# Travisbergen2 Rpcs1 Agent Tuner MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.travisbergen2%2Frpcs1-agent-tuner
Registry id: `mcp-registry/io.github.travisbergen2/rpcs1-agent-tuner`
Status: live (checked 2026-10-26T20:39:39.855Z)

## Verdict

Travisbergen2 Rpcs1 Agent Tuner MCP server answered 99.97% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 925 ms median handshake and 3 outages in 90 days. Its agent-readiness grade is A (96/100) across 9 tools, costing an agent about 3,569 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.97% | 42% of MCP servers |
| Median handshake latency | 925 ms | 26% of MCP servers |
| p95 handshake latency | 3131 ms | — |
| Checks in 30 days | 4,936 | — |
| Outages, 90 days | 3 | — |
| Median recovery | 7 min | — |
| Agent-readiness score | 96/100 (A) | 82% of MCP servers |
| Tools | 9 | — |
| Tool-list size for an agent | ~3,569 tokens | 43% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "travisbergen2-rpcs1-agent-tuner-mcp-serv": {
      "type": "http",
      "url": "https://rpcs1.dev/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http travisbergen2-rpcs1-agent-tuner-mcp-serv https://rpcs1.dev/mcp
```

## Tools (9)

- `calibrate_profile`: Build a ReceiverProfile (TI, SG, FT, UE, AR — continuous 0-100, never a category label) from five behavioral forced-choice answers. Call with NO answers to get 
- `fork`: The calibrated ambiguity surface: deterministic structural fork detectors (reference, scope, grouping, compare-vs-choose, polysemy) with character-offset spans,
- `interpret`: Detect ambiguity in user messages using the RPCS-1 Signature Ambiguity Framework. Returns AR level (AR0-AR5), confidence, candidate interpretations with scores,
- `normalize`: Clean up text with ellipses, fragments, and run-on thoughts into coherent prose. Use when a user types stream-of-consciousness or fragmented input.
- `prepare_prompt`: The inbound half of the Translation Bridge loop. Takes the user’s raw message (possibly ambiguous, fragmented, or underspecified) plus their ReceiverProfile, an
- `recommend_agent_configuration`: Diagnose why a deployed AI agent may fail. Takes environmental entropy, predictability, stakes, context horizon, and commitment style, then returns receiver pro
- `render_reply`: The outbound half of the Translation Bridge loop. Takes your draft reply plus the user’s ReceiverProfile and returns deterministic rendering instructions (struc
- `rewrite`: Get rewrite instructions for adapting text to a specific style: technical, plain, socially_gentle, concise, detailed, or direct. Use when communication needs to
- `route_intent`: Entropy routing over competing interpretations — the model proposes, the deterministic core disposes. YOU generate the candidate readings of the user’s message 

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.