog of setup guides, templates, protocols and research. Returns canonical URLs, Markdown URLs, revisions and evidence status. |
list_tuningsread-only | 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. |
Schemas: list_tools.
{
"name": "com.agent-tune/agenttune",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
"remotes": [
{
"url": "https://agent-tune.com/mcp",
"type": "streamable-http"
}
],
"version": "1.0.0",
"repository": {
"url": "https://github.com/bernardjhuang/agenttune",
"source": "github"
},
"websiteUrl": "https://agent-tune.com",
"description": "Personality tuning files for AI agents: 43 MIT-licensed tunings + 5 inline personality tests."
}