# com.agent-tune/agenttune

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

- name: com.agent-tune/agenttune
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 88/100
- quality: 69/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.agent-tune%2Fagenttune
- tools: https://api.protogrid.dev/v1/servers/com.agent-tune%2Fagenttune/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agenttune": {
      "type": "http",
      "url": "https://agent-tune.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 65
- provenance: 85
- drivers: +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.

## Quality 69/100 (needs work)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no 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_cost`: about 754 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 7 tool changes in 30 days
- fail `stability.rug_pull`: 2 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 754 tokens to load them all
- tool set hash: 6472bdb665a6992fc8d713a5f31cd115
- tools last changed: 2026-09-26T19:32:58.729Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.agent-tune/agenttune.svg)](https://protogrid.dev/servers/com.agent-tune/agenttune)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-09-26 `get_test_spec` changed (title, description, outputSchema) **meaning 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: 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.
- 2026-09-26 `get_resource` added
  - Retrieve one page-specific Markdown resource by the exact ID from list_resources; includes provenance and evidence status.
- 2026-09-26 `list_resources` added
  - Search the versioned catalog of setup guides, templates, protocols and research. Returns canonical URLs, Markdown URLs, revisions and evidence status.
- 2026-09-26 `get_test_spec` changed (outputSchema)
- 2026-09-26 `get_tuning` changed (description, outputSchema) **meaning 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: 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.
- 2026-09-26 `list_tunings` changed (outputSchema)
- 2026-09-26 `get_free_tools` added
  - 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: https://api.protogrid.dev/v1/servers/com.agent-tune%2Fagenttune/changes

## Remotes

- https://agent-tune.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9741379)

## Packages

_none_

## Tools (6)

- `get_free_tools`: 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_resource`: Retrieve one page-specific Markdown resource by the exact ID from list_resources; includes provenance and evidence status.
- `get_test_spec`: 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_tuning`: 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_resources`: Search the versioned catalog of setup guides, templates, protocols and research. Returns canonical URLs, Markdown URLs, revisions and evidence status.
- `list_tunings`: 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.