io.github.travisbergen2/rpcs1-agent-tuner

up checked 2026-11-11T03:38:39.039Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

RPCS-1 Agent Tuner & Translation Bridge

Publisher-provided description

Find your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.

Summary by lookupd

Tunes AI agent runtime settings, detects ambiguous user prompts, and rewrites or routes messages to clarify intent for an agent.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http rpcs1-agent-tuner https://rpcs1.dev/mcp

Codex, remote (streamable-http)

codex mcp add rpcs1-agent-tuner --url https://rpcs1.dev/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "rpcs1-agent-tuner": {
      "url": "https://rpcs1.dev/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (9 tools)

Publisher-provided text

• 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
• interpret Detect ambiguity in user messages using the RPCS-1 Signature Ambiguity Framework. Returns AR level (AR0-AR5), confidence, candidate interpretations with scores,
• fork The calibrated ambiguity surface: deterministic structural fork detectors (reference, scope, grouping, compare-vs-choose, polysemy) with character-offset spans,
• 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.
• rewrite Get rewrite instructions for adapting text to a specific style: technical, plain, socially_gentle, concise, detailed, or direct. Use when communication needs to
• 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
• 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
• 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
• route_intent Entropy routing over competing interpretations — the model proposes, the deterministic core disposes. YOU generate the candidate readings of the user’s message

Details

• Version: 0.3.0
• Transports: streamable-http
• Uptime (7 days): 100%
• Median latency: 350 ms
• First indexed: 2026-11-01T09:58:26.397Z
• Last seen in registry: 2026-11-01T09:58:26.427Z
• Repository: https://github.com/travisbergen2/rpcs1-sdk
• Website: https://rpcs1.dev/tuner?utm_source=official-mcp-registry&utm_medium=mcp-directory&utm_campaign=listing

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.travisbergen2/rpcs1-agent-tuner.svg)](https://lookupd.com/servers/io.github.travisbergen2/rpcs1-agent-tuner)

• 62141 servers
• Last crawl: 2026-11-11T18:17:25.333Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp