protogrid

Search / com.agent-tune/agenttune

agenttune

R0· no sign-in

Personality tuning files for AI agents: 43 MIT-licensed tunings + 5 inline personality tests.

v1.0.0 · active · repository · website · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality69needs work
Trust88of 100
Uptime, 30 days97%
Latency p50210 ms

Connect

8 clients · secrets stay placeholders
{
  "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

Quality 69 / 100needs work

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene86 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations6 of 6 tools declare readOnlyHint or destructiveHint
  • fail
    tools.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); …
  • pass
    tools.token_costabout 754 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability25 · weight 15
  • warn
    stability.changes7 tool changes in 30 days
  • fail
    stability.rug_pull2 tools kept their name but changed most of their description in 30 days; review before trusting them
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

6 tools, about 754 tokens to load them all · tool set 6472bdb665a6 · tools last changed 2026-09-26 · checked 2026-10-20 10:35 UTC

Tool changes

  • get_test_specchangedtitle, description, output schemameaning changed
    before

    Fetch 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).

    after · 20% of words in common

    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_resourceadded

    Retrieve one page-specific Markdown resource by the exact ID from list_resources; includes provenance and evidence status.

  • list_resourcesadded

    Search the versioned catalog of setup guides, templates, protocols and research. Returns canonical URLs, Markdown URLs, revisions and evidence status.

  • get_test_specchangedoutput schema
  • get_tuningchangeddescription, output schemameaning changed
    before

    Fetch 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.

    after · 30% of words in common

    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 schema
  • get_free_toolsadded

    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.

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.

Trust 88 / 100

provenance85
liveness99
freshness65
hygiene100

+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.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://agent-tune.com/mcp streamable-httpnoneyes97%210 ms2025-06-182026-10-20

Tools (6)

get_free_toolsread-onlyReturn 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-onlyRetrieve one page-specific Markdown resource by the exact ID from list_resources; includes provenance and evidence status.
get_test_specread-onlyFetch 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-onlyFetch 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-onlySearch the versioned catalog of setup guides, templates, protocols and research. Returns canonical URLs, Markdown URLs, revisions and evidence status.
list_tuningsread-onlyCatalog 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.

Similar MCP servers

Official server.json
{
  "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."
}