# RPCS-1 Agent Tuner & Translation Bridge MCP server

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

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-travisbergen2-rpcs1-agent-tuner
- Repository: https://github.com/travisbergen2/rpcs1-sdk
- Website: https://rpcs1.dev/tuner?utm_source=official-mcp-registry&utm_medium=mcp-directory&utm_campaign=listing

## Install
- Endpoint: https://rpcs1.dev/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://rpcs1.dev/mcp

## Tools
- recommend_agent_configuration (Recommend AI 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, FT, UE, AR), platform parameters (temperature, top_p, strategy), regime prediction, reasoning, and warnings. Optionally pass target_model (the actual model id) to attach MEASURED per-model receiver posture (E-LIT table): evidence-graded literalness, truth-override boundary, and translation directives. Deterministic, stateless, read-only — does not store past recommendations. Endpoint: https://rpcs1.dev/mcp
- interpret (Interpret ambiguous human input) - Detect ambiguity in user messages using the RPCS-1 Signature Ambiguity Framework. Returns AR level (AR0-AR5), confidence, candidate interpretations with scores, clarifying questions, and suggested next step. Use when a user says something vague, passive-aggressive, or underspecified. Endpoint: https://rpcs1.dev/mcp
- normalize (Normalize fragmented human input) - Clean up text with ellipses, fragments, and run-on thoughts into coherent prose. Use when a user types stream-of-consciousness or fragmented input. Endpoint: https://rpcs1.dev/mcp
- rewrite (Rewrite text for a target audience) - Get rewrite instructions for adapting text to a specific style: technical, plain, socially_gentle, concise, detailed, or direct. Use when communication needs tone adjustment. Endpoint: https://rpcs1.dev/mcp
- calibrate_profile (Calibrate a user’s receiver 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 to ask the user; call again with their answers (a/b/c per primitive) to get the profile. Store the returned profile JSON in the user’s notes or memory and pass it to render_reply / prepare_prompt on every turn. Deterministic and stateless — nothing is stored server-side. Schema: https://rpcs1.dev/v1/receiver-profile.json Endpoint: https://rpcs1.dev/mcp
- prepare_prompt (Prepare a user’s message before acting on it) - 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 recovered intent, a canonical translation to act on, ambiguity level, and — profile-aware — whether to clarify or commit. Call this before acting on any ambiguous user request. Scope note: its detectors are lexical/structural (vague signals, ambiguous references) — for the commit-vs-clarify DECISION, route_intent (with your own proposed readings) is the authority; when they disagree, follow route_intent. Endpoint: https://rpcs1.dev/mcp
- render_reply (Render a reply for a specific user’s receiver profile) - The outbound half of the Translation Bridge loop. Takes your draft reply plus the user’s ReceiverProfile and returns deterministic rendering instructions (structure, warmth, explicitness, revision posture, ambiguity handling — each with a why-trace). Apply the instructions to your draft before answering. Call this on every reply to a calibrated user. Endpoint: https://rpcs1.dev/mcp
- route_intent (Route an ambiguous request: commit, present options, or clarify) - 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 hypotheses covering the plausible interpretations, INCLUDING likely-typo readings, idiom-vs-literal readings, and domain senses) and pass them as hypotheses, ideally with your own likelihoods (0–1 per reading) AND a paraphrase per reading — the user’s message rewritten unambiguously under that interpretation, so the user can VERIFY intent by recognition before anything commits (one misread prompt skews a whole thread). The router computes the posterior and its normalized entropy T̂ and returns the decision: commit (one reading dominates), commit_with_note (close alternative disclosed), present_options (several readings live), or clarify (ask before acting — open-endedly when nothing discriminates). Thresholds adapt to the user’s ReceiverProfile (AR widens/narrows the commit region; high FT discloses near-ties). This tool is the commit-vs-clarify AUTHORITY in the pipeline. Omitting hypotheses falls back to a generic six-intent PRODUCT-ROUTING starter set — do not use the fallback for interpreting arbitrary sentences. Deterministic, stateless, read-only. Benchmarked: RTEB v1.1 (developer-bench grade; see docs/routing.md). Endpoint: https://rpcs1.dev/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.travisbergen2
- Version: 0.3.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 28, 2026
- Source: https://registry.modelcontextprotocol.io