MCP serverio.github.travisbergen2/rpcs1-agent-tuner

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

UNRATEDActivestreamable-httprpcs1.dev

Overview

Score?

UNRATED 0.775

of what a free look can see, on 30 looks

Looks

last 15 hr ago

Tools

More info

URL

rpcs1.dev/mcp

streamable-http

Says it is

rpcs1-agent-tuner 0.4.2

protocol 2025-06-18

In the record since

32 days ago

Among servers18,413 with a card

0median 0.606 · this server 0.775 · highest on record 0.8561

Toolsfrom sha256:9fe6df7ad0…11add4

The tools this server lists, read out of the definition it returned
Tool	Schema
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 the five questions t	input · no output
fork The calibrated ambiguity surface: deterministic structural fork detectors (reference, scope, grouping, compare-vs-choose, polysemy) with character-offset spans, plus per-reading on	input · no output
interpret Detect ambiguity in user messages using the RPCS-1 Signature Ambiguity Framework. Returns AR level (AR0-AR5), confidence, candidate interpretations with scores, clarifying question	input · no output
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.	input · no output
prepare_prompt The inbound half of the Translation Bridge loop. Takes the user’s raw message (possibly ambiguous, fragmented, or underspecified) plus their ReceiverProfile, and returns the recove	input · no output
recommend_agent_configuration Diagnose why a deployed AI agent may fail. Takes environmental entropy, predictability, stakes, context horizon, and commitment style, then returns receiver profile values (TI, SG,	input · output
render_reply The outbound half of the Translation Bridge loop. Takes your draft reply plus the user’s ReceiverProfile and returns deterministic rendering instructions (structure, warmth, explic	input · no output
rewrite Get rewrite instructions for adapting text to a specific style: technical, plain, socially_gentle, concise, detailed, or direct. Use when communication needs tone adjustment.	input · no output
route_intent Entropy routing over competing interpretations — the model proposes, the deterministic core disposes. YOU generate the candidate readings of the user’s message (3–7 short hypothese	input · no output

Verify it yourselfnpx teppi-check https://rpcs1.dev/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2NM68JRVQ0RQ01H8SV7B